VisionDepth3D - v4.1.1 Release

VisionDepth3D v4.1.1 Hotfix Update Coming Soon

Hey everyone, quick update.

I’ve been working on a v4.1.1 hotfix for VisionDepth3D. The release is not built yet, but once it is compiled and tested, the .exe installer will be uploaded to the GitHub releases page.

This update is focused mainly on stability, packaging, install issues, FFmpeg detection, diagnostics, and fixing problems users have reported after v4.1.

Main fixes coming in v4.1.1

• Fixed missing FFmpeg and FFprobe issues on clean Windows installs
• Fixed 3D Generator [WinError 2] errors caused by missing external tools
• Improved FFmpeg/FFprobe detection from bundled files, _internal, app folders, and system PATH
• Improved GPU Diagnostics so users can see if FFmpeg, FFprobe, CUDA, GPU, NVENC, and driver info are being detected
• Fixed FPS/Upscale frame extraction getting stuck on Preparing frame extraction
• Improved frame extraction progress behavior
• Improved 3D render audio merging and cleanup for failed/empty audio merge files
• Added safer MP4 audio handling using AAC for better compatibility
• Added a Depth Normalizer toggle in the Depth Engine
• Gated backend debug/log spam behind the Debug button
• Improved packaged .exe render behavior by reducing unnecessary debug output
• Improved installer/setup workflow
• Added cleaner setup file cleanup
• Added uninstall/open install folder improvements
• Prevented old loose source folders from interfering with the bundled app

Depth Engine note

The Depth Normalizer helps make depth output smoother and more stable across frames, but it can slow down depth generation depending on your hardware, model, and resolution.

v4.1.1 adds a toggle so users can choose between smoother depth consistency or faster depth render speed.

3D Generator note

v4.1.1 also adds a new Edge Repair Quality dropdown for the 3D Generator.

This lets users choose how much edge/disocclusion repair they want during 2D-to-3D rendering:

• Off = fastest, but more edge artifacts may appear
• Fast = faster rendering with lighter edge cleanup
• Balanced = recommended default for speed and quality
• High = stronger edge repair with slower render speed
• Showcase = best edge cleanup, slowest render mode

This was added so users can better balance render speed against edge cleanup quality, especially on larger Full-SBS or 4K renders.

Setup Downloader note

The release is not live yet.

Once v4.1.1 is available, you should be able to get it through the VisionDepth3D Setup Downloader / Setup Hub. Keep checking the setup downloader, and when v4.1.1 shows up, you can download and install the latest version from there.

The .exe installer will also be available on the GitHub release page once I finish compiling and testing the build.

Thanks again to everyone reporting bugs and giving feedback. This hotfix is mainly about making VisionDepth3D easier to install, diagnose, and run reliably on more systems.

VisionDepth3D v4.1 Official Release

VisionDepth3D v4.1 Polish Update

VisionDepth3D v4.1 is a major polish, workflow, and usability update built on top of the v4.0 PySide6 rewrite.

Thank you all for your feedback from v4.0. This update brings a major polish pass along with new features, better progress reporting, cleaner layouts, custom themes, and workflow improvements across the app.

VisionDepth3D is continuing to grow into a more complete creative suite for 2D to 3D conversion, depth map generation, depth blending, FPS interpolation, and upscaling.

---

Major Highlights

Core UI and Workflow Polish

• Unified Job Queue progress across more of the app
• Cleaner progress format with percentage, FPS, elapsed time, ETA, CPU, RAM, GPU, and VRAM
• New user-selectable theme system
• New Theme Studio for creating custom themes directly inside VisionDepth3D
• Built-in themes and custom user themes
• Theme reloading without restarting the app
• Adjustable panels and columns across major workflow tabs
• More consistent styling across 3D Generator, Depth Engine, FPS/Upscale, Depth Blender, and Live 3D
• User Guide link added under the Help menu
• Cleaner startup logging

---

3D Generator

• Restored and improved render mode support
• Clearer render modes for:
  • Single Video Render
  • 3D Image Render
  • Batch Video Folder Render
  • Image Folder Render
• Improved image render support
• Correct still-image aspect handling for SBS and anaglyph output
• Improved image folder render progress reporting
• Improved left/right eye output direction
• Better FFmpeg/debug output for frame-size mismatch and export issues
• Improved stereo tuning around foreground curvature, zero parallax, convergence, and pop-out control

---

Depth Engine

• Added video depth preview samples before full render
• Preview samples show original frame and generated depth map side by side
• Added Generate Preview, Previous, Next, and preview counter controls
• Improved Depth Engine processing mode labels
• Fixed Browse behavior for video, video folder, image, and image folder modes
• Improved Depth Engine queue progress reporting
• Normalized legacy depth progress into the shared Job Queue format
• Improved pause, resume, cancel, failed, and done state handling

---

FPS / Upscale

• Added preview generation before full processing
• Preview samples compare Original vs Preview output
• Added preview navigation with Previous, Next, and preview counter
• Added mouse wheel zoom and click-drag panning for preview inspection
• Improved frame extraction progress and completion feedback
• Integrated PySceneDetect progress into the shared Job Queue
• Reorganized Source Tools for frame extraction and scene detection
• Made the Render Plan panel more compact
• Increased preview area usability
• Moved FPS/Upscale processing feedback into the shared Job Queue

---

Depth Blender and Live 3D

• Depth Blender now follows the shared theme system
• Live 3D now follows the shared theme system
• Removed hardcoded styling from these pages
• Improved consistency with the rest of VisionDepth3D
• Added adjustable layouts where needed for a more flexible workspace

---

Theme System

VisionDepth3D now supports official built-in themes and custom user themes.

Official themes:

resources/themes/

User-created themes:

themes/

Theme support includes:

• JSON color themes
• Optional QSS stylesheet themes
• Built-in fallback themes
• User theme overrides
• Reload Themes menu option
• Create Theme tool
• Live theme preview
• Automatic save, reload, and apply workflow

---

Fixes and Stability

• Fixed stylesheet crashes caused by unsafe CSS inside Python f-strings
• Fixed startup crashes from misplaced or missing callback methods
• Fixed Theme Creator method indentation issues during development
• Fixed Qt ampersand display issues in labels such as Detect Scenes & Extract
• Improved Windows light-mode compatibility so the dark UI does not inherit broken white panels
• Improved packaging support for new v4.1 folders such as themes, dialogs, and styles

---

Notes on Performance and ETA

v4.1 improves progress reporting and ETA visibility across the app.

Depth generation now reports more clearly through the shared Job Queue, but ETA is still an estimate. Depth processing depends on several parts of the pipeline, including video decoding, frame resizing, model inference, post-processing, disk writing, and encoding.

GPU and VRAM usage may not always sit at 100%. That does not always mean something is wrong. The GPU handles the depth model, but other parts of the pipeline can still become the bottleneck.

Performance tuning, smarter batching, and better scheduling are still areas I plan to keep improving.

---

Upgrade Note

Users updating from v4.0 should back up:

presets/
weights/

---

Final Notes

v4.0 was the major PySide6 rewrite.

v4.1 is the first major polish and usability pass on top of that foundation.

This update makes VisionDepth3D feel more consistent, more customizable, and easier to use across long 3D, depth generation, depth blending, and FPS/Upscale workflows.

Thank you to everyone testing, giving feedback, and helping shape VisionDepth3D.

VisionDepth3Dv4.0 - Release

VisionDepth3D v4.0 - Major Release!

VisionDepth3D v4.0 is the biggest update to the project so far. This release is focused on the full PySide6 app rewrite, the new VisionDepth3D stereo method, Live 3D, improved depth workflows, better packaging, and a more complete desktop workflow for 2D-to-3D conversion.

Key Highlights

Complete PySide6 interface rewrite

VisionDepth3D has been rebuilt with a modern PySide6 interface, replacing the older Tkinter-style layout with a cleaner desktop application design. The app now includes a modern dark theme, updated tabs, cleaner panels, improved dialogs, better card layouts, a shared queue/progress dock, and GPU/device display in the top bar.

The interface now feels much closer to a proper modern desktop application instead of a rough old-school tool.

New VisionDepth3D stereo pipeline

The 3D Generator has been rebuilt around the updated VisionDepth3D Method. This new pipeline includes subject-aware depth normalization, pop-control depth shaping, structured foreground/midground/background disparity weighting, GPU stereo warping, dynamic convergence, edge-aware shift limiting, contour-safe repair logic, floating-window protection, and stereo debug telemetry.

This release also changes the recommended shift direction:

Foreground Shift: usually negative
Midground Shift: usually slightly negative or near zero
Background Shift: usually positive

Older presets that used positive foreground values may not transfer directly, so users should start from the new v4.0 defaults and rebuild older presets from there.

Live 3D preview

VisionDepth3D v4.0 introduces the new Live 3D tab for realtime 2D-to-3D testing. Live 3D supports camera input, capture cards, screen capture, secondary monitor capture, depth model selection, SBS preview output, passthrough preview, depth preview, and realtime stereo tuning.

Users can select depth models, tune stereo settings, check SBS output, preview depth behavior, and use screen capture to watch or play almost anything in realtime 3D.

Depth Engine updates

The Depth Engine received updates for model handling, video-depth workflows, ONNX behavior, and depth stability. This includes improved Video Depth Anything handling, better ONNX runtime detection, fixed temporal-size handling for VDA ONNX exports, safer trimming for padded final batches, clearer model resolution presets, and better video timing/smoothness testing support.

Video depth workflows also benefit from improved normalization behavior to help reduce depth breathing and flicker with models that produce less stable frame-to-frame depth ranges.

Depth Blender improvements

Depth Blender is now part of the new PySide6 workflow and has received major usability and performance improvements. This includes a GPU-optimized blending path, single image mode, video and frame folder modes, live preview, built-in blend presets, and cleaner controls for CLAHE, bilateral smoothing, feathering, and normalization.

This makes it easier to combine multiple depth sources into a cleaner depth map before stereo rendering.

FPS/Upscale Enhancement improvements

The FPS/Upscale Enhancer has been updated with the new PySide6 layout, cleaner workflow panels, shared progress reporting, and scroll-safe responsive behavior. It supports RIFE interpolation, Real-ESRGAN upscaling, merged and threaded pipelines, scene detection, codec/output settings, and improved render feedback.

This tab is now better integrated into the full VisionDepth3D workflow for preparing smoother or higher-resolution sources before 3D conversion.

Multi-language UI support

VisionDepth3D v4.0 adds multi-language UI support across the main application shell and major workflow tabs. Language files are now loaded from the resources system and include English, French, Spanish, German, Japanese, Simplified Chinese, and Traditional Chinese.

This release includes translated shell tabs, File/Help menu entries, page labels, buttons, group titles, placeholders, status labels, and Live 3D strings.

Better hardware/backend support

VisionDepth3D is still best on NVIDIA CUDA, but v4.0 improves backend detection and fallback paths. This release adds better support and documentation for NVIDIA CUDA, AMD/Intel DirectML on Windows, ROCm detection on Linux, CPU fallback, and FFmpeg NVENC/AMF/QSV/CPU encoding options.

The Windows installer now targets the user AppData folder instead of Program Files, improving write access for weights, presets, settings, downloaded models, and runtime cache files.

Cleaner preset behavior

3D presets now behave more like reusable render profiles instead of project files. Presets no longer overwrite the current input video path, depth map path, or output path, so users can switch between stereo presets without losing their loaded source files.

Packaging and release cleanup

The v4.0 build has been cleaned up for PyInstaller and Inno Setup packaging. Resources, languages, themes, icons, Python modules, and bundled runtime files are kept inside _internal, while the weights folder remains writable beside the executable for downloaded models and runtime assets.

Legacy Tkinter pieces are being separated from the active v4.0 workflow as the app continues moving fully into PySide6.

Notes

• Older presets may need to be rebuilt because of the new v4.0 shift convention.
• The recommended starting point for the new stereo method is:

Foreground Shift: -6.0
Midground Shift:  -0.8
Background Shift: +2.2

• Tooltips are still being expanded and will continue improving in future updates.
• Live 3D is new and will continue receiving performance and usability improvements.
• NVIDIA CUDA remains the recommended backend for best performance.
• The installer now uses AppData to avoid permission issues with model downloads and writable runtime folders.
• This version is a major workflow update, not a small patch release.

Special Thanks

A big thank you to everyone who has tested VisionDepth3D, reported issues, shared feedback, downloaded the project, and followed the development journey so far.

Community testing and feedback helped shape this release across the new PySide6 interface, stereo pipeline tuning, depth workflows, packaging, and release cleanup.

Full Changelog

For the complete update log, see the full changelog here:

VisionDepth3D v4.0 Full Changelog

make sure you back up your weights folder to transfer to the new weights folder so you dont have to redownload depth models

VisionDepth3Dv3.9 - Release

VisionDepth3D v3.9.0

VisionDepth3D v3.9 is a major update focused on workflow stability, model delivery, and overall usability across the 3D, depth, and enhancement pipelines.

Key Highlights

VR180 equirect output support

This release introduces native VR180 equirect stereo output with support for both Top-Bottom and Side-by-Side formats. A dual-resolution workflow was added so flat working resolution and final equirect output resolution can be controlled independently for better performance and quality tuning.

FPS/Upscale Enhancement improvements

The old FrameTools workflow has been renamed and reworked into FPS/Upscale Enhancement. This update includes UI cleanup, pause/resume/stop controls, and major fixes to the threaded RIFE + ESRGAN pipeline for better throughput, safer queue handling, cleaner progress reporting, and improved FFmpeg writer stability.

Hugging Face model delivery

VisionDepth3D now supports downloading and loading supported models directly from Hugging Face instead of relying as heavily on bundled model files. Models are cached locally after download, which reduces shipping size and improves long-term flexibility for updates.

Depth engine fixes and ONNX improvements

The depth pipeline received major fixes for single-video and folder-based processing, including UI freeze fixes, progress bar restoration, safer worker-thread handling, and improved FFmpeg output behavior. ONNX model loading now works from both local folders and Hugging Face repositories, with improved warm-up and compatibility handling for Video Depth Anything and Distill-Any-Depth exports.

Smarter UI behavior

Diffusion-only controls such as Inference Steps and CPU Offload Mode are now hidden unless a compatible diffusion model is selected, helping keep the depth UI cleaner and easier to understand.

3D pipeline reliability improvements

The 3D pipeline now includes better fallback handling for source video metadata when OpenCV fails to report valid FPS or dimensions, improving compatibility across more files and systems.

Notes

• Upscaling Models now downloaded from Hugging Face and cached locally after first download.
• ONNX and diffusion branches received targeted compatibility fixes in this release.
• This version is intended as a broader workflow update and not just a small patch release.

Special Thanks

A big thank you to AcolyteOfHedone for contributing fixes and technical improvements that helped strengthen this release, including AMD AMF encoder fixes, ONNX adjustments, and AMD GPU provider compatibility work.

GitHub: EvolvingProficiency

Full Changelog

For the complete update log, see the full changelog here:

VisionDepth3D v3.9 Full Changelog

VisionDepth3Dv3.8.2 Release

VisionDepth3D v3.8.2

This release brings major depth engine upgrades, large real-time performance gains, and important stability fixes across both offline rendering and live 3D preview.

Expect faster playback, cleaner depth output, improved codec reliability, and a smoother overall workflow.

---

New Depth Engines

Depth Anything 3 (DA3) Integration

• Native DA3 backend (not Hugging Face pipeline based)
• Supports DA3 Small, Base, Large, Giant, and Metric variants
• Proper resolution handling and depth normalization
• Faster warm-up and improved batching support

Video Depth Anything (VDA)

• Sequence-aware video depth inference
• Temporal processing for smoother depth output
• Target FPS control for heavy footage
• Unified post-processing with other depth engines

---

Performance Improvements

Live 3D

• 40 to 70 percent FPS increase on most GPUs
• Persistent GPU buffers eliminating per-frame allocations
• Smoother depth refresh scheduling
• Reduced jitter and stutter

Offline Depth and Rendering

• Single-pass resizing reducing CPU overhead
• Faster FP16 GPU inference
• Optimized ONNX runtime sessions
• FFmpeg piping enabled by default for faster encoding

---

Stability and Quality Fixes

ONNX Models

• Fixed Distill-Any-Depth shape mismatch crashes
• Enforced correct inference resolution (518×518)
• Aspect-ratio safe preprocessing without stretching
• Cleaner backend detection and logging

Letterbox Handling

• Black bars no longer corrupt depth maps
• Neutral depth fill prevents white banding artifacts
• Stable detection across frames

---

3D Generator Improvements

• Full render state reset per clip to eliminate drift artifacts
• Smoother convergence and floating window behavior
• Corrected output sizing for VR, SBS, and interlaced modes
• Optional convergence crosshair overlay in Preview GUI
• Cleaner encoding settings layout

---

GUI and Workflow Enhancements

• Depth Estimation tab renamed to Depth Engine
• Fixed preset loading from menu dropdown
• Fixed Output Path menu action
• Simplified File menu using preset system only
• Built-in VisionDepth3D Updater in Help menu
• Confirmation prompt before updating

---

Upgrade Note

Back up your weights/ and presets/ folders before uninstalling older versions.

Use VisionDepth3D_Setup_Downloader to install v3.8.2 and required .bin files.

---

Thanks to everyone supporting VisionDepth3D and helping shape each release.

VisionDepth3Dv3.8.1 - Release Bug patch

VisionDepth3D v3.8 – Bug Patch

---

1) Depth Estimation Inference Error

• Fixed progress bar error for depth estimation causing error on inference

---

Back up your weights/ and presets/ folders before uninstalling v3.8
Then run VisionDepth3D_Setup_Downloader to download the official
VisionDepth3D v3.8.1 Windows installer and required .bin files.

VisionDepth3Dv3.8 - Release

VisionDepth3D v3.8 – Changelog

---

1) Depth Estimation Tab

Depth Models

• Fixed ONNX model loading:
  • Distill-Any-Depth (inference resolution 518×518, batch size 8)
  • Video Depth Anything (inference resolution 512×288, batch size 8)
• Implemented LBM depth model (dev version). Thanks to Aether for the implementation fix.
• Removed depth models from the dropdown that returned no d_type.
• Fixed Hugging Face model downloads and caching so zoo models consistently save inside the app weights/ directory (no more extra .cache downloads).
• Updated Transformers image processor loading to prefer use_fast=True when available (with automatic fallback when unsupported).

Depth Backend

• Implemented temporal smoothing in the depth pipeline to reduce flicker and improve temporal stability of depth map output.
• Packaged VisionDepth3D.exe with Distill-Any-Depth (ONNX), Video Depth Anything (ONNX), and Depth Anything v2 Giant weights.

---

2) 3D Render Tab

UI Fixes

• Added buttons for encoder settings and processing options.
• Implemented multi-language support and tooltips for new dialog boxes.
• Adjusted preview image window size and video info layout to prevent window overflow.
• 3D tab columns now stack correctly when resizing the window on smaller screens.

3D Backend

• Reworked Auto Crop Black Bars to use first-frame detection with cached crop reuse.
• Prevents per-frame crop jitter and depth/frame misalignment.
• Improves stability for cinema content with subtle letterboxing.
• Keep Audio checkbox now respects the user-selected output container instead of forcing MP4.

---

3) Frametool Backend

• Reworked Frametool backend to support SSResNet models for feature model integration.

---

4) Console Improvements

• Standardized startup console messages to clearly reflect which subsystems are initializing (Torch, depth estimation, upscaler, external 3D pipeline, language, settings).
• Unified compute device reporting across pipelines for consistent and clearer console output.
• Suppressed optional xFormers dependency warning on startup.
• Prevented duplicate language loading during settings restore.

---

Summary

v3.8 focuses on stabilizing depth estimation, improving model compatibility,
and refining the 3D Render tab UI with better layout behavior, clearer diagnostics, and improved localization support.

Back up your weights/ and presets/ folders before uninstalling v3.7.
Then run VisionDepth3D_Setup_Downloader to download the official
VisionDepth3D v3.8 Windows installer and required .bin files.

(Optional but recommended) Clear the Hugging Face cache to free space and
avoid duplicate model downloads:
C:\Users\YOUR_USERNAME\.cache\huggingface

VisionDepth3Dv3.7 - Release

VisionDepth3D v3.7 –Release Changelog

---

1) Live 3D Capture Overhaul

Live 3D Capture received a full stability and quality pass.

What is new:

• Optional live audio passthrough for external capture devices, with device selection and audio delay control.
• Audio routed through DirectShow and WASAPI, with an FFplay based monitor for low latency listening.
• Color channel controls to fix purple and red tint issues on some capture cards.
• Tuning for real time depth inference so Live Capture can run at practical frame rates on 1080p HDMI sources.
• A headless mode (--no-preview) so you can run capture without a local preview window.
• Early groundwork for browser based SBS VR streaming with synchronized audio and video.

What is fixed:

• GUI settings (resolution, backend, FPS and more) are now correctly applied when starting Live Capture from the UI.
• Capture failures like “no frames arriving” are resolved by enforcing the correct fourcc and backend.
• Audio is now present in Live Capture sessions instead of silent output.
• Frame pacing is smoother and depth plus stereo warp no longer hit the same FPS bottlenecks as before.

---

2) Floating Window, Depth Stability and Black Bar Handling

The stereo presentation pipeline has been tightened up for more comfortable 3D.

Dynamic Floating Window (DFW):

• Rebuilt the floating window logic so it masks only one edge at a time, based on the dominant parallax direction.
• Adds a minimum parallax threshold so the window stays off when depth is near the screen plane.
• Uses temporal smoothing and easing so the window glides in and out instead of popping or flickering.
• Supports both soft faded edges and solid black cinema bars through a single toggle.

Result: fewer edge violations, a cleaner frame in VR and on monitors, and a more cinema friendly presentation.

Frame jitter and temporal stability:

• Fixed depth “breathing” where scenes would appear to move in and out over time.
• Introduced several smoothing passes over subject depth, depth percentiles and convergence.
• Added a global parallax smoother for foreground, midground and background layers.

Result: more stable parallax over time, less shimmer and a more comfortable stereo experience.

Auto crop for black bars:

• Improved black bar detection during fades and dark transitions.
• Added guards so detection does not update on very dark frames.
• Handles changes in letterbox height without vertical drift.

Result: 2.35:1 and similar letterboxed content now auto crops in a reliable and repeatable way.

---

3) Unified Depth Pipeline and Platform Support

The Depth tab has been upgraded into a unified, cross platform pipeline.

Multi backend support (CUDA, ROCm, MPS, CPU):

• Device detection has been rewritten so CUDA is no longer assumed by default.
• The app now picks the best available backend automatically.

Supported depth backends:

• CUDA on NVIDIA GPUs
• ROCm on AMD GPUs
• MPS on Apple Silicon
• CPU fallback when no GPU is present

This prevents crashes on AMD and macOS, avoids accidental CPU only runs on capable GPUs, and lays the foundations for Linux builds.

Codec selection for depth exports:

• The Depth tab now has a Video Codec dropdown.
• You can select from hardware encoders (NVENC, AMF, QSV) as well as CPU encoders (libx264, libx265, AV1, and legacy MPEG-4 variants).
• XVID and other problematic codecs now have safer defaults and better behavior on non NVIDIA systems.
• AV1 has guard rails where OpenCV decoding is limited, with warnings where needed.
• Codec support is now aligned with the 3D Converter and FrameTools.

Depth pipeline control:

• Depth renders now support Pause, Resume and Cancel.
• Pauses release resources more safely and cancels avoid corrupt output files.
• Clear status states show when a job is running, paused, canceling or completed.

---

4) 3D Pipeline and UX Polish

The main 3D converter pipeline has been cleaned up and extended.

• New Keep Original Audio option to pass through source audio into the final 3D export without re encoding.
• New image based 3D pipeline that runs through the same renderer, ideal for single frame 3D stills.
• Mode selector is now wired to switch cleanly between Single, Batch and Image workflows inside the same UI.
• A 3D filename suffix system automatically labels exports by format and eye mode
  (examples: _LRF_Full_SBS, _LRF_Half_SBS, _VR, _Anaglyph, _Interlaced, _LRF_Left, _LRF_Right).
• Multi language labels and tooltips across the app have been reviewed and cleaned up.

---

5) Depth Blender Preview

The Depth Blender tab has been upgraded into a more visual tool.

• Live preview now shows the base V2 depth map and the blended result side by side.
• All blend parameters (white strength, feather blur, CLAHE, bilateral filters) update the preview in real time.
• A frame scrubber lets you move through frames in a sequence and see how the blend behaves across time, before running a full batch on folders or videos.

---

Summary

VisionDepth3D v3.7 focuses on stability, cross platform support and workflow quality.

• Live 3D Capture is more stable, more accurate and closer to being stream ready.
• The stereo pipeline has better temporal behavior and cleaner edges.
• The Depth tab now runs on NVIDIA, AMD ROCm, Apple Silicon and CPU only setups with flexible codecs and playback options.
• The 3D converter and Depth Blender both gained quality of life improvements that make it easier to preview, tune and export 3D content.

These changes set the stage for future Linux builds, more advanced streaming paths and additional 3D presets in upcoming releases.

How to Install

1. Go to the VisionDepth3D Releases page
2. Download the latest installer .exe and .bin parts
3. Place all files in the same folder
4. Run the .exe installer and follow the prompts
5. Launch VisionDepth3D from the Start Menu or Desktop shortcut

Download VisionDepth3D Release Installer to simplify fetching most recent releases

For source installation and advanced setup see the Installation Guide.

VisionDepth3Dv3.6.2 - Release

VisionDepth3D v3.6.2 – Bug Patches & Cleanup

Adapters
• Fixed Hugging Face call in depthanything_adapter.py.
• Fixed Depth Anything V2 Giant download in VisionDepth3D.py.

UI & Codec
• Fixed threaded render button.
• Fixed codec bug where output wasn’t respecting selected codec.

Codebase Cleanup
• Removed broken/unused DepthCrafter files (depth_crafter_ppl.py, depthcrafter_adapter.py, weights dir).
• Cleaned up render_depth.py, dropped legacy/unused code.

Assets
• Deleted old previews and logo icon.
• Added updated UI photos.

VisionDepth3Dv3.6 - Release

VisionDepth3D v3.6 Release

This update is all about quality and speed. A brand-new Depth Blender tab lets you mix models with precision for cleaner separation and smoother parallax, while HDR10 handling has been rebuilt to preserve true 10-bit color and metadata. The experimental Live 3D pipeline makes its debut, turning capture cards, consoles, and webcams into real-time 3D feeds. Upscaling and interpolation have been overhauled with threaded workers, dropping render times from 10 hours to ~1 hour on long projects. Add in clip-range rendering, direct Left/Right output, smarter padding, codec fixes, and a full UI overhaul — v3.6 is the most refined and flexible VisionDepth3D yet.

---

1) Upscaling & Interpolation – Massive Speed Boost

• Rewritten Frames tab pipeline with threaded workers + queues
• RIFE, ESRGAN, and FFmpeg writing now run concurrently instead of sequentially
• Intelligent frame indexing and buffering preserve order while maximizing throughput
• Render time reduced from 10 hours → ~1 hour on long clips
• Result: creators can upscale and interpolate full-length videos in a fraction of the time without crashes or dropped frames

---

2) Depth Pipeline – Refinements & Blending

• New Depth Blender tab with sliders for model blend weights
• Improved 16-bit depth output handling for smoother disparity
• Early percentile clipping reduces outliers without flattening depth
• Added Depth Anything V2 Giant model support
• Added FP16 precision toggle for faster inference and reduced VRAM use
• Result: cleaner separation between foreground and background, less fuzz, and more consistent 3D parallax

---

3) HDR10 Support – Preservation & Metadata

• Fixed washed-out HDR outputs when re-encoding
• Preserves:
  • 10-bit pixel format (yuv420p10le)
  • BT.2020 color space
  • PQ curve (smpte2084)
  • HDR metadata (Master Display / MaxCLL)
• UI toggle: Preserve HDR10 Metadata
• Result: HDR content now keeps its original punch and dynamic range

---

4) Experimental Live 3D (WIP)

• Added real-time 3D pipeline for external inputs (consoles, capture cards, webcams)
• Uses Depth Anything v2 Small by default (swap models if GPU allows)
• Stereo conversion powered by the VisionDepth3D method
• End-to-end capture → depth → stereo loop is working
• Early tests show playable 3D console and video feeds
• Performance optimizations ongoing for fps, latency, and GPU acceleration

---

5) General Fixes & Stability

Rendering

• Restored Clip-range UI — set start/end times for partial renders
• Added Left-only / Right-only output modes (no post-split required)
• Extra padding + edge reflection reduce stereo bleed-through
• Optimized per-eye resize, aspect ratio, and DOF/color grading checks
• Fixed floating-window scaling in single-eye renders

UI & Error Handling

• Patched white-edge artifact from 16-bit normalization
• Better error handling when models fail to load
• Synced language packs with new controls (HDR toggle, depth blender, etc.)
• All buttons and inputs styled with a new dark theme

Codec & Output

• Fixed FFmpeg forcing slow presets on GPU codecs
• NVENC now uses correct encoder flags (preset p5, rc vbr, cq)
• CPU codecs retain CRF + preset for consistent quality

---

6) UI & Workflow Enhancements

• Full 3D Generator tab UI overhaul for a cleaner look
• Hotkeys to import video & depth maps directly into workflow
• Save/load presets with one click
• Reset button and quick navigation to docs, bug reports, and GitHub
• Result: smoother daily workflow and better testing inside VD3D

---

Summary

v3.6 delivers depth blending refinements, true HDR10 preservation, and massive speed boosts through concurrent processing.
It restores clip-range flexibility, adds direct eye outputs, and debuts the first Live 3D pipeline, moving VisionDepth3D toward real-time stereo rendering.

---

How to Install

1. Go to the VisionDepth3D Releases page
2. Download the latest installer .exe and .bin parts
3. Place all files in the same folder
4. Run the .exe installer and follow the prompts
5. Launch VisionDepth3D from the Start Menu or Desktop shortcut

Download VisionDepth3D Release Installer to simplify fetching most recent releases

For source installation and advanced setup see the Installation Guide.