VisionDepth3Dv3.2.4 - Release

VisionDepth3D – Hybrid 2D-to-3D Converter

Convert any 2D video into immersive stereoscopic 3D using AI-powered depth estimation, real-time preview, and fully customizable stereo controls — all built for creators, VR tinkerers, and 3D enthusiasts.

Whether you're producing content for VR headsets, YouTube 3D, or your own Blu-ray collection, VisionDepth3D delivers sharp, artifact-free 3D with GPU-accelerated tools and formats for every workflow.

Download .exe and both .bin files and make sure they are in the same folder before installing

---

Powered by the VisionDepth3D Method

At the core of this app is the VisionDepth3D Method — a custom real-time rendering technique designed to produce smooth, eye-comfortable stereo from AI depth maps.

Core Features of the Method:

• Dynamic parallax scaling
• Zero-parallax tracking
• Edge-aware masking
• Scene-aware stereo dampening

Want to dive deeper into how it works?

📄 Read the Method → VisionDepth3D_Method.md

---

Features

• AI Depth Estimation — Supports 20+ models (DPT, MiDaS, Depth Anything v2, etc.) with CUDA acceleration
• Batch Processing — Smart VRAM-aware queueing for images & video
• 3D Output Modes — Half-SBS, Full-SBS, Interlaced, Anaglyph
• Frame Interpolation — Smooth motion via ONNX RIFE (2×–8×)
• Super Resolution — Real-ESRGAN upscaling (e.g., 1080p → 4K)
• Parallax Tuning — Independent controls for foreground, midground, and background
• Smart Mask Effects — Built-in feathering and ghost suppression
• Audio Tools — Attach AAC, MP3, or WAV using the FFmpeg GUI
• Live Feedback — Real-time FPS, ETA, pause/resume/cancel support
• Preview Modes — Heatmap, SBS, Anaglyph, Interlaced
• Export-Ready — Output for YouTube 3D, Oculus Quest, and MP4/MKV/AVI with GPU encoding

---

Free to Use. Built for Creators.

If you find it helpful, consider donating — every bit goes toward:

• New hardware for testing
• Supporting more depth models
• Continued updates and features

Thanks for supporting open 3D tools!

---

VisionDepth3D v3.2.4 – Changelog

Note: Although the last official version was listed as 3.1.9, several intermediate patches were applied via GitHub and consolidated under version 3.2.4.

---

GUI Enhancements

Inference Steps Control

• Introduced inference_steps_entry field to support user-defined inference steps for diffusion models.
• Includes input validation and fallback handling.
• Dynamically updates on <Return> and <FocusOut> events.

Resolution Dropdown Improvements

• Expanded resolution options to include model-native sizes:
  • 512x256, 704x384, 960x540, 1024x576, and others for improved performance and visual quality.
• Automatically strips display hints like " (DC-Fastest)" for cleaner parsing of dimensions.

CPU Offload Mode Selection

• Added support for multiple modes:
  • "model", "vae", "unet", "sequential", "none"
• The selected value is passed directly to the pipeline logic via offload_mode_dropdown.get().

Sidebar Layout

• Sidebar width increased from 22 to 30 for improved component spacing and usability.

---

DepthCrafter Integration (Work-in-Progress)

Pipeline integration

• load_depthcrafter_pipeline() now supports the following arguments:
  • inference_steps
  • offload_mode
• Additional parameters are currently hardcoded and will be configurable in future updates.
• Device mapping is handled dynamically based on offload_mode:
  • "sequential" runs all operations on the GPU.
  • Other modes selectively offload components to CPU to manage VRAM usage.

---

Stability Fixes and Improvements

• Warm-up logic now includes spinner feedback to prevent GUI freeze during model loading.
• All models, including local ones, now run reliably. However, local models still require manual configuration of inference resolution and batch size due to unresolved dynamic resolution handling.
• invert_var toggle is now functioning correctly for .
• Subject depth smoothing introduced in the 3D pipeline to reduce temporal jitter in estimated depth maps.
• Focal depth consistency added for stereo rendering: subject depth is now shared across both eye views.

---

License Notice

VisionDepth3D is free for personal and non-commercial use only.
Commercial use, modification, or redistribution is not permitted without prior written consent.

Full license terms available in the GitHub repository.

VisionDepth3Dv3.1.8 - ❌ Bugged Release

===========================
📦 VisionDepth3D v3.1.8

GPU-accelerated 2D-to-3D rendering with real-time depth estimation, TensorRT support, and customizable stereo effects.

---

VisionDepth3D v3.1.8 Changelog

Major Fixes

• Fixed bug where the depth progress label wouldn't reset after 3D rendering.
• Added model warmup logic for Hugging Face and ONNX depth estimators (eliminates first-frame lag).

New Features

• Depth of Field (DoF) support added to the full render pipeline.
• DoF blur controlled via GUI slider with tooltip + multi-language support.
• Save Preset dialog now allows custom filename entry.
• Graceful CLI notifications for all major operations.
• DOF controls added to Preview GUI for consistency.

Refactors & Pipeline Logic

• Convergence Offset fully integrates with subject-aware zero-parallax system.
• Removed legacy convergence shifting logic.
• Refactored pixel_shift_cuda: subject shift unclamped.
• Removed background shift multiplier logic — BG shift now reflects true raw value.

---

🔗 GitHub Repository: VisionDepth3D

---

🔧 How to Install

1. Download and run the official Download link in README_INSTALL file:
   [README_INSTALL.md]

2. The script will automatically:

   • Download the full VisionDepth3D archive from Dropbox
   • Extract the contents to a directory of your choice
   • once completed Launch VisionDepth3D_WIN_v3.1.8_x64_Installer.exe to begin actual installation process

⚠️ Important: Ensure all .bin files remain in the same folder as the installer EXE after extraction.

3. (Optional) Drop ONNX or Safetensors models into the /weights folder:
   • Supports RIFE, RealESRGAN, DepthAnything, etc.

---

Troubleshooting (TensorRT / CUDA)

If TensorRT fails to load on launch, ensure these files exist in your /dlls folder:

• nvinfer_*.dll
• nvinfer_plugin_10.dll
• nvinfer_builder_resource_10.dll
• nvonnxparser_10.dll
• cudart64_12.dll
• cublas64_12.dll
• cudnn64_9.dll
  ...etc.

VisionDepth3D will fall back to CUDA or CPU if TensorRT isn't available, but performance may be reduced.

---

Need Help?
Open an issue at:
👉 https://github.com/VisionDepth/VisionDepth3D/issues

VisionDepth3D - Release

VisionDepth3D - Release v3.1.6

---

⚠️ Note on First Launch ⚠️

The program may take a few minutes to load the first time after installing — there's a lot going on under the hood.
Be patient, grab a snack, and you’ll be rendering in no time!

---

Files in This Release (Uploaded Individually)

• VisionDepth3D_WIN_x64_INSTALLER.exe
• VisionDepth3D_WIN_x64_INSTALLER-1.bin
• VisionDepth3D_WIN_x64_INSTALLER-2.bin

Important: Download all three files and place them in the same folder before running the installer.

---

🖥️ Requirements

• Windows 10 or 11
• NVIDIA GPU with CUDA (recommended for real-time performance)
• ffmpeg.exe in the same folder as VisionDepth3D.exe (optional for audio/video features)

ℹ️ If no compatible GPU is found, VisionDepth3D will gracefully fall back to CPU mode.

---

✨ Features

• AI Depth Estimation — Supports 20+ models (DPT, MiDaS, Depth Anything v2, etc.) with CUDA acceleration
• Batch Processing — Smart VRAM-aware queueing for images & video
• 3D Output Modes — Half-SBS, Full-SBS, VR180, Interlaced, Anaglyph, Floating Window
• Frame Interpolation — Smooth motion with ONNX-based RIFE (2x–8x)
• Super Resolution — Real-ESRGAN upscaling (x4 from 1080p → 4K)
• Parallax Tuning — Foreground, midground, and background depth controls
• Smart Mask Effects — Feathering and ghost suppression
• Audio Tools — Attach AAC/MP3/WAV using FFmpeg (GUI-based)
• Live Feedback — Real-time FPS, ETA, cancel/pause/resume
• Preview Modes — Anaglyph, heatmap, interlaced, SBS previews
• Built-in 3D Video Player — Supports scrubbing, VR, SBS, interlaced
• Export Ready — Outputs for Quest, YouTube 3D, MP4/MKV/AVI with GPU encoding

---

🚀 How to Install & Use

Step 1: Run the Installer

Double-click VisionDepth3D_v3.1.6_WIN_x64_Installer.exe to install the app.

Step 2: Download and Install Model Weights

Grab the weights here, then extract the weights/ folder into: C:\Program Files\VisionDepth3D\ to run Ai Upscaling in Frame Tool Tab (Worth It for buttery smooth fps playback and clear image quality)