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.

 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.

 Features include:

• Dynamic parallax scaling

• Zero-parallax tracking

• Edge-aware masking

• Scene-aware stereo dampening

If you're curious how it works or want to dive deeper into the stereo math, check out the official write-up:
📄 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 (4× from 1080p to 4K)

• Parallax Tuning — Independent controls for foreground, midground, and background depth

• 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

• Preview Modes — Heatmap, SBS, Anaglyph, Interlaced

• Built-in 3D Player — Scrub preview frames in VR, SBS, and more

• Export-Ready — Output for YouTube 3D, Oculus Quest, and MP4/MKV/AVI with GPU encoding

 Free to Use. Built for Creators.

VisionDepth3D is 100% free to use with no licensing restrictions.
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! 💙

What’s New in v3.1.8

This release brings performance fixes, new features, and tighter stereo logic for more accurate 3D output:

Major Fixes

• Depth progress label now resets correctly after each render

• Eliminated first-frame lag with warmup logic for ONNX + Hugging Face depth models

 New Features

• Depth of Field (DoF) support added to full render pipeline

• DoF strength now adjustable from GUI + preview window

• Save Presets now allows custom filenames

• Clear CLI notifications for all key operations (render, convert, export)

 Render Pipeline Refactors

• Convergence Offset now fully integrates with subject-aware zero-parallax

• Removed legacy convergence & background shift multipliers

• pixel_shift_cuda logic refined — now reflects true raw stereo parallax

License Notice:
VisionDepth3D is free to use for personal and non-commercial projects only.
Commercial use, modification, or redistribution is not permitted without prior written consent.
Full license terms available in the GitHub repository.