Lists (30)
3DSceneReconstruction
4D Video
AI-3D Character
AI-Agent-Coding
AI-Audio
AI-ComfyUI-Nodes
AI-Image
AI-Retouching
Ai Rules
AI-UI
AI-Video
Background-Removal
Camera Caliberation
Claude Code
ClaudeCode_agents
ClaudeCode_commands
ComfyUI
Depth
Depth_video
GLSL
Image Distortion
Image Rectification
inpainting
Lens Correction
Pano_image_generation
Pose_Estimations
Stereo
Tracking
Tracking_Seg_Hands
WebGPU
Stars
A feed-forward 3D foundation model for reconstructing scenes from streaming data
A ThreeJs module to quickly setup a Media Pipe skeletal rig with minimal code.
[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching
Apple's Liquid Glass effect for React
🔮 The Ultimate Apple Liquid Glass UI — Recreated for the Web, powered by WebGL2 & WebGPU
SphereGlue: A Graph Neural Network based feature matching for high-resolution spherical images
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Plug-and-Play Image Restoration with Deep Denoiser Prior (IEEE TPAMI 2021) (PyTorch)
Official code repository for the paper "Neural Light Spheres for Implicit Image Stitching and View Synthesis"
A matting method that combines dynamic 2D foreground layers and a 3D background model.
Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching
[CVPR 2025] Official implementation of paper on depth estimation for AR stereo cameras.
Official implementation of "S²M²: Scalable Stereo Matching Model for Reliable Depth Estimation, ICCV 2025"
[CVPR '24] Official Implementation of Flow-Guided Online Stereo Rectification for Wide Baseline Stereo
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
Wan: Open and Advanced Large-Scale Video Generative Models
[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Official implementation of "DA²: Depth Anything in Any Direction"
A framework to convert any 2D videos to immersive stereoscopic 3D
[ECCV 2024] Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching.
[CVPR 2023] DynamicStereo: Consistent Dynamic Depth from Stereo Videos.
A curated list of awesome Deep Stereo Matching resources
[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision