Implementation of ICCV19 Paper "Learning Two-View Correspondences and Geometry Using Order-Aware Network"

Official code for PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking (ICCV 2023)

[CVPR 2023] DynamicStereo: Consistent Dynamic Depth from Stereo Videos.

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild. ECCV 2022.

My Curriculum Vitae

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

3D Gaussian Splat Editor

Unofficial implementation of "Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting", ECCV2024.

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving

Let us control diffusion models!

Medical SAM 2: Segment Medical Images As Video Via Segment Anything Model 2

CoTracker is a model for tracking any point (pixel) on a video.

The repository provides code for training/fine tune the Meta Segment Anything Model 2 (SAM 2)

Differentiable gaussian rasterization with depth, alpha, normal map and extra per-Gaussian attributes, also support camera pose gradient

A collaboration friendly studio for NeRFs

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi Xie, Andrew Zisserman

The implementation of the technical report: "Customized Segment Anything Model for Medical Image Segmentation"

code for "PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction"

Web-based 3D visualization + Python

Tracking Any Point (TAP)

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

CUDA accelerated rasterization of gaussian splatting