DreamCinema: Cinematic Transfer with Free Camera and 3D Character

code for CVPR'24 "AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents"

Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)

[SIGGRAPH'24] A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose

[ECCV 2024]"FSGS: Real-Time Few-Shot View Synthesis using Gaussian Splatting", Zehao Zhu*, Zhiwen Fan*, Yifan Jiang, Zhangyang Wang

[CVPR 2024] DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

Project Page for Paper "Deep Learning-Based Object Pose Estimation: A Comprehensive Survey"

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

[ECCV 2024] EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion.

Code repository for "ZeroShape: Regression-based Zero-shot Shape Reconstruction".

An open source implementation of CLIP.

AnyLoc: Universal Visual Place Recognition (RA-L 2023)

[ECCV2022] Masked Autoencoders for Point Cloud Self-supervised Learning

Tooling for the Common Objects In 3D dataset.

DUSt3R: Geometric 3D Vision Made Easy

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

English version of slam in autunomous driving

Offical Pytorch Implementation of CVPR2024 KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation

GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering

Mobile manipulation research tools for roboticists

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