-
The Chinese University of Hong Kong
- Hong Kong
- Homepage: https://wrld.github.io/
- in/jiaxin-guo-043a6b1b8
- https://www.researchgate.net/profile/Jiaxin-Guo-6
Stars
[NeurIPS] 3D Visual Illusion Depth Estimation
A real-time material point method (MPM) simulation library using CUDA.
Official implementation of “4D LangVGGT: 4D Language-Visual Geometry Grounded Transformer”
[Arxiv'25] SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images
Towards a Generative 3D World Engine for Embodied Intelligence
GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting
ViPE: Video Pose Engine for Geometric 3D Perception
PyTorch code and models for VJEPA2 self-supervised learning from video.
[ICCV 2025] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
[ICCV 2025] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation
3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding
[ICCV 2025 Highlight] BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment
Wan: Open and Advanced Large-Scale Video Generative Models
A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.
[Arxiv'25] MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
KALM: Keypoint Abstraction using Large Models for Object-Relative Imitation Learning, ICRA 2025 & CoRL 24 WS
[MICCAI'25 Oral] Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video
[ICLR 2025] Track-On: Transformer-based Online Point Tracking with Memory, and [arXiv 2025] Track-On2: Enhancing Online Point Tracking with Memory
StereoPilot Elastic3D StereoWorld BetterDepth BRIDGE BriGeS ChronoDepth Depth Any Video Depth Anything Depth Pro DepthCrafter Distill Any Depth FE2E GRIN M2SVid MegaSaM Metric3D Metric-Solver MoGe …
[CVPR 2025 Highlight] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"
[ICCV 2025 Highlight] Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
[CVPR 2025] WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
Official implementation of "DepthLab: From Partial to Complete"
A comprehensive list of papers on learning-based image registration, as well as python implementation of various loss functions and evaluation metrics for medical image registration

