-
Carnegie Mellon University
- USA
- @IsaacXiaoyuan
- in/xiaoyuan-isaac-wang
Highlights
- Pro
Lists (17)
Sort Name ascending (A-Z)
Stars
A 3DGS framework for omni urban scene reconstruction and simulation.
Code for "Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting" by Jaewoo Jung, Jisang Han, Honggyu An, Jiwon Kang, Seonghoon Park, and Seungryong Kim
[ICCV 2021] A dataset of non-rigidly deforming objects.
GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting
Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
[CVPR'24] MESA: Matching Everything by Segmenting Anything
[ECCV'24] OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation
High-resolution models for human tasks.
EmbodiedSAM: Online Segment Any 3D Thing in Real Time
LoopSplat: Loop Closure by Registering 3D Gaussian Splats
[ECCV 2024] GenAD: Generative End-to-End Autonomous Driving
Repository relating to "Reinforcement Learning Meets Visual Odometry" (ECCV, 2024).
MOTSFusion: Track to Reconstruct and Reconstruct to Track
Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information
[CVPR 2024] Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras
Official Implementation of paper "Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence"
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
Official codebase for "Any-point Trajectory Modeling for Policy Learning"
code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"
Code for the paper "Language Models are Unsupervised Multitask Learners"
RTG-SLAM: Real-time 3D Reconstruction at Scale Using Gaussian Splatting (ACM SIGGRAPH 2024)
[ECCV 2022] Map-free Visual Relocalization: Metric Pose Relative to a Single Image
[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos