NJ, USA

Harvey Chang

Advanced
@changhaonan

LLM/VLM Robotics, Video generation Robotics, Scalable Robot-Learning, Non-rigid Reconstruction.

A3VLM. [CoRL2024] Official repo of `A3VLM: Actionable Articulation-Aware Vision Language Model`

122

OVSG. [CoRL2023] Open-Vocabulary Scene-Graph

73

Mono-STAR-demo. [ICRA2023] Demo of Mono-STAR

32

STAR-no-prior. [IROS2022] Project page for Scene-level tracking and reconstruction without object-prior.

14

LGMCTS-D. Python

12

DPS. Python

10

Easy3DViewer. A easy to use 3d visualization pipeline based on three.js.

8

RPLBenchTools. Tools for RPLBench, processing PartNet-Mobility, extracting space.

3

SuperPose. Robust 6D-tracker

3

WebViewer3D. A 3D viewer based on WebGL, enabing pointcloud, graph, mesh.

2

StarHub. A unification library inherited by all STAR-related project

2

LG-MCTS. Official implementation of Language-guided Monte-Carlo Tree Search

2

PointFeatureHub2. A unified frame for easily integrating SOTA point feature pipeline.

1

SStar. Scene-level tracking and reconstruction with semantic information.

1

tacto. Simulator of vision-based tactile sensors.

1

nerf-pytorch. A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

1
16
Apply