WeitaiKang

PhD student @ Illinois Tech

Chicago

Pinned Repositories

3D-VisTA
Official implementation of ICCV 2023 paper "3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment"
Language:Python197 3 3111
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Language:Python21.2k 158 1.6k2.3k
Mask3D
Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.
Language:Python578 8 168112
Grounded_3D-LLM
Code&Data for Grounded 3D-LLM with Referent Tokens
Language:Python98 6 112
prismatic-vlms
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
Language:Python553 16 40303
Robin3D
Improving 3D Large Language Model via Robust Instruction Tuning
45 4 23
SegVG
[ECCV 2024] SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding
Language:Python503
WeitaiKang.github.io
Weitai's personal website
Language:HTML0 0 01
EDA
[CVPR 2023] EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding
Language:Python112 3 244
Chat-Scene
Code for "Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers" (NeurIPS 2024)
Language:Python130 8 549

WeitaiKang's Repositories

WeitaiKang/SegVG
[ECCV 2024] SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding
Language:Python503
WeitaiKang/Robin3D
Improving 3D Large Language Model via Robust Instruction Tuning
45 4 23
WeitaiKang/WeitaiKang.github.io
Weitai's personal website
Language:HTML0 0 01