WeitaiKang

3D-VisTA

Official implementation of ICCV 2023 paper "3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment"

Vote2Cap-DETR

[CVPR 2023] Vote2Cap-DETR and [T-PAMI 2024] Vote2Cap-DETR++; A set-to-set perspective towards 3D Dense Captioning; State-of-the-Art 3D Dense Captioning methods

Chat-3D-v2

Code for "Chat-3D v2: Bridging 3D Scene and Large Language Models with Object Identifiers"

RefTeacher

RefTeacher is a strong baseline method for Semi-Supervised Referring Expression Comprehension.

Mask3D

Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.

butd_detr

Code for the ECCV22 paper "Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds"

openscene

[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies

SeqTR

SeqTR: A Simple yet Universal Network for Visual Grounding

WeitaiKang.github.io

EDA

[CVPR 2023] EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding

WeitaiKang/WeitaiKang.github.io