Dave Z. Chen

Text2Tex. [ICCV 2023] Text2Tex: Text-driven Texture Synthesis via Diffusion Models

ScanRefer. [ECCV 2020] ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language

SceneTex. [CVPR 2024 Highlight] SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors

Pointnet2.ScanNet. PointNet++ Semantic Segmentation on ScanNet in PyTorch with CUDA acceleration

Scan2Cap. [CVPR 2021] Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

D3Net. [ECCV2022] D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding

image-captioning. Image captioning models "show and tell" + "show, attend and tell" in PyTorch

3d-captioning. Generate descriptions automatically for 3D shapes in ShapeNet via cross-modal joint embedding

ScanRefer_Browser. JavaScript

faster-captioning. Python

ConvRNN. Implementations of convolutional recurrent neural cells

vision_language. This is a repository for the papers and materials in Image Captioning, Text-to-Image Generation and Image-Text Matching

dl4cv. Solutions for assignment of Deep Learning for Computer Vision

CVPR2021-Papers-with-Code. CVPR 2020 论文开源项目合集

3D-SIS. [CVPR'19] 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans

3D-Machine-Learning. A resource repository for 3D machine learning

ScanNet. C

PlyMerge. Python

phpc. My lecture notes of Parallel and High Performance Computing

flink-eagle-eye. A search engine developed with Big Data Science Lab at University of Munich