A unified framework for 3D content generation.

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)

🦜🔗 Build context-aware reasoning applications

Multimodal-GPT

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

Poisson Surface Reconstruction for LiDAR Odometry and Mapping

A modular RL library to fine-tune language models to human preferences

NDJIR: Neural Direct and Joint Inverse Rendering for Geometry, Lights, and Materials of Real Object

PhyCV: The First Physics-inspired Computer Vision Library

A playbook for systematically maximizing the performance of deep learning models.

Open Source Graph Neural Net Based Pipeline for Image Matching

OpenXRLab Structure-from-Motion Toolbox and Benchmark

Deep SR-HDR: Joint Learning of Super-Resolution and High Dynamic Range Imaging for Dynamic Scenes

Official implementation of SPTS: Single-Point Text Spotting (ACM MM 2022 Oral)

[WACV 2023] Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Human Performance Modeling and Rendering via Neural Animated Mesh (Published in SIGGRAPH Asia 2022)

[TPAMI 2024 & CVPR 2022] Attention Concatenation Volume for Accurate and Efficient Stereo Matching

Distributed and Graph-based Structure from Motion. This project includes the official implementation of our Pattern Recognition 2020 paper: Graph-Based Parallel Large Scale Structure from Motion.

Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification (TPAMI 2022)

Learning Generative Models of Textured 3D Meshes from Real-World Images, ICCV 2021

DS-SLAM: Real-Time Dynamic SLAM Using Semantic Segmentation Methods

Minimal keyword extraction with BERT

Code for "Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning (EMNLP 2022)"

A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

CVPR 2022: https://caoang327.github.io/FWD/

Adversarial Texture Optimization from RGB-D Scans (CVPR 2020).

[ICLR 2023] "Is Attention All NeRF Needs?" by Mukund Varma T*, Peihao Wang* , Xuxi Chen, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang