#
Liumouliu
Follow
Starred repositories
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
Official implementation of "Decentralization and Acceleration Enables Large-Scale Bundle Adjustment"
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.
[ECCV'20] Convolutional Occupancy Networks
Ongoing research training gaussian splatting at scale by distributed system
Pointcept: a codebase for point cloud perception research. Latest works: PTv3 (CVPR'24 Oral), PPT (CVPR'24), OA-CNNs (CVPR'24), MSC (CVPR'23)
Code for the paper "Contrastive Clustering" (AAAI 2021)
Roof Information Dataset for CV-Based Photovoltaic Potential Assessment
Official repository for CVPR 2024 highlight paper 4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations.
A python wrapper for gco-v3.0 package, used for graph cuts based MRF optimization.
CUDA integration for Python, plus shiny features
[ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes
Code for "SAM-guided Graph Cut for 3D Instance Segmentation"
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation
PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images
[CVPR 2023] L2G-NeRF: Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields
Machine Learning use in edge and corner detection in point clouds
Official implementation for "UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction" (KDD 2024)
Techniques for deep learning with satellite & aerial imagery
Polygonal Surface Reconstruction from Point Clouds
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
HEDNet (NeurIPS 2023) & SAFDNet (CVPR 2024 Oral)