-
Beijing University of Posts and Telecommunications
- Beijing, China
Highlights
- Pro
Reconstruction
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"
Source code for the paper "Volumetric 3D Reconstruction with Transformers for Voxel-wise View Selection and Fusion"
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation
Code for "DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion" (CVPR 2021)
DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting
[NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral
Instant neural graphics primitives: lightning fast NeRF and more
[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM
This repository implements our CVPR2022 paper "BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion"
[ICCV2023] GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
[CVPR 2023] Code for "VisFusion: Visibility-aware Online 3D Scene Reconstruction from Videos"
Official Implementation of CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction
Code for "AutoRecon: Automated 3D Object Discovery and Reconstruction" CVPR 2023 (Highlight)
Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
COLMAP - Structure-from-Motion and Multi-View Stereo
(ECCV 2022) Code for Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency
Official Code: 3D Scene Reconstruction from a Single Viewport
[CVPR'20] Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement
User-friendly, commercial-grade software for processing aerial imagery.