Stars
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
Transparent Image Layer Diffusion using Latent Transparency
The official repo for [NeurIPS'23] "SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model"
Code for paper 《Efficient Multi-view Stereo by Iterative Dynamic Cost Volume》
A collaboration friendly studio for NeRFs
Plenoxels: Radiance Fields without Neural Networks
NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning
A small ROS package for visualizing trajectory from stream of pose or odometry messages
Continual SLAM: Beyond Lifelong Simultaneous Localization and Mapping through Continual Learning. http://continual-slam.cs.uni-freiburg.de
3D City Database - The Open Source CityGML Database
The ultimate list of open data semantic 3D city models
[ICCV 2021] Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation
Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"
Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral
GSOC-2K18: This project uses dense optical flow based on FlowNet2 model, to estimate the VO trajectory.
PyTorch C++ implementation for single-image relative depth estimation (MiDaS)
Official implementation of the paper: MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (CVPR 2021)
CVPR 2021 "Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias"
MD-SLAM: Multi-cue Direct SLAM. Implements the first photometric LiDAR SLAM pipeline, that works withouth any explicit geometrical assumption. Universal approach, working independently for RGB-D an…
A dataset to facilitate the research of Structure-from-Motion (SfM) for movie and TV shows.
RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization, CVPR 2022
PlenOctree Volume Rendering (supports CUDA & fragment shader backends)
Semantic LIDAR odometry and mapping for cylinderical objects (e.g. trees in forests)