dkerjw1

AnimateAnyone

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

LayerDiffuse

Transparent Image Layer Diffusion using Latent Transparency

SAMRS

The official repo for [NeurIPS'23] "SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model"

Effi-MVS

Code for paper 《Efficient Multi-view Stereo by Iterative Dynamic Cost Volume》

nerfstudio

A collaboration friendly studio for NeRFs

GeoNeRF

Generalizing NeRF with Geometry Priors

svox2

Plenoxels: Radiance Fields without Neural Networks

nerf_pl

NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

mega-nerf

trajectory_visualization

A small ROS package for visualizing trajectory from stream of pose or odometry messages

CL-SLAM

Continual SLAM: Beyond Lifelong Simultaneous Localization and Mapping through Continual Learning. http://continual-slam.cs.uni-freiburg.de

3dcitydb

3D City Database - The Open Source CityGML Database

awesome-citygml

The ultimate list of open data semantic 3D city models

DF-VO

Depth and Flow for Visual Odometry

maed

[ICCV 2021] Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation

humor

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

ADOP

manhattan_sdf

Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral

Monocular-visual-odometry

GSOC-2K18: This project uses dense optical flow based on FlowNet2 model, to estimate the VO trajectory.

MiDaS-cpp

PyTorch C++ implementation for single-image relative depth estimation (MiDaS)

MonoRec

Official implementation of the paper: MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (CVPR 2021)

CPP

CVPR 2021 "Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias"

DANCE

mdslam

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 and LiDAR.

small-baseline-camera-tracking

A dataset to facilitate the research of Structure-from-Motion (SfM) for movie and TV shows.

RNNPose

RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization, CVPR 2022

volrend

PlenOctree Volume Rendering (supports CUDA & fragment shader backends)

sloam

Semantic LIDAR odometry and mapping for cylinderical objects (e.g. trees in forests)

Online-Panoptic-3D

Online Panoptic 3D Reconstruction

STAD