-
Institute for Not-so-Advanced Study
- https://quepas.github.io
3d reconstruction
Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"
Plane-Based Optimization of Geometry and Texture for RGB-D Reconstruction of Indoor Scenes
MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects
Papers and resources about RGBD reconstruction in recent years
A Simple Sparse Odometry Dense Mapping RGBD-Reconstruction
A multi-sensor capture system for free viewpoint video.
InstanceFusion: Real-time Instance-level 3D Reconstruction of Indoor Scenes using a Single RGBD Camera
Intrinsic3D - High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting (ICCV 2017)
Real-time 3D-reconstruction from multiple RGBD-sensor streams. Please cite our work when using our software in your own research or publication.
3D reconstruction system to creating detailed scene geometry from range video.
Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects
some personal implementation of 3d object reconstruction, recognition and pose estimation
[Siggraph 2017] BundleFusion: Real-time Globally Consistent 3D Reconstruction using Online Surface Re-integration
3D geometry estimation from RGB-D data using Kinect Fusion approach
Implementation of the KinectFusion approach in modern C++14 and CUDA
[SIGGRAPH 2021] ROSEFusion is proposed to tackle the difficulties in fast-motion camera tracking using random optimization with depth information only.
KinectFusion implemented in Python with PyTorch
ROS node for collecting data from one or more cameras/depth sensors
Implementation of CVPR'20 Oral: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
This project is doing 3D reconstruction using Jetson nano and intel realsense to capture images and reconstruct a mesh model on Google Cloud using openMVG and openMVS algorithm