There are 14 repositories under rgbd topic.
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
Algorithms and Publications on 3D Object Tracking
3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.
Fuse multiple depth frames into a TSDF voxel volume.
DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting
Easy to use and accurate hand eye calibration which has been working reliably for years (2016-present) with kinect, kinectv2, rgbd cameras, optical trackers, and several robots including the ur5 and kuka iiwa.
MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects
A multi-sensor capture system for free viewpoint video.
Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects
Intrinsic3D - High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting (ICCV 2017)
[IEEE T-RO 2025] iKalibr: Multi-Sensor Calibration (Extrinsics & Time Offsets)
Accompanying library for the Record3D iOS app (https://record3d.app/). Allows you to receive RGBD stream from iOS devices with TrueDepth camera(s).
A paper list of RGBD semantic segmentation (processing)
Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.
[ECCV 2020] PyTorch Implementation of some RGBD Semantic Segmentation models.
MIT-Princeton Vision Toolbox for Robotic Pick-and-Place at the Amazon Robotics Challenge 2017 - Robotic Grasping and One-shot Recognition of Novel Objects with Deep Learning.
[TPAMI 2023, NeurIPS 2020] Code release for "Deep Multimodal Fusion by Channel Exchanging"
MIT-Princeton Vision Toolbox for the Amazon Picking Challenge 2016 - RGB-D ConvNet-based object segmentation and 6D object pose estimation.
OcclusionFusion: realtime dynamic 3D reconstruction based on single-view RGB-D
[ECCV-20] 3D human scene interaction dataset: https://people.eecs.berkeley.edu/~zhecao/hmp/index.html
RGBD plane detection and color-based plane refinement
3D Graph Neural Networks for RGBD Semantic Segmentation
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.
This repo includes the source code of the fully convolutional depth denoising model presented in https://arxiv.org/pdf/1909.01193.pdf (ICCV19)