Implementation of the method proposed in the paper "Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation"

Official implementation of Implicit Behavioral Cloning, as described in our CoRL 2021 paper, see more at https://implicitbc.github.io/

An open-source tool for visual and modular block programming in python

[IROS 2021] Dynamic Grasping with Reachability and Motion Awareness

RL implementations

Code for ICRA 2021 paper: https://arxiv.org/abs/2012.03385

[ECCV 2022] MVSTER: Epipolar Transformer for Efficient Multi-View Stereo

AdaCat

Disentangling Categorization in Multi-agent Emergent Communication

source code for ICLR"22 paper "VOS: Learning What You Don’t Know by Virtual Outlier Synthesis"

source code for CVPR"22 paper "Unknown-Aware Object Detection: Learning What You Don’t Know from Videos in the Wild"

Independent PyTorch implementation of Scene Representation Transformer

Deep Reinforcement Learning for Robotic Grasping from Octrees

Official repository for the paper F, B, Alpha Matting

(3DV 2021 oral) PyTorch implementation of paper "PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning"

Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition - NeurIPS2021

Research code of ICCV 2021 paper "Mesh Graphormer"

Generate static HTML archives of Slack workspaces

NeRD: Neural Reflectance Decomposition from Image Collections - ICCV 2021

Real-time 3D reconstruction tool based on DROID SLAM and CDS MVSNet.

SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse views

[CVPR"21] Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild

Doodler. A web application built with plotly/dash for image segmentation with minimal supervision. Plays nicely with segmentation gym, https://github.com/Doodleverse/segmentation_gym

[ECCV 2022] PlaneFormers: From Sparse View Planes to 3D Reconstruction

An all-in-one toolkit for computer vision

Topologically-Aware Deformation Fields for Single-View 3D Reconstruction (CVPR 2022)

This repository implements our CVPR2022 paper "BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion"

This repository provides source code, trained neural network model and dataset for our NeuralPassthrough work that is published at SIGGRAPH 2022.