SfM for sphere images in the ERP format within the framework of ColMap

A GPU-based ray-surface intersection test implemented in CUDA

Code and trained networks of the paper "NanoFlowNet: Real-time Dense Optical Flow on a Nano Quadcopter"

depth estimation with error propagation

SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation

The repository containing tools and information about the WoodScape dataset.

Variational Fisheye Stereo

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

BlAInder range scanner is a Blender add-on to simulate Lidar and Sonar measurements. The result can be saved as annotated 2D image or 3D point cloud.

Some code of the implements of Geological Modeling Using 3D Pixel-Adaptive and Deformable Convolutional Neural Network

Biologically inspired deep learning model for efficient foveal-peripheral vision

Learning Temporal Consistency for Low Light Video Enhancement from Single Images (CVPR2021)

Code for "DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion" (CVPR 2021)

TRI-ML Monocular Depth Estimation Repository

An unofficial PyTorch implementation of ICCV 2019 paper "OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching"

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

Code used to generate synthetic scenes and bounding box annotations for object detection. This was used to generate data used in the Cut, Paste and Learn paper

Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021.

Code of JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection(CVPR2020)

The pytorch implement of the retina track original paper link: https://arxiv.org/abs/2003.13870

(CVPR 2021 Oral) Open World Object Detection

Adaptive control-oriented meta-learning for nonlinear systems

Out-of-the-box code and models for CMU's object detection and tracking system for multi-camera surveillance videos. Speed optimized Faster-RCNN model. Tensorflow based. Also supports EfficientDet. …

Main repo for ECCV 2020 paper MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images. visual.cs.brown.edu/matryodshka