Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion (AAAI 2021)

A pytorch implementation of DLCA

Video Frame Synthesis using Deep Voxel Flow

Video classification tools using 3D ResNet

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

3D ResNets for Action Recognition (CVPR 2018)

This is a copy of package for medical image synthesis work with LRes-ResUnet and GAN (wgan-gp) in pytorch framework

An open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy

Pytorch implementation of group normalization in https://arxiv.org/abs/1803.08494 (Following the PyTorch Style)

Everything about Transfer Learning and Domain Adaptation--迁移学习

PyTorch implementations of Generative Adversarial Networks.

An "infinite"-resolution GAN. It additionally produces interpretable results based on a photo editing model and reinforcement learning. (ACM Transactions on Graphics, to be presented at SIGGRAPH 2018)

Resources of semantic segmantation based on Deep Learning model

Generative Image Inpainting with Contextual Attention https://arxiv.org/abs/1801.07892, demo: http://jhyu.me/demo

Transfer Learning Library

Datasets, Transforms and Models specific to Computer Vision

A learning resource repository for 3D machine learning

PyTorch implementation of AlexNet

Estimate a depth map from two or more images

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

A deep learning framework for synthesizing novel views of objects and scenes

[CVPR 2017] Video motion segmentation and tracking

MODS (Matching On Demand with view Synthesis) is algorithm for wide-baseline matching.

Image-to-image translation using conditional adversarial nets

code for Holistically-Nested Edge Detection

Bachelor thesis "Superpixel Segmentation using Depth Information", including a thorough comparison of several state-of-the-art superpixel algorithms.