liuziyang123

FAMINet

Implementation of our paper entitiled FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical Flow published in TIM.

LDRFlow

Implementation of our paper, entitiled Unsupervised Optical Flow Estimation for Differently Exposed Images in LDR Domain, submitted to IEEE TCSVT.

BasicSR

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

flownet2-pytorch

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

FuseDepth

Implementation of our paper entitiled LiDAR-ToF-Binocular depth fusion using gradient priors published in CCDC.

permutohedral_lattice

Permutohedral Lattice C++/CUDA implementation + TensorFlow Op (CPU/GPU)

PWC-Net

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)

RAFT

SCNet

Implementation of our paper entitiled S&CNet: A lightweight network for fast and accurate depth completion published in JVCI.

slambook

Sparse-Depth-Completion

Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st place on KITTI)

SVEHDRI

Implementation of our papers entitiled Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot published in TCSVT and Restoration of HDR Images for SVE-Based HDRI via a Novel DCNN published in ICME.