Qian Ming's Projects
a machine learning method improved by deep forest
PyTorch implementation of the paper "A Generative Appearance Model for End-to-End Video Object Segmentation".
ECCV AIM 2020 Challenge on Rendering Realistic Bokeh, rank first
PyTorch reimplementation of Interactive Deep Colorization
Grayscale Image Colorization with Generative Adversarial Networks. https://arxiv.org/abs/1803.05400
Depth and DOF Cues Make Better Defocus Blur Detection
Package containing helper functions for loading and evaluating DAVIS
Evaluation Framework for DAVIS 2017 Semi-supervised and Unsupervised used in the DAVIS Challenges
The source code of "Deep Exemplar-based Colorization".
Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks
Official Pytorch implementation of "Learnable Gated Temporal Shift Module for Deep Video Inpainting. Chang et al. BMVC 2019." and the FVI dataset in "Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN, Chang et al. ICCV 2019"
A low-level vision zoo for dehazing, deblurring, denoising, deraining, inpainting, color enhancement, brightening, and super resolution .
Code and models for our ICCV 2021 paper "MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis"
LPIPS metric. pip install lpips
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)
Config files for my GitHub profile.
The official implementation of the paper: Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs (ICCV 2023)
Code for the paper "DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement". http://iizuka.cs.tsukuba.ac.jp/projects/remastering/
SRN-DeblurNet pytorch replicate , pretrained model provided
Optical Flow Prediction with TensorFlow. Implements "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume," by Deqing Sun et al. (CVPR 2018)
unet/pspnet/unet2d segment implement for Remote sensing image segmentation