Shengdong Zhang's repositories
DehazingCNN
this is a project for paper, we also provide materail on
AdaAttN
Officially unofficial PyTorch re-implementation of paper: AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer, ICCV 2021.
AIM
[IJCAI'21] Deep Automatic Natural Image Matting
BiAM
[ICCV 2021] Official Pytorch implementation for Discriminative Region-based Multi-Label Zero-Shot Learning SOTA results on NUS-WIDE and OpenImages
CGDM
Codes for "Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation" in CVPR 2021
co-mod-gan
[ICLR 2021, Spotlight] Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
crfill
CR-Fill: Generative Image Inpainting with Auxiliary Contextual Reconstruction. ICCV 2021
DHVR
[ICCV 2021] Deep Hough Voting for Robust Global Registration
DMNet
Dynamic Multi-scale Filters for Semantic Segmentation (DMNet ICCV'2019)
FaPN
[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction
G-SFDA
code for ICCV 2021 paper 'Generalized Source-free Domain Adaptation'
GLCIC-PyTorch
A High-Quality PyTorch Implementation of "Globally and Locally Consistent Image Completion".
HDTF
the dataset and code for "Flow-guided One-shot Talking Face Generation with a High-resolution Audio-visual Dataset"
ic_gan
Official repository for the paper "Instance-Conditioned GAN" by Arantxa Casanova, Marlene Careil, Jakob Verbeek, Michał Drożdżal, Adriana Romero-Soriano.
img2pose
The official PyTorch implementation of img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation - CVPR 2021
Latent2im
ICLR'21 paper ``Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation"
mmediting
OpenMMLab Image and Video Editing Toolbox
NR-GAN
NR-GAN: Noise Robust Generative Adversarial Networks
ShapeConv
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation (ICCV 2021)
SOF-VSR
[ACCV 2018 & TIP 2020] Deep Video Super-resolution using HR Optical Flow Estimation
SPML
Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning
Talking-Face_PC-AVS
Code for Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021)
UNITE
Unbalanced Feature Transport for Exemplar-based Image Translation (CVPR 2021)
vrn
:man: Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"
wrapd-2d
A reference implementation of "WRAPD: Weighted Rotation-aware ADMM for Parameterization and Deformation" written in C++. This code supports 3D -> 2D surface parameterization.
xcnet
Open source repository at GitHub for Attention-based Stylisation for Exemplar Image Colourisation