menghanxia Goto Github PK

3d-cinemagraphy

apdrawinggan

Code for APDrawingGAN: Generating Artistic Portrait Drawings from Face Photos with Hierarchical GANs (CVPR 2019 Oral)

autostitching

Automatic topology constructing and global stitching optimization for large-scale unordered UAV aerial images. [Pattern Recognition 2017]

carafe

This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures

colorconsistency

Improving color consistency across multiple images via global optimization on the color remapping curves. [ICCVW 2017 & ISPRS Journal 2019]

demosfm

A basic SFM framework that estimates the poses and reconstructs the sparse 3D point clouds from the input either image sequence or video. [Undergraduate FYP 2014]

digital-halftoning

The repository contains MATLAB and Python code for the digital halftoning techniques

disentangledcolorization

A colorization framework that disentangles the color multimodality and the structural consistency via adaptively located anchors, so that both aspects can be achieved effectively. [SIGGRAPH Asia 2022]

exposure

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

flops-counter.pytorch

Flops counter for convolutional networks in pytorch framework

generative-models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

halftones

A fork from https://bitbucket.org/kuraiev/halftones

inversehalftoning

An inverse halftoning model, which is applied to recover the 8-bit grayscale image from 1-bit error diffused halftones. [ACCV 2018]

invertiblegrayscale

An invertible generative model that converts color images into grayscale variant such that the original color is still restorable. [SIGGRAPH Asia 2018]

lf2mv

Learning to represent the 4D light field with a single meta-view that is both compact and editable. Most 2D image edits could be applied to it and then gets consistently propagated to other views through our decoding network.

lightfieldangularsr

Fast Light Field Reconstruction With Deep Coarse-To-Fine Modeling of Spatial-Angular Clues

menghanxia

Config files for my GitHub profile.

menghanxia.github.io

MyHomepage

nerfplusplus

improves over nerf

pen-net-for-inpainting

pytorch-colors

Small utility for color space conversions of PyTorch Tensors and Variables

reversiblehalftoning

The first approach to utilize CNN for image dithering, which is actually non-trivial. This formulation enables us to equip it with extra features, e.g. reversibility. [ICCV 2021]