Kepeng Xu Claim this profile

[IJCAI'24] Beyond Alignment: Blind Video Face Restoration via Parsing-Guided Temporal-Coherent Transformer

PRISM-VL studies measurement-grounded VLM learning with RAW-derived Meas.-XYZ inputs, camera-conditioned grounding, and exposure-bracketed supervision transfer.

ACMMM'24 An End-to-End Real-World Camera Imaging Pipeline

Extended from AAAI-26(oral) RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learning

No description.

introduce video face restoration method

No description.

This repository is used to read numpy array image direct from HDR and SDR video

No description.

AcadHomepage: A Modern and Responsive Academic Personal Homepage

No description.

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

Faster-RCNN in Tensorflow

Computation using data flow graphs for scalable machine learning

No description.

Tensorflow implementation of DeepFM for CTR prediction.

Automatically generate headlines to short articles

No description.

No description.

Train and deploy real-time artistic style transfer in mobile apps with Fritz Style Transfer.

No description.

Open solution to the Mapping Challenge :earth_americas:

No description.

No description.

PC-DARTS:Partial Channel Connections for Memory-Efficient Differentiable Architecture Search

Bayesian Optimization with Neural Architectures for Neural Architecture Search - https://arxiv.org/abs/1910.11858

Unofficial implementation of Octave Convolutions (OctConv) in TensorFlow / Keras.

Solve Poisson equation on arbitrary 2D domain using the finite element method.

cython powered bindings for v4l2 capture

“四人帮”-《设计模式：可复用面向对象软件的基础》所有模式的实现，使用C++语言

SegNet-Basic with Keras

Preparing a dataset for TensorFlow text summarization (TextSum) model.

ResNet model in TensorFlow

No description.

FastER RCNN built on tensorflow

Spot Garbage Dataset

tensorflow implementation of 'YOLO : Real-Time Object Detection'

some tips

Keras-tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation（Unfinished）

some question

Simple Reinforcement learning tutorials

Reimplementation of DeepLabV3

write data about my learning faster rcnn experience

C++

Keras implementation of "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks"

Group Normalization in PyTorch

TensorFlow implementation of Independently Recurrent Neural Networks

C++&&data_struct

Text summarization using seq2seq in Keras

A special way to tune parameter with your RP.

Pre-trained word vectors of 30+ languages

2018腾讯广告算法大赛baseline 线上0.73

2018

Neural Machine Translation with Keras (Theano/Tensorflow)

Official ROS packages for Kinova robotic arms

Models and examples built with TensorFlow

BetterNetWork4SSD

unet for image segmentation

Fine-tune CNN in Keras

Semantic Segmentation Architectures Implemented in PyTorch

No description.

No description.

🎓 西电 Slides 技能包 - 基于西电视觉规范的零依赖 HTML 演示文稿生成Skill | 支持西电官方 Logo、配色方案和专业排版，适用于毕业答辩、课程汇报、学术会议等场景

Claude Code Cloak — 保护本地设备隐私，安全使用 Claude Code

[NeurIPS' 2025] JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent

PyTorch implementation of adversarial attacks [torchattacks]

Official codes of Towards Real-World Blind Face Restoration with Generative Diffusion Prior

U-Net Biomedical Image Segmentation

No description.

No description.

Tools for converting from HDR10 to HLG

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

The test code for 'SDRTV-to-HDRTV via Hierarchical Dynamic Context Feature Mapping'.

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

No description.

[CVPR 2023 Highlight] DNF: Decouple and Feedback Network for Seeing in the Dark

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.

:books: A collection of papers about Sketch Synthesis (Generation).

[ICCV 2023] Implicit Neural Representation for Cooperative Low-light Image Enhancement

Official repository of the Deep Image Debanding conference paper. This research project was done with Dr. Shahrukh Athar, Zhongling Wang, and Prof. Zhou Wang, and the work is published in ICIP 2022.

No description.

some materials about mesh processing, including papers, videos, codes, and so on. Updating every day!

No description.

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文总结+润色+审稿+审稿回复

Official code for ECCV2022 paper: Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution

Super-Resolution Neural Operator, in CVPR 2023

Compatible Intrinsic Triangulations (SIGGRAPH 2022)

Code release for PConv and FasterNet

Deep Contextual Video Compression

Our method and experience of wining the NTIRE22 challenge on video quality enhancement

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the training code!

Collect super-resolution related papers, data, repositories

Code for the ECCV 2022 paper "Unleashing Transformers"

Taming Transformers for High-Resolution Image Synthesis

Winner solution of mobile AI (CVPRW 2021).

DifFace: Blind Face Restoration with Diffused Error Contraction (PyTorch)

A comprehensive list of recources (papers, repositories etc.) about face restoration methods.

[CVPR 2022] Learning Adaptive Warping for Real-World Rolling Shutter Correction

No description.

The official implementation of VidFace

A collection of state-of-the-art face super-resolution/hallucination methods

No description.

Differentiable fast wavelet transforms in PyTorch with GPU support.

Pytorch implementation of convolutional neural network visualization techniques

Code for DISCNet.

PyTorch implementation of [1412.6553] and [1511.06530] tensor decomposition methods for convolutional layers.

Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet

This is an official pytorch implementation of Fast Fourier Convolution.

Official pytorch implementation of paper "RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution"

SwinIR: Image Restoration Using Swin Transformer (official repository)

Video Deblurring with Transformer

The official MegEngine implementation of the ECCV 2022 paper: Ghost-free High Dynamic Range Imaging with Context-aware Transformer

An integer linear program solver using a Lagrange decomposition into binary decision diagrams. Lagrange multipliers are updated through dual block coordinate ascent.

This is an offical implementation of the CVPR2022's paper [Learning the Degradation Distribution for Blind Image Super-Resolution](https://arxiv.org/abs/2203.04962)

Training and Testing codes for our paper "Real-world Image Super-resolution via Domain-distance Aware Training"

darktable is an open source photography workflow application and raw developer

This repo is for glsl shaders converted by hand from libretro's common-shaders repo, since some don't play nicely with the cg2glsl script.

My own gentoo configuration files, for backup and other purposes

libplacebo-based debanding, scaling and color mapping plugin for VapourSynth

A video processing framework with simplicity in mind

No description.

[CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.

Code for "Neural 3D Reconstruction in the Wild", SIGGRAPH 2022 (Conference Proceedings)

PyTorch implementation of paper "Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes"

A curated list of awesome neural radiance fields papers

an example of a CUDA extension for PyTorch using CuPy which computes the Hadamard product of two tensors

CVPR 2022 "Online Convolutional Re-parameterization"

This is the official repository for the Deep Banding Index paper Implementation. I worked on this project as a graduate researcher under Dr. Zhou Wang. The research project resulted is in ICASSP 2021 Conference paper on Banding, CNN, and Data Science for Image Processing.

No description.

A Collection of Papers and Codes in CVPR2022 about low level vision

Automatic line art colorization using various types of hint or without hint

:books: A collection of Deep Learning based Image Colorization and Video Colorization papers.

The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐

Official code for paper "On the Connection between Local Attention and Dynamic Depth-wise Convolution" ICLR 2022 Spotlight

使用c++以及cuda加速神经网络样例（实现矩阵加法和矩阵乘法）

No description.

No description.

my personal mpv conf build

This repository is for "Image Colorization: A Survey and Dataset" paper

Tool for plotting rd curves from output of video coding test model software

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

[CVPR 2020] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Official PyTorch implementation of "Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss" (SIGGRAPH 2020)

Official Implementation of Swapping Autoencoder for Deep Image Manipulation (NeurIPS 2020)

The official implementation of the CVPR2021 paper: Decoupled Dynamic Filter Networks

PyTorch implementation and benchmark of Video Compression

Bjontegaard metric calculation. Include BD-PSNR and BD-rate

FFmpeg Debug Script for QP Values

ICCV2021 - A New Journey from SDRTV to HDRTV.

PyTorch implementation of "Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement", AAAI 2020.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Fast Blind Natural Video Quality (V-BLIINDS)

Gitl HEVC/H.265 Analyzer based on Qt. Custom filters supported.

Keras implementation of EDVR: Video Restoration with Enhanced Deformable Convolutional Networks

[ECCV'2020] STTN: Learning Joint Spatial-Temporal Transformations for Video Inpainting

Implementing Lambda Networks using Pytorch

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

TensorFlow Implementation of Generative Adversarial Networks for Extreme Learned Image Compression

Implemention of Fidelity Controllable Extreme Image Compression with GAN

[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang

Winning Solutions from SpaceNet Road Detection and Routing Challenge

Code for "Deep Snake for Real-Time Instance Segmentation" CVPR 2020 oral

AutoML tools chain

No description.

No description.

pytorch implementation of scene change detection

No description.

No description.

No description.

Binary Particle Swarm Optimisation algorithm implementation

Library of swarm optimization algorithms.

Single Path One-Shot NAS MXNet implementation with full training and searching pipeline. Support both Block and Channel Selection. Searched models better than the original paper are provided.

No description.

Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search

No description.

keras-HRNet

High-resolution representation learning (HRNets) for Semantic Segmentation

No description.

Codes for our paper "Progressive Differentiable Architecture Search:Bridging the Depth Gap between Search and Evaluation"

A PyTorch implementation of the architecture of Mask RCNN, serves as an introduction to working with PyTorch

A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware.

No description.

PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

Pytorch implementation of the U-Net for image semantic segmentation, with dense CRF post-processing

No description.

3D U-Net model for volumetric semantic segmentation written in pytorch

Code for Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells, CVPR '19

Retina blood vessel segmentation with a convolutional neural network

No description.

Python - 100天从新手到大师

Next generation FEniCS problem solving environment

List of satellite imagery datasets with annotations for computer vision and deep learning

No description.

No description.

No description.

No description.

deeplabv3plus2018:Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

DeepLabv3+ built in TensorFlow

No description.