[ICLR '26 Oral] Official repository of the paper "AnyUp: Universal Feature Upsampling".

🛡 A curated list of adversarial attacks in PyTorch, with a focus on transferable black-box attacks.

[Official Implementation] Model Inversion Attacks through Target-specific Conditional Diffusion Models

[ECCV 2022 Oral] 3D-Aware Indoor Scene Synthesis with Depth Priors

PyTorch implementations of Generative Adversarial Networks.

Using modified BiSeNet for face parsing in PyTorch

PyTorch implementation of the paper: "Improving 2D Face Recognition via Discriminative Face Depth Estimation"

(ICCV2023) A large-pose Flickr face dataset comprised of 19,590 high-quality real large-pose portrait images.

Learning Directly from Synthetic Point Clouds for "In-the-wild" 3D Face Recognition

RegGeoNet: Learning Regular Representations for Large-Scale 3D Point Clouds

⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet) / If you find it useful, please star this project, thanks~

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

[CVPR 2022] Shape-invariant Adversarial Point Clouds

🔥PCL（Point Cloud Library）点云库学习记录

The official TensorFlow implementation for ICCV'21 paper 'Dual Contrastive Loss and Attention for GANs'

Face recognition processing on RGB-D images using ResNet-50, GoogLeNet, and SqueezeNet, all trained from scratch.

《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持简中、繁中、English、日本語，提供 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 等代码实现

Facial Depth and Normal Estimation using Dual-Pixel Camera (ECCV 22)

A trusty face analysis research platform developed by Tencent Youtu Lab

3D face modeling and recognition using a depth camera (RGBD)

A pipeline for 3D face recognition(FR), including data preprocessing, feature extraction and face recognition. Suit for consumer RGB-D cameras, for example, Kinect V2.

This project is an implementation for "Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-quality 3D Faces".

DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

[CVPR2023] A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images.

This is the official implementation of ContraNet (NDSS2022).