Bo-Hsu Ke

LongE2V. [SIGGRAPH 2026] Official implementation of "LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models"

FireRedASR. Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.

DF3DV. [ECCV 2026] DF3DV-1K Dataset and DI²FIX Codebase

JanusMesh. Python

BRDFusion. BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering

mllm-reroute. Official code release for Reroute, Don’t Remove: Recoverable Visual Token Routing for Vision-Language Models.

YoCausal. YoCausal: How Far is Video Generation from World Model? A Causality Perspective

zipa. A family of efficient speech models for multilingual phone recognition

awesome-ai-security. A collection of awesome resources related AI security

Hestia-NBV. [WACV 2026] Hestia-NBV

Classical-Piano-Composer. Python

VLIPP. [ICCV 2025] Pytorch implementation of "VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior"

cosmos-reason1. Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.

StealthAttack_official. [ICCV2025] StealthAttack

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

GaussianPrediction. [SIGGRAPH Conference 2024] GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis

tesseract. Tesseract Open Source OCR Engine (main repository)

DynamiCrafter. [ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

ShowHowTo. Code for the paper "ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions" published at CVPR 2025

OmniAvatar. Python

ICCV2025-Papers-with-Code. ICCV 2025 论文和开源项目合集

CVPR2026-Papers-with-Code. CVPR 2026 论文和开源项目合集

GPT-SoVITS. 1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Retrieval-based-Voice-Conversion-WebUI. Easily train a good VC model with voice data <= 10 mins!

AEGIS. [ACM SIGCHI 2025] The official repo for “AEGIS: Human Attention-based Explainable Guidance for Intelligent Vehicle Systems”

GlobustVP. [CVPR 2025 Best Paper Award Candidate & Oral] Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World

street_gaussians. [ECCV 2024] Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting

Depth-Anywhere. Python

TensoRF. [ECCV 2022] Tensorial Radiance Fields, a novel approach to model and reconstruct radiance fields

jpeg_tutorial. 跟我寫 JPEG 解碼器 (Write a JPEG decoder with me)

nerfstudio. A collaboration friendly studio for NeRFs

DPT. Dense Prediction Transformers

colmap. COLMAP - Structure-from-Motion and Multi-View Stereo

f1db. Open Source Formula 1 Database

formula1-datasets. Datasets & Analyses for Formula 1 World Championship

AutomatedTicketBot. An automated python crawler using Splinter for reserving tickets on a popular Chinese ticket selling website.

feature-3dgs. [CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

awesome-3D-point-cloud-attacks. List of state of the art papers, code, and other resources

Awesome-Backdoor-in-Deep-Learning. A curated list of papers & resources on backdoor attacks and defenses in deep learning.

dust3r. DUSt3R: Geometric 3D Vision Made Easy

LeftRefill. LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model (CVPR2024)

Time-Reversal. Unofficial implementation of "Explorative Inbetweening of Time and Space"

nerf-pytorch. A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

gaussian-painters. Gaussian Painters using 3D Gaussian Splatting

jonbarron.github.io. HTML

ddrm. [NeurIPS 2022] Denoising Diffusion Restoration Models -- Official Code Repository

ddrm-jpeg. JPEG Artifact Correction using Denoising Diffusion Restoration Models -- Official Code Repository

U-shape_Transformer_for_Underwater_Image_Enhancement. U-shape Transformer for Underwater Image Enhancement

DiffIR2VR-Zero. Python

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

course-selection. Python

stable-diffusion-webui-colab. stable diffusion webui colab

SoraWebui. SoraWebui is an open-source Sora web client, enabling users to easily create videos from text with OpenAI's Sora model.

difftaichi. 10 differentiable physical simulators built with Taichi differentiable programming (DiffTaichi, ICLR 2020)

ControlNet. Let us control diffusion models!

zero123. Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

nerf. Code release for NeRF (Neural Radiance Fields)

face_recognition. The world's simplest facial recognition api for Python and the command line

pi-hole. A black hole for Internet advertisements

my_.vimrc. Vim Script

KDDF. [GLOBECOM 2023] Knowledge Distillation Based Defense for Audio Trigger Backdoor in Federated Learning

domain-driven-hexagon. Learn Domain-Driven Design, software architecture, design patterns, best practices. Code examples included

pulse. PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

rethinking-image-scaling-attacks. [ICML 2022] Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems

DeepFaceLive. Real-time face swap for PC streaming or video calls

hello-algo. 《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

pytorch-deepdream. PyTorch implementation of DeepDream algorithm (Mordvintsev et al.). Additionally I've included playground.py to help you better understand basic concepts behind the algo.

knowledge-distillation-pytorch. A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

deepdarkCTI. Collection of Cyber Threat Intelligence sources from the deep and dark web

codon. A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support

OpenChatKit. Python

so-vits-svc. 基于vits与softvc的歌声音色转换模型

ChatGPT-ToolBox. 由ChatGPT自己编写的ChatGPT工具箱。 当前功能: 1. 绕过高负载禁止登录 2.关闭数据监管 3.链路维持(减少网络错误) 4.API混合接入 5.会话导入导出 6.聊天记录下载 7.解锁GPT4-Mobile

awesome-chatgpt-prompts-zh. ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

linux-wifi-hotspot. Feature-rich wifi hotspot creator for Linux which provides both GUI and command-line interface. It is also able to create a hotspot using the same wifi card which is connected to an AP already ( Similar to Windows 10).

PBCNN. Jupyter Notebook

BackdoorBox. The open-sourced Python toolbox for backdoor attacks and defenses.

Programming. C++

CTF. JavaScript

zsh-autosuggestions. Fish-like autosuggestions for zsh

StegaStamp. Invisible Hyperlinks in Physical Photographs

PCCA_2023. practice

instruct-pix2pix. Python

deeplearning-models. A collection of various deep learning architectures, models, and tips

flower. Flower: A Friendly Federated AI Framework

VGGFace2-pytorch. PyTorch Face Recognizer based on 'VGGFace2: A dataset for recognising faces across pose and age'

backdoor_federated_learning. Source code for paper "How to Backdoor Federated Learning" (https://arxiv.org/abs/1807.00459)

ultrasonic_backdoor. Python

fish. Dart

powerlevel10k. A Zsh theme

ISSBA. Invisible Backdoor Attack with Sample-Specific Triggers

SICDF. [ICC 2023] Successive Interference Cancellation Based Defense for Trigger Backdoor in Federated Learning

batchgenerators. A framework for data augmentation for 2D and 3D image classification and segmentation

facenet-pytorch. Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

Class-agnostic-Few-shot-Object-Counting. pytorch implementation of a WACV 2021 Paper "Class-agnostic Few-shot-Object-Counting"

metasploit-framework. Metasploit Framework

malware-samples. Malware samples, analysis exercises and other interesting resources.

theZoo. A repository of LIVE malwares for your own joy and pleasure. theZoo is a project created to make the possibility of malware analysis open and available to the public.