Kenneth Wu

onnxruntime-genai. Generative AI extensions for onnxruntime

Apollo-11. Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.

onnxruntime-qnn. onnxruntime-qnn is the Qualcomm AI Runtime (QAIRT) execution provider for onnxruntime. It provides onnxruntime hardware acceleration and advanced functionalities on Qualcomm devices.

onnxruntime. ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Skyfall-GS. [ECCV 2026] Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

gemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal.

n8n. Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

GaussianLSS. Official PyTorch implementation of "GaussianLSS - Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting" (CVPR 2025).

LongSplat. [ICCV 2025] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

depthsplat. [CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

OpenSplat. Production-grade 3D gaussian splatting with CPU/GPU support for Windows, Mac and Linux 🚀

Grendel-GS. [ICLR 2025 Oral] On Scaling Up 3D Gaussian Splatting Training

speedy-splat. Python

EDGS. [CVPR 2026] A PyTorch implementation of the paper "EDGS: Eliminating Densification for Efficient Convergence of 3DGS"

ever_training. Original reference implementation of "EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis"

AnySplat. [SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

on-the-fly-nvs. Official implementation of On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images. A. Meuleman, I. Shah, A. Lanvin, B. Kerbl, G. Drettakis, ACM TOG (proc. SIGGRAPH) 2025

tiny-llm. A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

FluxText. Implementation of "FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing"

poster-design. 迅排设计 - 美观且功能强大的图片编辑器、在线海报设计，仿稿定设计，适用于多种场景：海报生成、电商产品图、文章长图、视频/公众号封面等。A beautiful online image designer, suitable for various scenarios like generate posters, making design easier!

gemini-code. Gemini 2.5 Pro code assistant

PosterCraft. [ICLR'26] Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

lang-segment-anything. SAM with text prompt

vcard. TypeScript

GEN3C. [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

YoLLaVA. 🌋👵🏻 Yo'LLaVA: Your Personalized Language and Vision Assistant (NeurIPS 2024)

FrugalNeRF. [CVPR 2025] FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors

asuka-misato. [CVPR 2025 Highlight] Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency

CUT3R. Official implementation of Continuous 3D Perception Model with Persistent State

dcseg. DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian Splatting

LAPIS.

ai-toolkit. The ultimate training toolkit for finetuning diffusion models

KD_llama_1B-Knowledge-Distillation-for-LLaMA-3.2-1B. This project demonstrates knowledge distillation from LLaMA-3.2-3B-Instruct (teacher) to LLaMA-3.2-1B-Instruct (student). The goal is to transfer knowledge from a larger model into a smaller one to improve efficiency while maintaining performance.

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

openai-python. The official Python library for the OpenAI API

GeoWizard. [ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

Step1X-Edit. A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

awesome-gpt4o-images. Awesome curated collection of images and prompts generated by GPT-4o and gpt-image-1. Explore AI generated visuals created with ChatGPT and Sora, showcasing OpenAI’s advanced image generation capabilities.

AREdit. Training-Free Text-Guided Image Editing Using Visual Autoregressive Model

perception_models. State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

hqq. Official implementation of Half-Quadratic Quantization (HQQ)

ml-depth-pro. Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

AnyText2. Official implementation code of the paper <AnyText2: Visual Text Generation and Editing With Customizable Attributes>

AnyText. Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

DiffSynth-Studio. Enjoy the magic of Diffusion models!

TransPixeler. CVPR2025

awesome-ai-system-prompts. 🧠 Curated collection of system prompts for top AI tools. Perfect for AI agent builders and prompt engineers. Incuding: ChatGPT, Claude, Perplexity, Manus, Claude-Code, Loveable, v0, Grok, same new, windsurf, notion, and MetaAI.

MinorityPrompt. Official PyTorch Implementation of "Minority-Focused Text-to-Image Generation via Prompt Optimization" (CVPR 2025 Oral)

unidisc. UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, and inpainting.

arxiv-mcp-server. A Model Context Protocol server for searching and analyzing arXiv papers

See3D. [CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

Murre. Code for "Multi-view Reconstruction via SfM-guided Monocular Depth Estimation". CVPR 2025 (Oral Presentation)

AutoPrompt. A framework for prompt tuning using Intent-based Prompt Calibration

cse234-w25-PA. Python

Torch-Pruning. [CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

nerficg. The ICG Neural Radiance Fields and Novel View Synthesis Framework.

star-vector. StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.

MV-Adapter. [ICCV 2025] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"

DiptychPrompting. Python

stable-virtual-camera. Stable Virtual Camera: Generative View Synthesis with Diffusion Models

hackmd-mcp. A Model Context Protocol server for integrating HackMD's note-taking platform with AI assistants.

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

RF-Solver-Edit. [🚀ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!

MIDI-3D. [CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

personalize-anything. [AAAI 2026] Personalize Anything for Free with Diffusion Transformer

python-genai. Google Gen AI Python SDK provides an interface for developers to integrate Google's generative models into their Python applications.

deprecated-generative-ai-python. This SDK is now deprecated, use the new unified Google GenAI SDK.

AuraFusion360_official. [CVPR2025] Official Implementation of AuraFusion360

octotools. OctoTools: An agentic framework with extensible tools for complex reasoning

HunyuanVideo-I2V. HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

FLARE. Python

fast3r. [CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

AnyV2V. Code and data for "AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks" [TMLR 2024]

InstantSplat. InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

FlowEdit. Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"

syncd. SynCD: Generating Multi-Image Synthetic Data for Text-to-Image Customization (ICCV 2025)

FlashMLA. FlashMLA: Efficient Multi-head Latent Attention Kernels

wonderland. Python

FLUX-Controlnet-Inpainting. Python

goku. [CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/

EZIGen. [BMVC 2025] Official implementation for paper EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidance

prompt-to-prompt. Jupyter Notebook

Awesome-Controllable-Diffusion. Papers and resources on Controllable Generation using Diffusion Models, including ControlNet, DreamBooth, IP-Adapter.

accelerate. 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

stable-point-aware-3d. SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

diptych-prompt-unofficail. Python

DepthLab. Official implementation of "DepthLab: From Partial to Complete"

GPA. Online photography assistance, tailored for food photograph.

flux. Official inference repo for FLUX.1 models

lambda-eclipse-inference. [TMLR] Official PyTorch implementation of "λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space"

StableCascade. Official Code for Stable Cascade

InstantStyle. InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥

IP-Adapter. The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

TRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

IC-Light. More relighting!

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

leetcode-master. 《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

rcg. PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

SimpleTuner. A general fine-tuning kit geared toward image/video/audio diffusion models.

SyncNoise. SyncNoise: Geometrically Consistent Noise Prediction for Text-based 3D Scene Editing

LeetCode. This repository contains the solutions and explanations to the algorithm problems on LeetCode. Only medium or above are included. All are written in C++/Python and implemented by myself. The problems attempted multiple times are labelled with hyperlinks.

Anything-3D. Segment-Anything + 3D. Let's lift anything to 3D.

VideoGS. [SIGGRAPH Asia 2024] V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians

Bend. A massively parallel, high-level programming language

graphrag. A modular graph-based Retrieval-Augmented Generation (RAG) system

Depth-Anywhere. Python

Stable-Diffusion-Inpaint. Stable diffusion for inpainting

GSD. Geometry-Aware Score Distillation via 3D Consistent Noising and Gradient Consistency Modeling

bitsandbytes. Accessible large language models via k-bit quantization for PyTorch.

GScream. Official code for ECCV2024 paper: GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal

DNGaussian. [CVPR'24] DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

DiffIR2VR-Zero. Python

MVIP-NeRF. official repo for MVIP-NeRF (CVPR 2024)

2d-gaussian-splatting. [SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

diff-surfel-rasterization. A differentiable rasterizer used in the project "2D Gaussian Splatting"

efficient-kan. An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

coremltools. Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

litert-torch. Support PyTorch model conversion with LiteRT.

canvas-confetti. 🎉 performant confetti animation in the browser

aimet. AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

pykan. Kolmogorov Arnold Networks

Infusion. Official implementation for paper: InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior

CustomNeRF. [CVPR 2024] Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training

IOPaint. Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

UniDepth. Universal Monocular Metric Depth Estimation

Inpaint-Anything. Inpaint anything using Segment Anything and inpainting models.

GaussianPro. [ICML2024] Official code for GaussianPro: 3D Gaussian Splatting with Progressive Propagation

DIP_Final. Water Segmentation

CompletionFormer. [CVPR2023] CompletionFormer: Depth Completion with Convolutions and Vision Transformers

servstat. Server resource and GPU process monitor.

garfield. [CVPR'24] Group Anything with Radiance Fields

SimpleNeRF. Official code release accompanying the paper "SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutions"

awesome-nerf-editing. 🧙🏻‍♂️A list of papers curated for you to dive into the Awesome Radiance Field-based 3D Editing.

AnyDoor. Official implementations for paper: Anydoor: zero-shot object-level image customization

SIGNeRF. SIGNeRF: Scene Integrated Generation for Neural Radiance Fields

SegAnyGAussians. The official implementation of Segment Any 3D GAussians (AAAI-25)

clipseg. This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".

DINO. [ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

ByteTrack. [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

mip-splatting. [CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting

repaint123. Official implementation of Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting (ECCV 2024)

LoRA. Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

deep_sort. Simple Online Realtime Tracking with a Deep Association Metric

talktopapers. Jupyter Notebook

paper-reading. 深度学习经典、新论文逐段精读

GaussianSplats3D. Three.js-based implementation of 3D Gaussian splatting

gaussian-grouping. [ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

calibur. Conversion between different conventions of camera matrices and transform matrices.

GaussianEditor. [CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

Awesome-CV. :page_facing_up: Awesome CV is LaTeX template for your outstanding job application

interview. 📚 C/C++ 技术面试基础知识总结，包括语言、程序库、数据结构、算法、系统、网络、链接装载库等知识及面试经验、招聘、内推等信息。This repository is a summary of the basic knowledge of recruiting job seekers and beginners in the direction of C/C++ technology, including language, program library, data structure, algorithm, system, network, link loading library, interview experience, recruitment, recommendation, etc.

academicpages.github.io. Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

scene-representation-networks. Official Pytorch implementation of Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

f3rm. F3RM: Feature Fields for Robotic Manipulation. Official repo for the paper "Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation" (CoRL 2023).

awesome-3D-gaussian-splatting. Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

scalingup. [CoRL 2023] This repository contains data generation and training code for Scaling Up & Distilling Down

Instant-angelo. Instant-angelo: Build high-fidelity Digital Twin within 20 Minutes!

Tri-MipRF. [ICCV'23 Oral, Best Paper Finalist]Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields

gsplat. CUDA accelerated rasterization of gaussian splatting

LichtFeld-Studio. Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.

lama. 🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

robust_cvd. Robust Consistent Video Depth Estimation

Applied-Deep-Learning. Applied Deep Learning Course

ZoeDepth. Metric depth estimation from a single image

stable-diffusion. A latent text-to-image diffusion model

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

jonbarron.github.io. HTML

gdown. Google Drive public file downloader when curl/wget fails.

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

neuralangelo. Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

torch_efficient_distloss. Efficient distortion loss with O(n) realization.

ViP-NeRF. Official code release accompanying the paper - "ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields"

deformable-sprites. Python

vision_transformer. Jupyter Notebook

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

NCTU_DLP. Jupyter Notebook

vision-nerf. Official PyTorch Implementation of paper "Vision Transformer for NeRF-Based View Synthesis from a Single Input Image", WACV 2023.

FreeNeRF. [CVPR23] FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

fourier-feature-networks. Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

nerfacc. A General NeRF Acceleration Toolbox in PyTorch.

sdfstudio. A Unified Framework for Surface Reconstruction

humanrf. Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"

EndoNeRF. Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic Surgery

awesome. 😎 Awesome lists about all kinds of interesting topics

nerf. Code release for NeRF (Neural Radiance Fields)

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

nerfstudio. A collaboration friendly studio for NeRFs

awesome-computer-vision. A curated list of awesome computer vision resources

nerf_pl. NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

awesome-NeRF. A curated list of awesome neural radiance fields papers

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

google-research. Google Research

jax3d. Python

ExpirationExpert. Swift

VoxFormer. Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]