Xiaoyang Guo

awesome-world-action-models.

Awesome-Video-Action-Model.

wall-x. Building General-Purpose Robots Based on Embodied Foundation Model

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Pi3. [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning

Epona. Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)

taehv. Tiny AutoEncoder for Hunyuan Video (and other video models)

3dgrut. Ray tracing and hybrid rasterization of Gaussian particles

TrajectoryCrafter. [ICCV 2025, Oral] TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

GoalFlow. Repo of "GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving"

lobehub. 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

Easy3D. A lightweight, easy-to-use, and efficient library for processing and rendering 3D data (C++ & Python)

skorch. A scikit-learn compatible neural network library that wraps PyTorch

gpt-researcher. An autonomous agent that conducts deep research on any data using any LLM providers

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

awesome-deepseek-integration. Integrate the DeepSeek API into popular software

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

IGCS-GITC. Camera tools based on Frans Bouma's IGCS framework.

MagicDrive-V2. [ICCV 2025] Official implementation of the paper “MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”

DrivingWorld. Code for "DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT"

SS3DM-Exporter. [NeurIPS 2024] Data exporter for SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset

gs2mesh. [ECCV 2024] Official implementation of the paper "GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views"

mvsplat. 🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

filebrowser. File Browser provides a file managing interface within a specified directory and it can be used to upload, delete, preview and edit your files.

libcom. Image composition toolbox: everything you want to know about image composition/compositing or object/subject insertion/addition/compositing.

drivestudio. A 3DGS framework for omni urban scene reconstruction and simulation.

GeoMaster. GeoMaster: Advanced Geometry Enhancement for High-Resolution 3D Modeling

omg-tools. Optimal Motion Generation-tools: motion planning made easy

ReconX. [TIP 2026] ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

webdataset. A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

viser. Web-based 3D visualization in Python

RealityCapture-to-Postshot. Process for processing Reality Capture output into Colmap format to allow importing into Postshot.

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

MetalSplatter. Render Gaussian Splats using Metal on Apple platforms (iOS/iPhone/iPad, macOS, and visionOS)

VEnhancer. Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

msplat. A modular differential gaussian rasterization library.

hierarchical-3d-gaussians. Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"

mar. PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

NDC. PyTorch implementation of Neural Dual Contouring.

wayve_scenes. Codebase for the WayveScenes101 Dataset

street-gaussians-ns. Unofficial implementation of "Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting", ECCV2024.

DriveDreamer2. [AAAI 2025] DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation

CAD. CAD: Photorealistic 3D Generation via Adversarial Distillation (CVPR 2024)

MoneyPrinterTurbo. 利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

LightDiff. About [CVPR 2024] The official implementation of paper " Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving"

Open-Sora-Plan. This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

sd-forge-layerdiffuse. [WIP] Layer Diffusion for WebUI (via Forge)

generative-ai-for-beginners. 21 Lessons, Get Started Building with Generative AI

EfficientSAM. EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Depth-Anything. [CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

GaussianAvatar. [CVPR 2024] The official repo for "GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians"

supersplat. 3D Gaussian Splat Editor

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

dreamgaussian4d. [arXiv 2023] DreamGaussian4D: Generative 4D Gaussian Splatting

ra-neus. RaNeuS

SyncMVD. Official PyTorch & Diffusers implementation of "Text-Guided Texturing by Synchronized Multi-View Diffusion"

MERFStudio. A Unified Framework for Real-Time Rendering on the Web

StreamDiffusion. StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

ground_normal_filter. Official implementation of: Towards Accurate Ground Plane Normal Estimation from Ego-Motion

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.

AdaBins. Official implementation of Adabins: Depth Estimation using adaptive bins

awesome-knowledge-driven-AD. A curated list of awesome knowledge-driven autonomous driving (continually updated)

mvs-texturing. Algorithm to texture 3D reconstructions from multi-view stereo images

ChatSim. [CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration

ganerf. GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields

neurad-studio. [CVPR2024] NeuRAD: Neural Rendering for Autonomous Driving

Awesome-Image-Harmonization. A curated list of papers, code and resources pertaining to image harmonization.

RoMe. Python

Awesome-LLM-Robotics. A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

DriveLM. [ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

ICCV-2023-25-Papers. ICCV 2023-2025 Papers: Discover cutting-edge research from ICCV 2023-25, the leading computer vision conference. Stay updated on the latest in computer vision and deep learning, with code included. ⭐ support visual intelligence development!

LISA. Project Page for "LISA: Reasoning Segmentation via Large Language Model"

ArcNerf. Nerf and extensions in all

transferlearning. Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

maplab. A Modular and Multi-Modal Mapping Framework

LIO-SAM. LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping

LandMark. Python

Awesome-Occupancy-Prediction-Autonomous-Driving. Awesome papers about Multi-Camera Semantic Occupancy Prediction, such as TPVFormer, OccFormer, Occ3D, OpenOccupancy

omnimotion. Python

colmap--Important-code-is-to-parse-line-by-line. 教你一点点掌握视觉三维重建-colmap 重要代码逐行解析(本人利用下班和周末时间update,so 速度会慢)

VMA. A general map auto annotation framework based on MapTR, with high flexibility in terms of spatial scale and element type

Strivec. Official code for the paper: Strivec (ICCV2023)

SAM3D. [SCIS] SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model

raytracing. A CUDA Mesh RayTracer with BVH acceleration, with python bindings and a GUI.

NeRF-Texture. [SIGGRAPH 2023, TPAMI 2024] Code for NeRF-Texture: Texture Synthesis with Neural Radiance Fields

openMVS. open Multi-View Stereo reconstruction library

Explicit-Visual-Prompt. [CVPR 2023 & TPAMI 2025] Explicit Visual Prompting for Low-Level Structure Segmentations

neuralsim. neuralsim: 3D surface reconstruction and simulation based on 3D neural rendering.

DragGAN. Official Code for DragGAN (SIGGRAPH 2023)

ConsistentNeRF. ConsistentNeRF Enhances Neural Radiance Fields with 3D Consistency for Sparse View Synthesis

threestudio. A unified framework for 3D content generation.

pixel-perfect-sfm. Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

Hierarchical-Localization. Visual localization made easy with hloc

agi2nerf. Simple tool for converting Agisoft XML files to NERF JSON files for https://github.com/NVlabs/instant-ngp

NeRO. [SIGGRAPH2023] NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images

SegmentAnything3D. [ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes

ACMH. A simple yet effective PatchMatch MVS method, which is the base model of ACMM and ACMP.

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