Hanzhe Hu

awesome-science-agents.

RayRoPE. [ECCV '26] Code for paper "RayRoPE: Projective Ray Positional Encoding for Multi-view Attention"

CV. ✅（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】

Cortex. 从零构建大模型：从预训练到RLHF的完整实践

TorchLeet. Leetcode for Pytorch

vibe-coding-cn. Python

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

AIGC-Interview-Book. 【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试秘籍。涵盖AIGC、LLM大模型、AI Agent、具身智能、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、世界模型、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。

composition_rendering. Python

MoGe. [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

sekai-codebase. [NeurIPS 2025] Sekai: A Video Dataset towards World Exploration

radial-attention. [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation

HunyuanWorld-1.0. Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

Awesome-Nano-Banana-images. A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development of image generation and unified models(click to website to see our blog)

minFM. HTML

llm_interview_note. 主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

MAGI-1. MAGI-1: Autoregressive Video Generation at Scale

LVSM. [ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"

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

blender-mcp. Open-source MCP to use Blender with any LLM

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

brush. 3D Reconstruction for all

juicefs. JuiceFS is a distributed POSIX file system built on top of Redis and S3.

REPA. [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

VideoTuna. Let's finetune video generation models!

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

DimensionX. [ICCV'25]DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

flow_matching. A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Turbo3D. Turbo3D: Ultra-fast Text-to-3D Generation

IC-Light. More relighting!

fiftyone. Refine high-quality datasets and visual AI models

DMD2. (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

gaussiansplattingnote. Studying Gaussian Splatting Source Code

mvdfusion. [CVPR 2024] MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation

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

SuGaR. [CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

RayDiffusion. Code for "Cameras as Rays"

camp_zipnerf. Python

EscherNet. [CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis

Deformable-3D-Gaussians. [CVPR 2024] Official implementation of "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction"

4DGaussians. [CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Awesome-AIGC-3D. A curated list of awesome AIGC 3D papers

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.

awesome-dynamic-scene-reconstruction. A curated list of awesome neural scene reconstruction datasets and papers, inspired by awesome-computer-vision.

Awesome-LLM-3D. Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources

objaverse-xl. 🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

SyncDreamer. [ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

PyBlend. PyBlend: a package for Blender with Python 🎨

ControlNet. Let us control diffusion models!

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

github-readme-stats. :zap: Dynamically generated stats for your github readmes

GET3D. Python

stanford-shapenet-renderer. Scripts for batch rendering models using Blender. Tested with models from stanfords shapenet library.

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

Body_Reconstruction_References. Paper, dataset and code collection on human body reconstruction

OpenMMD. OpenMMD is an OpenPose-based application that can convert real-person videos to the motion files (.vmd) which directly implement the 3D model (e.g. Miku, Anmicius) animated movies.

text2image. Generating Images from Captions with Attention

awesome_3DReconstruction_list. A curated list of papers & resources linked to 3D reconstruction from images.

IFA. Learning Implicit Feature Alignment Function for Semantic Segmentation, ECCV 2022

awesome_OpenSetRecognition_list. A curated list of papers & resources linked to open set recognition, out-of-distribution, open set domain adaptation and open world recognition

cs-video-courses. List of Computer Science courses with video lectures.

awesome_3d_slam_resources. 记录3D视觉、VSLAM、计算机视觉的干货资料。

3dv_tutorial. An Invitation to 3D Vision: A Tutorial for Everyone

RegionContrast. Region-aware Contrastive Learning for Semantic Segmentation, ICCV 2021

Awesome-Visual-Transformer. Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

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

SemiSeg-AEL. Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning, NeurIPS 2021 (Spotlight)

Generalization-Causality. 关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative model各式各样研究的阅读笔记

DCNet. Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection, CVPR 2021

PositionalEncoding2D. A PyTorch implementation of the 1d and 2d Sinusoidal positional encoding/embedding.

first-order-model. This repository contains the source code for the paper First Order Motion Model for Image Animation

PixelSSL. A PyTorch-based Semi-Supervised Learning (SSL) Codebase for Pixel-wise (Pixel) Vision Tasks [ECCV 2020]

pytorch-distributed. A quickstart and benchmark for pytorch distributed training.

MPSR. Multi-scale Positive Sample Refinement for Few-shot Object Detection, ECCV2020

pytorch-center-loss. Pytorch implementation of Center Loss

IBN-Net. Instance-Batch Normalization Networks (ECCV2018)

awesome-ai-awesomeness. A curated list of awesome awesomeness about artificial intelligence

semantic-segmentation-pytorch. Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

CR-GAN. Yu Tian et al. "CR-GAN: Learning Complete Representations for Multi-view Generation", IJCAI 2018

Made-With-ML. Learn how to develop, deploy and iterate on production-grade ML applications.

DeepLearning-500-questions. 深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

awesome-quantum-machine-learning. Here you can get all the Quantum Machine learning Basics, Algorithms ,Study Materials ,Projects and the descriptions of the projects around the web