Ranran Huang

DiffSynth-Studio. Enjoy the magic of Diffusion models!

LatentForcing. Python

Gen3R. [CVPR 2026] Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction

VIST3A. [ICLR 2026 oral] Official code for VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator

Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

vggt-omega. [CVPR 2026 Oral] VGGT Omega

ijepa. Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

ml-lgtm. Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting

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

PixelDiT. [CVPR 2026 Best Paper Finalist] Pixel Diffusion Transformers for Image Generation

lagernvs. Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)

diffusion-forcing-transformer. [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"

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

UniScene3D. [ECCV 2026] Offical Repository of RGB-Pointmap Pretraining for Unified 3D Scene Understanding

scenetok. [CVPR '26] SceneTok: A Compressed, Diffusable Token Space for 3D Scenes

dreamzero. Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

lingbot-depth. Masked Depth Modeling for Spatial Perception

lingbot-world. Advancing Open-source World Models

NAS3R. [CVPR 2026] From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis

VicaSplat. "VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Frames"

rerun. Visualize, query, and stream to train on multimodal robotics data.

viser. Web-based 3D visualization in Python

ECC. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

HunyuanWorld-Mirror. [ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks

traj-dist-rs. trajectory similarity high performance solution in rust with python binding

MVSNet. MVSNet (ECCV2018) & R-MVSNet (CVPR2019)

robustmvd. Repository for the Robust Multi-View Depth Benchmark

map-anything. MapAnything: Universal Feed-Forward Metric 3D Reconstruction

ARKitScenes. This repo accompanies the research paper, ARKitScenes - A Diverse Real-World Dataset for 3D Indoor Scene Understanding Using Mobile RGB-D Data and contains the data, scripts to visualize and process assets, and training code described in our paper.

co3d. Tooling for the Common Objects In 3D dataset.

BlendedMVS. BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks

wildrgbd. Python

improved-diffusion. Release for Improved Denoising Diffusion Probabilistic Models

guided-diffusion. Python

glide-text2im. GLIDE: a diffusion-based text-conditional image synthesis model

JiT. PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

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

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

Open-DiffusionGS. Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)

VACE. [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

LGM. [ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

TripoSR. TripoSR: Fast 3D Object Reconstruction from a Single Image

3DGPT. Python

infinigen. Infinite Photorealistic Worlds using Procedural Generation

WorldGen. 🌍 WorldGen - Generate Any 3D Scene in Seconds

SPFSplatV2. Official implementation of SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views

lightly-studio. Curate, Annotate, and Manage Your Data in LightlyStudio.

LotteryCodec. Here is the resources and code for the LotteryCodec.

SPFSplat. Python

TrajDL. A python toolkit for deep learning in trajectory data mining

SPFSplat. [ICCV 2025 Highlight] No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views

us-visa-bot. US Visa Bot

RCDS-parallel-programming-in-python. Jupyter Notebook

Hypo3D. ICML 2025 Hypo3D: Exploring Hypothetical Reasoning in 3D

GeometryCrafter. [ICCV 2025] GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

Geo4D. [ICCV 2025 Highlight] Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

DiffGS. [NeurIPS'2024]: DiffGS: Functional Gaussian Splatting Diffusion

PyTorch-VAE. A Collection of Variational Autoencoders (VAE) in PyTorch.

DiffSplat. [ICLR 2025] Official implementation of "DiffSplat: Repurposing Image Diffusion Models for Scalable 3D Gaussian Splat Generation".

latentsplat. [ECCV 2024] Implementation of latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

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

diff-gaussian-rasterization. Differentiable gaussian rasterization with depth, alpha, normal map and extra per-Gaussian attributes, also support camera pose gradient

generative-models. Generative Models by Stability AI

mast3r. Grounding Image Matching in 3D with MASt3R

dust3r. DUSt3R: Geometric 3D Vision Made Easy

HiNet. Official PyTorch implementation of "HiNet: Deep Image Hiding by Invertible Network" (ICCV 2021)

DeepMIH. Official repository of "DeepMIH: Deep Invertible Network for Multiple Image Hiding", TPAMI 2022.

bidastereo. [ECCV 2024] Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching.

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

CF-3DGS. Python

real-state-10k. The real state 10k dataset from https://google.github.io/realestate10k

3dgs_render_python. Python

diff-gaussian-rasterization. Cuda

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

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

vggsfm. VGGSfM: Visual Geometry Grounded Deep Structure From Motion

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

point-e. Point cloud diffusion for 3D model synthesis

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

VAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

CVinW_Readings. A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

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

Awesome-Video-Diffusion. A curated list of recent diffusion models for video generation, editing, and various other applications.

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

Ctrl-Adapter. Official implementation of Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model (ICLR 2025 Oral)

stable-diffusion. Jupyter Notebook

ControlNet. Let us control diffusion models!

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

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

stable-diffusion-webui. Stable Diffusion web UI

cnnimageretrieval-pytorch. CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

deep-image-retrieval. End-to-end learning of deep visual representations for image retrieval

awesome-domain-adaptation. A collection of AWESOME things about domain adaptation

Hierarchical-Localization. Visual localization made easy with hloc

visuallocalizationbenchmark. Python

pixloc. Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)

MVSNet_pytorch. PyTorch Implementation of MVSNet

SegFormer. Official PyTorch implementation of SegFormer

CIRKD. Official implementations of CIRKD: Cross-Image Relational Knowledge Distillation for Semantic Segmentation and implementations on Cityscapes, ADE20K, COCO-Stuff., Pascal VOC and CamVid.

NIID-Net. Code for "NIID-Net: Adapting Surface Normal Knowledge for Intrinsic Image Decomposition in Indoor Scenes" TVCG

deep-iterative-surface-normal-estimation. Code repository for our paper: Deep Iterative Surface Normal Estimation

IRS. IRS: A Large Synthetic Indoor Robotics Stereo Dataset for Disparity and Surface Normal Estimation

RGBD2Normal. Code for Deep Surface Normal Estimation with Hierarchical RGB-D Fusion (CVPR2019)

DPT. Dense Prediction Transformers

RGBD_Semantic_Segmentation_PyTorch. [ECCV 2020] PyTorch Implementation of some RGBD Semantic Segmentation models.

Depth2HHA-python. Use python3 to convert depth image into hha image

moco. PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

pytorch-OpCounter. Count the MACs / FLOPs of your PyTorch model.

yolact. A simple, fully convolutional model for real-time instance segmentation.

Swin-Transformer-Semantic-Segmentation. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.

21LPCVC-UAV_VIdeo_Track-Sample-Solution. Python

pointnet.pytorch. pytorch implementation for "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation" https://arxiv.org/abs/1612.00593

structure_knowledge_distillation. The official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation'. (CVPR 2019 ORAL) and extension to other tasks.

DSRL. Implementation of CVPR 2020 Dual Super-Resolution Learning for Semantic Segmentation

opencv. Open Source Computer Vision Library

network-slimming. Network Slimming (Pytorch) (ICCV 2017)

Deformable-ConvNets. Deformable Convolutional Networks

UPSNet. UPSNet: A Unified Panoptic Segmentation Network

Deformable-Convolution-V2-PyTorch. Deformable ConvNets V2 (DCNv2) in PyTorch

pytorch-superpoint. Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629

Class-balanced-loss-pytorch. Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"

DALI. A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

openseg.pytorch. The official Pytorch implementation of OCNet, OCRNet, and SegFix.

GCNv2_SLAM. Real-time SLAM system with deep features

semantic-segmentation. Nvidia Semantic Segmentation monorepo

awesome-semantic-segmentation-pytorch. Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)

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

apex. A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

DANet. Dual Attention Network for Scene Segmentation (CVPR2019)

nvidia-docker. Build and run Docker containers leveraging NVIDIA GPUs

pytorch-sync-batchnorm-example. How to use Cross Replica / Synchronized Batchnorm in Pytorch

HRNet-Semantic-Segmentation. The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

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

flops-counter.pytorch. Flops counter for neural networks in pytorch framework

deform_conv_pytorch. PyTorch Implementation of Deformable Convolution

Attention-Gated-Networks. Use of Attention Gates in a Convolutional Neural Network / Medical Image Classification and Segmentation

RACNN-pytorch. This is a third party implementation of RA-CNN in pytorch.

fast-reid. SOTA Re-identification Methods and Toolbox

Non-local_pytorch. Implementation of Non-local Block.

WS-DAN.PyTorch. A PyTorch implementation of WS-DAN (Weakly Supervised Data Augmentation Network) for FGVC (Fine-Grained Visual Classification)

LearnToPayAttention. PyTorch implementation of ICLR 2018 paper Learn To Pay Attention (and some modification)

carla. Open-source simulator for autonomous driving research.

awesome-autonomous-vehicles. Curated List of Self-Driving Cars and Autonomous Vehicles Resources

AutonomousVehiclePaper. 无人驾驶相关论文速递

CAL. [CoRL'18] Conditional Affordance Learning

research. dataset and code for 2016 paper "Learning a Driving Simulator"

mmdetection. OpenMMLab Detection Toolbox and Benchmark

class-balanced-loss. Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

DCL. Destruction and Construction Learning for Fine-grained Image Recognition

nitrain. Train AI models efficiently on medical images using any framework

self-ensemble-visual-domain-adapt. Code repository for the small image experiments our paper 'Self-ensembling for Domain Adaptation'

senet.pytorch. PyTorch implementation of SENet

reid-strong-baseline. Bag of Tricks and A Strong Baseline for Deep Person Re-identification

fast-MPN-COV. @CVPR2018: Efficient unrolling iterative matrix square-root normalized ConvNets, implemented by PyTorch (and code of B-CNN,Compact bilinear pooling etc.) for training from scratch & finetuning.

siamese-triplet. Siamese and triplet networks with online pair/triplet mining in PyTorch

pytorch-cifar. 95.47% on CIFAR10 with PyTorch

deep-residual-networks. Deep Residual Learning for Image Recognition

cvpr18-inaturalist-transfer. Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning. CVPR 2018

inat_comp. iNaturalist competition details

pytorch-vgg-cifar10. This is the PyTorch implementation of VGG network trained on CIFAR10 dataset

pytorch-cifar100. Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)

MobileNet-Caffe. Caffe Implementation of Google's MobileNets (v1 and v2)

caffe. Caffe: a fast open framework for deep learning.

caffe-mobilenet. A caffe implementation of mobilenet's depthwise convolution layer.

models. Models and examples built with TensorFlow

examples. A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

pytorch-cnn-visualizations. Pytorch implementation of convolutional neural network visualization techniques

tensorflow. An Open Source Machine Learning Framework for Everyone

JDDA-Master. Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation（AAAI-2019）

Deep-Mutual-Learning. TensorFlow Implementation of Deep Mutual Learning

DANN. pytorch implementation of Domain-Adversarial Training of Neural Networks

adversarial-feature-augmentation. Code for the paper "Adversarial Feature Augmentation for Unsupervised Domain Adaptation", CVPR 2018

domain_adversarial_neural_network. Domain Adaptation Representation Learning Algorithm (as published in JMLR 2016)

fastswa-semi-sup. Improving Consistency-Based Semi-Supervised Learning with Weight Averaging

STL10. Python utilities for reading the STL-10 dataset: http://cs.stanford.edu/~acoates/stl10/

realistic-ssl-evaluation. Open source release of the evaluation benchmark suite described in "Realistic Evaluation of Deep Semi-Supervised Learning Algorithms"

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

arcface-pytorch. Python

VAT-pytorch. Virtual Adversarial Training (VAT) implementation for PyTorch

ladder. Ladder network is a deep learning algorithm that combines supervised and unsupervised learning

mean-teacher. A state-of-the-art semi-supervised method for image recognition

Cutout. 2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552

mixup-cifar10. mixup: Beyond Empirical Risk Minimization

ESPNet. ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

espnet. End-to-End Speech Processing Toolkit

pytorch-generative-model-collections. Collection of generative models in Pytorch version.

pretrained-models.pytorch. Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

pytorch-playground. Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)

resnet-protofiles. Caffe Protofiles for MSRA ResNet: train prototxt

ResNet-on-Cifar10. Reimplementation ResNet on cifar10 with caffe

sphereface. Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.

caffe-windows. Configure Caffe in one hour for Windows users.

arcface-caffe. insightface-caffe

GoogleNet-BN. GoogleNet-BN,namely InceptionNetV2 based on pytorch.

hourglass-facekeypoints-detection. face keypoints deteciton based on stackedhourglass

caffe_to_torch_to_pytorch. Python

cbp. Multimodal Compact Bilinear Pooling for Torch7

SENet. Squeeze-and-Excitation Networks

CliqueNet. Convolutional Neural Networks with Alternately Updated Clique (to appear in CVPR 2018)