ChenHsing

FlashMotion. [CVPR 2026] FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance

OpenRT. Open-source red teaming framework for MLLMs with 42+ attack methods

FlashPortrait. [CVPR2026]We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference speed.

Wan-Move. [NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

ProLongVid. [EMNLP 2025 Oral] ProLongVid: A Simple but Strong Baseline for Long-context Video Instruction Tuning

StableAvatar. We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.

Wan2.2-TI2V-5B-Turbo. 4-steps distilled version of Wan2.2-TI2V-5B

Lumos. [ICLR 2026] Lumos Project: Frontier video unified model research by Alibaba DAMO Academy.

video-generation-survey. A reading list of video generation

ChenHsing.github.io. JavaScript

ReasonGen-R1. Official respository for ReasonGen-R1

ComfyUI_StableAnimator. ComfyUI nodes for StableAnimator

VideoX-Fun. 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

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

FramePack. Lets make video diffusion practical!

SimpleAR. Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"

Awesome-Physics-Cognition-based-Video-Generation. A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.

CreatiLayout. [ICCV 2025] CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation

MagicMotion. [ICCV 2025] MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance

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

RealisDance. The official implementation of RealisDance

StableAnimator. [CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.

ccf-deadlines. ⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)

awesome-diffusion-v2v. Awesome diffusion Video-to-Video (V2V). A collection of paper on diffusion model-based video editing, aka. video-to-video (V2V) translation. And a video editing benchmark code.

HunyuanDiT. Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

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

fiftyone. Refine high-quality datasets and visual AI models

MotionFollower. [ICCV2025] MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion

SmartEdit. Official code of SmartEdit [CVPR-2024 Highlight]

generative-models. Generative Models by Stability AI

NExT-GPT. Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model

qformer. Implementation of Qformer from BLIP2 in Zeta Lego blocks.

PhotoMaker. PhotoMaker [CVPR 2024]

PixArt-alpha. PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

SEINE. [ICLR 2024] SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

adaptive-diffusion. [CVPR'2024] Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

HD-VG-130M. The HD-VG-130M Dataset

MotionGPT. [NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

SVD_Xtend. Stable Video Diffusion Training Code and Extensions.

latent-consistency-model. Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

sdxl-turbo-cog. SDXL-Turbo is a real-time synthesis model, derived from SDXL 1.0, and utilizes a training method called Adversarial Diffusion Distillation (ADD). It achieves high image quality within one to four sampling steps

AutoStory. [IJCV'24] AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort

freecontrol. Official implementation of CVPR 2024 paper: "FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition"

VideoBLIP. Supercharged BLIP-2 that can handle videos

ART.V.

VIDiff.

MotionEditor. [CVPR2024] MotionEditor is the first diffusion-based model capable of video motion editing.

consistencydecoder. Consistency Distilled Diff VAE

NRVQA. no reference image/video quaity assessment(BRISQUE/NIQE/PIQE/DIQA/deepBIQ/VSFA

Open-VCLIP. Python

loveu-tgve-2023. Official GitHub repository for the Text-Guided Video Editing (TGVE) competition of LOVEU Workshop @ CVPR'23.

InstructDiffusion. PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

Ground-A-Video. Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models (ICLR 2024)

AnimateDiff. Official implementation of AnimateDiff.

PVDM. [CVPR'23] Video Probabilistic Diffusion Models in Projected Latent Space

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

ProPainter. [ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

Make-A-Protagonist. Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts

Veri3d. Python

CrossLoc. [CVPR'22] CrossLoc localization: a cross-modal visual representation learning method for absolute localization

SwinGNN. SwinGNN: diffusion model for graph generation

PSG-biased-annotation. Panoptic Scene Graph Biased Annotation

WaterScenes. Official repository for WaterScenes dataset

Awesome-Radar-Camera-Fusion. Radar Camera Fusion in Autonomous Driving

ICL_SSL. [IEEE TNNLS 2022] An official source code for paper Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning.

Awesome-Skeleton-based-Action-Recognition. A curated paper list of awesome skeleton-based action recognition.

Robot_Navigation_RL. Two paper About robot navigation in dynamic environment

DealMVC. [ACM MM 2023] An official source code for paper "DealMVC: Dual Contrastive Calibration for Multi-view Clustering"

CONVERT. [ACM MM 2023] An official source code for paper "CONVERT: Contrastive Graph Clustering with Reliable Augmentation".

CCGC. [AAAI 2023] An official source code for paper Cluster-guided Contrastive Graph Clustering Network.

ICCV23-IDPT. The code for the paper "Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models" (ICCV'23).

BadHash. The official implementation of BadHash

AdvCLIP. The implementation of our ACM MM 2023 paper "AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning"

SigmaCCS. [Communications Chemistry 2023] Highly accurate and large-scale collision cross section prediction with graph neural network for compound identification

NeMF. [ICCV 2023] NeMF: Inverse Volume Rendering with Neural Microflake Field

3D_Semantic_Subspace_Traverser. C++

ScaleVLN. [ICCV 2023 Oral]: Scaling Data Generation in Vision-and-Language Navigation

RFN. [TCSVT2022] Industria Scene Text Detection

SkeletonMAE. SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training

CMCIR. [IEEE T-PAMI 2023] Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

DTP. [ICCV 2023] Official implement of <Disentangle then Parse: Night-time Semantic Segmentation with Illumination Disentanglement>

FIMVC-VIA. [IEEE TNNLS 2022] Code of "Fast Incomplete Multi-view Clustering with View-independent Anchors"

EOMSC-CA. [AAAI 2022] Code of "Efficient One-pass Multi-view Subspace Clustering with Consensus Anchors"

SiT. Official implementation of "Self-slimmed Vision Transformer" (ECCV2022)

LoGoNet. [CVPR2023] LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion

Awesome-Nighttime-Enhancement. Collection of recent nighttime enhancement works, including papers, codes, datasets, and metrics.

FogRemoval. [ACCV22] Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal, https://arxiv.org/abs/2210.03061

S-Aware-network. [AAAI23] Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning, https://arxiv.org/abs/2211.14751

nighttime_dehaze. [ACMMM2023] "Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution", https://arxiv.org/abs/2308.01738

night-enhancement. [ECCV2022] "Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression", https://arxiv.org/abs/2207.10564

DC-ShadowNet-Hard-and-Soft-Shadow-Removal. [ICCV2021]"DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network", https://arxiv.org/abs/2207.10434

NVDS. ICCV 2023 "Neural Video Depth Stabilizer" (NVDS) & TPAMI 2024 "NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation" (NVDS+)

UAL. The code for ECCV2022 paper: Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval

ISR_ICCV2023_Oral. The code for ICCV2023 Oral paper: Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification

SimDA. [CVPR 2024] SimDA: Simple Diffusion Adapter for Efficient Video Generation

VTSNN. Public code for VTSNN: A Virtual Temporal Spiking Neural Network (Fron. Neur.)

ICLR_TINY_SNN. Offical implementation of "When Spiking Neural Networks Meet Temporal Attention Image Decoding And AdaptiveE Spiking Neuron" (ICLR2023)

GAC. Offical implementation of "Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks" (AAAI2024)

ASDA. Python

MG-SCR. [IJCAI-2021] Official Codes for "Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification"

SGE-LA. [IJCAI-2020] Official Codes for "Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identification"

Locality-Awareness-SGE. [TPAMI-2022] Official Codes for "A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification"

TranSG. [CVPR-2023] Official Codes for "TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification"

SM-SGE. [ACMMM-2021] Official Codes for "SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification"

SimMC. [IJCAI-2022] Official Codes for "SimMC: Simple Masked Contrastive Learning of Skeleton Representations for Unsupervised Person Re-Identification"

Hi-MPC. [IJCV-2024] Official Codes for "Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identification"

NvEM. [ACM MM 2021 Oral] Official repo of "Neighbor-view Enhanced Model for Vision and Language Navigation"

DeRy. [NeurIPS2022] Deep Model Reassembly

ConsistentTeacher. [CVPR2023 Highlight] Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection

Openvino_Yolov5_async. yolov5的openvino模型，带异步推理

AdvEncoder. The implementation of our ICCV 2023 paper "Downstream-agnostic Adversarial Examples"

RelightHuman.

C3BN. accepted by ICME2023 oral（CCF B）

AAAI2023-PVD. [IJCV] Official Implementation of PVD and PVDAL: http://sk-fun.fun/PVD-AL/

DiffusionTrack. [AAAI 2024] DiffusionTrack: Diffusion Model For Multi-Object Tracking. DiffusionTrack is the first work to employ the diffusion model for multi-object tracking by formulating it as a generative noise-to-tracking diffusion process.

LVOS.

PBRNet. The code is for PBRnet for action detection

CoDT. The implementaion of CoDT on the task of NTU-60+->PKUMMD

Variational-Degeneration-to-Structural-Refinement.

UniPC. [NeurIPS 2023] UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models

Math-Reasoning-With-PLMs. EMNLP22: Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem

UDR-S2Former_deraining. [ICCV'23] Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks

SnowFormer. This is the official implementation code repository of SnowFormer: Scale-aware Transformer via Context Interaction for Single Image Desnowing

DiffMIC. [MICCAI 2023] DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification

ViWS-Net. [ICCV 2023] Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation

SIGA. [CVPR2023] Self-supervised Implicit Glyph Attention for Text Recognition

RecommendFlow. A Industrialization recommendation system which can easy to build pipeline between local/hdfs train data and tensorflow2.x model.

FaissSearcher. a common faiss searcher

VideoDesnowing. [ICCV 2023] Snow Removal in Video: A New Dataset and A Novel Method

MaskedDenoising. [CVPR 2023] Masked Image Training for Generalizable Deep Image Denoising https://arxiv.org/abs/2303.13132

Co-DETR. [ICCV 2023] DETRs with Collaborative Hybrid Assignments Training

HoP. [ICCV 2023] Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction

MutexMatch4SSL. "MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization" by Yue Duan (TNNLS)

VQ-Font. [ICCV 2023] Few shot font generation via transferring similarity guided global and quantization local styles

VPD. [ICCV 2023] VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to downstream visual perception tasks.

Exp-BLIP. Official implementation of BMVC2023 Oral paper: 《Describe Your Facial Expressions by Linking Image Encoders and Large Language Models》

Data-Copilot. Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow

Parameterized-Cost-Volume-for-Stereo-Matching. PCVNet (ICCV2023)

XNet. [ICCV2023] XNet: Wavelet-Based Low and High Frequency Merging Networks for Semi- and Supervised Semantic Segmentation of Biomedical Images

SPC. [BMVC2023] Spatial and Planar Consistency for Semi-Supervised Volumetric Medical Image Segmentation

DS2DP. The official implement of DS2DP [TGRS 2022]

ProST. Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval --ICCV2023 Oral

Partial2Complete. [ICCV 2023] P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds

BACL. Balanced Classification: A Unified Framework for Long-Tailed Object Detection (TMM 2023)

ETPNav. [TPAMI 2024] Official repo of "ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments"

DT-ST. Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation(CVPR-2023)

CCD. [ICCV2023] Self-supervised Character-to-Character Distillation for Text Recognition

IAGNet. The Pytorch implementation of Grounding 3D Object Affordance from 2D Interactios in Images.

PRG4SSL-MNAR. "Towards Semi-supervised Learning with Non-random Missing Labels" by Yue Duan (ICCV 2023)

CASE. Accepted by ICCV2023, Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach

DDS2M. The official implementation of DDS2M [ICCV 2023].

PCS. Boosting Single Image Super-Resolution via Partial Channel Shifting.

ViECap. Transferable Decoding with Visual Entities for Zero-Shot Image Captioning, ICCV 2023

CausalVLR. CausalVLR: A Toolbox and Benchmark for Vision-Language Causal Reasoning (多模态因果推理开源框架)

TF-ICON. [ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official Implementation)

VLN-BEVBert. [ICCV 2023] Official repo of "BEVBert: Multimodal Map Pre-training for Language-guided Navigation"

PanoSwinTransformerObjectDetection. Python

Awesome-Open-Vocabulary. (TPAMI 2024) A Survey on Open Vocabulary Learning

Awesome-Video-Diffusion-Models. [CSUR] A Survey on Video Diffusion Models

mmagic. OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.

awesome-AI-system. paper and its code for AI System

svdiff-pytorch. Implementation of "SVDiff: Compact Parameter Space for Diffusion Fine-Tuning"

VideoCrafter. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

semi-vit. PyTorch implementation of Semi-supervised Vision Transformers

adamae. [CVPR'23] AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

SVFormer. Python

SSP3D. [ECCV 2022, Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors]

TALLFormer. Python

mmaction2. OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

VideoMAE. [NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

VideoTransformer-pytorch. PyTorch implementation of a collections of scalable Video Transformer Benchmarks.

jonbarron.github.io. HTML

UP-TAL. [CVPR2022] Unsupervised Pre-training for Temporal Action Localization Tasks (UP-TAL)

unbiased-teacher. PyTorch code for ICLR 2021 paper Unbiased Teacher for Semi-Supervised Object Detection

FSL-Mate. FSL-Mate: A collection of resources for few-shot learning (FSL).

EIL. Python

PanoBasic. Matlab Toolbox for Panorama Image Processing

A-Single-View-3D-Object-Point-Cloud-Reconstruction. 3D-ReConstnet: A Single-View 3D-Object Point Cloud Reconstruction Network for more details,please see this link:and please cite our paper: https://ieeexplore.ieee.org/document/9086481?source=authoralert B. Li, Y. Zhang, B. Zhao and H. Shao, "3D-ReConstnet: A Single-View 3D-Object Point Cloud Reconstruction Network," in IEEE Access, vol. 8, pp. 83782-83790, 2020, doi: 10.1109/ACCESS.2020.2992554.

A-Single-View-3D-Object-Point-Cloud-Reconstruction. 3D-ReConstnet: A Single-View 3D-Object Point Cloud Reconstruction Network for more details,please see this link:and please cite our paper: https://ieeexplore.ieee.org/document/9086481?source=authoralert B. Li, Y. Zhang, B. Zhao and H. Shao, "3D-ReConstnet: A Single-View 3D-Object Point Cloud Reconstruction Network," in IEEE Access, vol. 8, pp. 83782-83790, 2020, doi: 10.1109/ACCESS.2020.2992554.

pytorch_deephash. Pytorch implementation of Deep Learning of Binary Hash Codes for Fast Image Retrieval, CVPRW 2015

keras-ctpn. keras复现场景文本检测网络CPTN: 《Detecting Text in Natural Image with Connectionist Text Proposal Network》；欢迎试用，关注，并反馈问题...

keras-yolo3. A Keras implementation of YOLOv3 (Tensorflow backend)

Navigation-system. Java

Compress-software. Java

Course-scheduling-system. Java

YOLO-TrafficDetection. Python

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

pytorch-vsumm-reinforce. Unsupervised video summarization with deep reinforcement learning (AAAI'18)

GitRepo. C#

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

WMSManager. Java