MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

Bring portraits to life!

Wan: Open and Advanced Large-Scale Video Generative Models

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also …

Open-source unified multimodal model

Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

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

GPT4V-level open-source multi-modal model based on Llama3-8B

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models (CVPR 2024 Highlight)

DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding

③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.

[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images

IQA: Deep Image Structure and Texture Similarity Metric

CVPR 2025: Frequency Dynamic Convolution for Dense Image Prediction

An expert benchmark aiming to comprehensively evaluate the aesthetic perception capacities of MLLMs.

②[CVPR 2024] Low-level visual instruction tuning, with a 200K dataset and a model zoo for fine-tuned checkpoints.

[CVPR2023] Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective

[NeurIPS 2025 D&B🔥] ImgEdit: A Unified Image Editing Dataset and Benchmark

[NeurIPS 2025 Spotlight] Q-Insight: Understanding Image Quality via Visual Reinforcement Learning

[CVPR'20] Official SPAQ & Implementation

Official Repository for PosterGen

[CVPR 2025 Highlight] Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis

Edit-R1: Reinforce Image Editing with Diffusion Negative-Aware Finetuning and MLLM Implicit Feedback

[NeurIPS 2025 Spotlight] VisualQuality-R1 is the first open-sourced NR-IQA model can accurately describe and rate the image quality.

Very Long Natural Scenery Image Prediction by Outpainting, ICCV2019, TensorFlow

Reliable Conflictive Multi-view Learning

ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models