official code of "MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction"

[ICCV 2025] This is the official PyTorch codes for the paper: "DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution"

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Open-source simulator for autonomous driving research.

Official code for the paper: Depth Anything At Any Condition

[ICCV 2023] MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond.

[CVPR 2025 Oral & Award Candidate] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

[ICCV 2025] DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation

The official code for the paper: LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

Unified Vision-Language-Action Model

Dingo: A Comprehensive AI Data Quality Evaluation Tool

Adding Scene-Centric Forecasting Control to Occupancy World Model

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

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

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

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

ICCV 2025 | Nexus: Decoupled Diffusion Sparks Adaptive Scene Generation

Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

A Paper List for Humanoid Robot Learning.

Enhancing Representations through Heterogeneous Self-Supervised Learning (TPAMI 2025)

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Wan: Open and Advanced Large-Scale Video Generative Models

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.