Real-Time Diffusion-Based Streaming Video Super-Resolution / 基于Diffusion架构的实时视频流超分模型

[CVPR 2025] Official implementation of the paper "TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution".

[CVPR 2025] FaithDiff for Classic Film Rejuvenation, Old Photo Revival, Social Media Restoration, Image Enhancement and AIGC Enhancement.

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

[NeurIPS 2025] 4KAgent: Agentic Any Image to 4K Super-Resolution. An intelligent computer vision agent that can magically restore any image to perfect-4K!

Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)

A sparse attention kernel supporting mix sparse patterns

Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional de…

[ICCV 2025] STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

AppWorld agent with Agentic Context Engineering (ACE)

Evolve your language agent with Agentic Context Engineering (ACE)

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

Official implementation of paper "ACON: Optimizing Context Compression for Long-horizon LLM Agents"

🧠 Make your agents learn from experience. Based on the Agentic Context Engineering (ACE) framework.

Self Supervised Prompt Optimization.

[SIGGRAPH'24] CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization

[CVPR 2025] StdGEN: Semantic-Decomposed 3D Character Generation from Single Images

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

[ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

Multi-view Diffusion for 3D Generation

Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

✂️ Automated high-quality background removal framework for an image using neural networks. ✂️

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

A collection of useful functions for 3D vision & graphics research in Python.

DUSt3R: Geometric 3D Vision Made Easy

Official implementation of "DepthLab: From Partial to Complete"

Main Web Site (Online Books)

[CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

Software developer resume in Latex

An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git