-
Xiaomi Inc.
- BEIJING, CHINA
- https://hongyuanyu.github.io/
Highlights
- Pro
Language
Sort by: Recently starred
Starred repositories
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
[ECCV 2024] InstructIR: High-Quality Image Restoration Following Human Instructions https://huggingface.co/spaces/marcosv/InstructIR
Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks
MINT-1T: A one trillion token multimodal interleaved dataset.
MambaOut: Do We Really Need Mamba for Vision?
Official repo of our paper "SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions"
Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
Open-Sora: Democratizing Efficient Video Production for All
Trading bot running on Binance, Bybit, Bitget, OKX, BingX, and Hyperliquid
Fast Lane, an open-source arbitrage protocol, allows any user to perform arbitrage between Bancor ecosystem protocols and external exchanges and redirect arbitrage profits back to the protocol.
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its…
YOLOv7 to detect bone fractures on X-ray images
Bone Fracture Detection using deep learning (Resnet50) - Final project in the fourth year of the degree
Swift Parameter-free Attention Network for Efficient Super-Resolution
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
This is an official PyTorch implementation of the NeurIPS 2023 paper 《OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling》
Generative Agents: Interactive Simulacra of Human Behavior
FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)
PromptIR: Prompting for All-in-One Blind Image Restoration [NeurIPS 2023]
Real-time Web Dashboard for Optuna.
Pytorch code for "BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment", CVPRW, 1st place in NTIRE 2022 BurstSR Challenge (real-world track).
Unsupervised Learning for Image Registration