Neural Network Model Restores Damaged Historical Artifacts From Photos
3D images reconstructed from old photographs allow for the exploration of damaged relief carvings through virtual reality
最近新闻
Recent Posts
课题组论文被计算机视觉国内顶会 PRCV 2024 录用
课题组最新论文 Thangka Mural Super-Resolution Based on Nimble Convolution and Overlapping Window Transformer 被大会正式录用
课题组最新论文被计算机视觉国内顶会 PRCV 2023 录用
课题组最新论文 Anime Sketch Coloring Based on Self-Attention Gate and Progressive PatchGAN 被大会正式录用
人工智能在文化遗产保护传承中的价值研究
人工智能在文化遗产保护和传承中的应用具有巨大潜力，可以提升保护管理能力、挖掘文化价值、提高展示水平、扩大传承影响力，并提供智能化的公共文化服务。
实验室最新论文被期刊 JOURNAL OF ELECTRONIC IMAGING 选为封面
本实验室 2023 年 7 月最新发表的论文《Thangka mural style transfer based on progressive style-attentional network and multi-level loss function》被 SCI 期刊《Journal of Electronic Imaging（JEI）》选为封面。
Microsoft Researchers Present InstructDiffusion: A Unifying and Generic AI Framework for Aligning Computer Vision Tasks with Human Instructions
In a groundbreaking stride towards adaptable, generalist vision models, researchers from Microsoft Research Asia have unveiled InstructDiffusion.
Image Recognition Vs. Computer Vision: What Are the Differences?
In the current Artificial Intelligence and Machine Learning industry, “Image Recognition”, and “Computer Vision” are two of the hottest trends.
OpenAI Introduces Fine-Tuning for GPT-3.5 Turbo and GPT-4
OpenAI has announced the ability to fine-tune its powerful language models, including both GPT-3.5 Turbo and GPT-4.
Learning to Grow Machine-Learning Models
New LiGO technique accelerates training of large machine-learning models, reducing the monetary and environmental cost of developing AI applications.
Matthew Kearney: Bringing AI and Philosophy Into Dialogue
The computer science and philosophy double-major aims to advance the field of AI ethics.
Short Story on AI: Forward Pass
A story of an existential crisis under the hood of a humble forward pass.
实验室介绍
Laboratory Introduction
The Computer Vision Lab of Northwest Minzu University focuses on artificial intelligence-based computer vision problems.
Our main research includes image super-resolution, image style transfer, image auto restoration, image auto coloring, and auto line-extraction of ancient mural images.
Our vision is to protect human traditional culture and discover the beauty of the traditional culture using computer science and AI technology.
最近出版
Recent Publications
- Thangka Mural Super-Resolution Based on Nimble Convolution and Overlapping Window Transformer, Pattern Recognition and Computer Vision. PRCV 2024. Lecture Notes in Computer Science, vol 15038. Springer, Singapore
- Thangka Super-Resolution Diffusion Model Based on DCT-Upsample and High-Frequency Focused Attention, Research Square
- Anime Sketch Coloring Based on Self-Attention Gate and Progressive PatchGAN, Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14435. Springer, Singapore.
- Image Inpainting of Thangka Murals Using Edge-Assisted Feature Fusion and Self Attention Based Local Refine Network, IEEE Access, 2023
- Thangka Mural Style Transfer Based on Progressive Style-Attentional Network and Multi-Level Loss Function, Journal of Electronic Imaging, 2023
研究领域
Research Fields
- Image Auto Line DrawingDigital drawings blend art appreciation and preservation via edge detection.
- Image Intelligent InpaintingAI inpainting restores damaged art, filling missing parts for image restoration.
- Image Sketch ColoringAI sketch auto-coloring gains attention in computer vision, recognizing and coloring faces, clothes, and background components, enhancing image illustration.
- Image Style TransferStyle transfer: Recompose images in artistic styles, like famous paintings.
- Image Super ResolutionImage Super Resolution enhances low-resolution images to high-resolution quality.