Shanxin Yuan

Queen Mary University of London — United Kingdom

Computer Science · Physical Sciences

18h-index2.1kcitations54works1.82yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Image Processing Techniques(26), Human Pose and Action Recognition(16), Image Enhancement Techniques(16), Hand Gesture Recognition Systems(16), Image Processing Techniques and Applications(14)

Publications54 total

HandSCS: Structural Coordinate Space for Animatable Hand Gaussian Splatting
ArXiv.org·2025Open Access
SuperCap: Multi-resolution Superpixel-based Image Captioning
arXiv (Cornell University)·2025Open Access
HanDrawer: Leveraging Spatial Information to Render Realistic Hands Using a Conditional Diffusion Model in Single Stage
ArXiv.org·2025Open Access
Adaptive Multi-modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss
Lecture notes in computer science·2025
ST-ITO: Controlling Audio Effects for Style Transfer with Inference-Time Optimization
arXiv (Cornell University)·2024· 1 citedOpen Access
Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss
arXiv (Cornell University)·2024Open Access
Non-local degradation modeling for spatially adaptive single image super-resolution
Neural Networks·2024· 9 cited
GoLDFormer: A global–local deformable window transformer for efficient image restoration
Journal of Visual Communication and Image Representation·2024· 4 cited
Wavelet-based network for high dynamic range imaging
Computer Vision and Image Understanding·2023· 9 citedOpen Access
Depth-guided deep filtering network for efficient single image bokeh rendering
Neural Computing and Applications·2023· 6 cited
Exploring Effective Mask Sampling Modeling for Neural Image Compression
arXiv (Cornell University)·2023· 3 citedOpen Access
NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds
2023· 14 cited
NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds
arXiv (Cornell University)·2023Open Access
Graph Neural Networks in Vision-Language Image Understanding: A Survey
arXiv (Cornell University)·2023· 2 citedOpen Access
DomainPlus: Cross Transform Domain Learning towards High Dynamic Range Imaging
Proceedings of the 30th ACM International Conference on Multimedia·2022· 12 cited
Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment
arXiv (Cornell University)·2022Open Access
SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-trained Siamese Transformers
Proceedings of the AAAI Conference on Artificial Intelligence·2022· 14 citedOpen Access
SJ-HD^2R: Selective Joint High Dynamic Range and Denoising Imaging for Dynamic Scenes
arXiv (Cornell University)·2022· 3 citedOpen Access
TAPE: Task-Agnostic Prior Embedding for Image Restoration
arXiv (Cornell University)·2022· 4 citedOpen Access
Constrained Predictive Filters for Single Image Bokeh Rendering
IEEE Transactions on Computational Imaging·2022· 23 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Greg Slabaugh(21), Tae‐Kyun Kim(13), Aleš Leonardis(13), Bolun Zheng(12), Qi Tian(9), Jianzhuang Liu(8), Björn Stenger(7), Guillermo Garcia-Hernando(6), Qi Ye(6), Chenggang Yan(6), Radu Timofte(6), Wengang Zhou(5), Yanyun Qu(4), Ming Hong(4), Zhenyong Fu(4), Gyeongsik Moon(3), Ju Yong Chang(3), Kyoung Mu Lee(3), Pavlo Molchanov(3), Jan Kautz(3)