Sicheng Li

Japan Advanced Institute of Science and Technology — Japan

Computer Science · Physical Sciences

8h-index565citations31works0.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Advanced Neural Network Applications(11), 3D Shape Modeling and Analysis(4), Medical Image Segmentation Techniques(3), Computer Graphics and Visualization Techniques(3), Advanced Vision and Imaging(3)

Publications31 total

A Two Stage Generative Model for Controllable Human Head Motion Video Generation
2025
GIFStream: 4D Gaussian-Based Immersive Video with Feature Stream
2025· 2 cited
GSCodec Studio: A Modular Framework for Gaussian Splat Compression
arXiv (Cornell University)·2025Open Access
Selective Synthesis of Large-Area Monolayer Tin Sulfide from Simple Substances
Nano Letters·2025· 3 citedOpen Access
GIFStream: 4D Gaussian-based Immersive Video with Feature Stream
arXiv (Cornell University)·2025Open Access
The Cortical Spatial Responses and Decoding of Emotion Imagery Toward a Novel fNIRS-Based Affective BCI
IEEE Transactions on Neural Systems and Rehabilitation Engineering·2025· 1 citedOpen Access
Cross-Domain Knowledge Integration Framework for Optical Coherence Tomography Images Denoising
SSRN Electronic Journal·2025Open Access
DORec: Decomposed Object Reconstruction and Segmentation Utilizing 2D Self-Supervised Features
IEEE Robotics and Automation Letters·2024
A Tightly Coupled AI-ISP Vision Processor
IEEE Transactions on Circuits and Systems for Video Technology·2024· 3 cited
Vehicle and Pedestrian Detection Based on Improved YOLOv5s
Journal of Vibration Testing and System Dynamics·2024· 1 cited
Interactive Drawing Interface for Aging Anime Face Sketches Using Transformer-Based Generative Model
IEEE Access·2024Open Access
DORec: Decomposed Object Reconstruction and Segmentation Utilizing 2D Self-Supervised Features
arXiv (Cornell University)·2023Open Access
SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory
arXiv (Cornell University)·2022· 1 citedOpen Access
A Drawing Support System for Sketching Aging Anime Faces
2022· 3 cited
Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
arXiv (Cornell University)·2022· 31 citedOpen Access
Interactive drawing interface with 3D animal model retrieval
International Workshop on Advanced Imaging Technology (IWAIT) 2022·2022· 1 cited
CycleGAN with DenseU-Net for Medical Image Synthesis
SSRN Electronic Journal·2022· 1 citedOpen Access
MIA-Former: Efficient and Robust Vision Transformers via Multi-grained Input-Adaptation
arXiv (Cornell University)·2021Open Access
2D3D Medical Image Registration Based on Fully Convolutional Network Approved by Attention Mechanism
2021· 2 cited
Skeleton-Based Interactive Fabrication for Large-Scale Newspaper Sculpture
2021· 2 cited
page 1 of 2Next →

Frequent Co-authors

Haoran Xie(6), Yiyi Liao(6), Kazunori Miyata(5), Hai Li(4), Yiran Chen(4), Chunpeng Wu(3), Lu Yu(3), Yue Wang(3), Zhan Chen(2), Qinghan Li(2), Hong Liu(2), Chaojian Li(2), Zihao Liu(2), Yingyan Lin(2), Wei Wen(2), Yen-Kuang Chen(2), Hao Li(2), Xiang Gao(2), Abudouaihati Batuer(2), Deqing Kong(2)