Xin Di
Scholar

Xin Di

Google Scholar ID: 2lzOXwQAAAAJ
University of Science and Technology of China
Computer visionLow level visionSuper-resolutionComputer vision\Low level vision\Super-resolution
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
178
 
H-index
8
 
i10-index
7
 
Publications
12
 
Co-authors
0
 
Contact
Emaildx9826@mail.ustc.edu.cn
Publications
10 items
PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-Resolution
2026
Cited
0
Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2
2026
Cited
0
GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting
2026
Cited
0
ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysis
2026
Cited
0
REE-TTT: Highly Adaptive Radar Echo Extrapolation Based on Test-Time Training
arXiv.org · 2026
Cited
0
RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions
2025
Cited
0
PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement
2025
Cited
0
Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling
2025
Cited
0
Resume
Academic Achievements
  • 2025: Paper accepted by IJCAI 2025 (Co-first Author)
  • 2025: Paper accepted by CVPR 2025 (First Author)
  • 2025: Paper accepted by NeurIPS 2025 (Co-first Author)
  • 2025: Paper accepted by AAAI 2025
  • Mar 2024: 2nd Place in Real-Time Super-Resolution Challenge (CVPR2024W)
  • Mar 2024: 2nd Place in Efficient Super-Resolution Challenge (CVPR2024W)
  • Multiple preprints on Low-Level Vision, Image Restoration, Video Enhancement, and Gaussian Splatting as co-first or key author