collaborators

9 papers

cs.CV2026

DROSR: Degradation-Disentangled Representation for Real-World Omnidirectional Image Super-Resolution

Hongyu An, Xinfeng Zhang, Xu Fan +3

With the growing demand for immersive visual experiences, high-quality omnidirectional images (ODIs) have become increasingly important. However, limitations in imaging devices and…

cs.CV2026

Video Compression with Hierarchical Temporal Neural Representation

Jun Zhu, Xinfeng Zhang, Lv Tang +3

Video compression has recently benefited from implicit neural representations (INRs), which model videos as continuous functions. INRs offer compact storage and flexible reconstruc…

cs.CV2026

Frequency-aware Neural Representation for Videos

Jun Zhu, Xinfeng Zhang, Lv Tang +3

Implicit Neural Representations (INRs) have emerged as a promising paradigm for video compression. However, existing INR-based frameworks typically suffer from inherent spectral bi…

eess.IV2025

SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization

Gai Zhang, Xinfeng Zhang, Lv Tang +3

Light field images capture multi-view scene information and play a crucial role in 3D scene reconstruction. However, their high-dimensional nature results in enormous data volumes,…

cs.CV2025

UAR-NVC: A Unified AutoRegressive Framework for Memory-Efficient Neural Video Compression

Jia Wang, Xinfeng Zhang, Gai Zhang +3

Implicit Neural Representations (INRs) have demonstrated significant potential in video compression by representing videos as neural networks. However, as the number of frames incr…

cs.CV2025

Spatio-Temporal Distortion Aware Omnidirectional Video Super-Resolution

Hongyu An, Xinfeng Zhang, Shijie Zhao +2

Omnidirectional videos (ODVs) provide an immersive visual experience by capturing the 360° scene. With the rapid advancements in virtual/augmented reality, metaverse, and generati…