8 papers
EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3
Chengxi Zeng, Yuxuan Jiang, Aaron Zhang
The Segment Anything Model 3 (SAM3) advances visual understanding with Promptable Concept Segmentation (PCS) across images and videos, but its unified architecture (shared vision b…
GFix: Perceptually Enhanced Gaussian Splatting Video Compression
Siyue Teng, Ge Gao, Duolikun Danier +5
3D Gaussian Splatting (3DGS) enhances 3D scene reconstruction through explicit representation and fast rendering, demonstrating potential benefits for various low-level vision task…
Compressed Video Super-Resolution based on Hierarchical Encoding
Yuxuan Jiang, Siyue Teng, Qiang Zhu +6
This paper presents a general-purpose video super-resolution (VSR) method, dubbed VSR-HE, specifically designed to enhance the perceptual quality of compressed content. Targeting s…
Agglomerating Large Vision Encoders via Distillation for VFSS Segmentation
Chengxi Zeng, Yuxuan Jiang, Fan Zhang +2
The deployment of foundation models for medical imaging has demonstrated considerable success. However, their training overheads associated with downstream tasks remain substantial…
C2D-ISR: Optimizing Attention-based Image Super-resolution from Continuous to Discrete Scales
Yuxuan Jiang, Chengxi Zeng, Siyue Teng +4
In recent years, attention mechanisms have been exploited in single image super-resolution (SISR), achieving impressive reconstruction results. However, these advancements are stil…
Blind Video Super-Resolution based on Implicit Kernels
Qiang Zhu, Yuxuan Jiang, Shuyuan Zhu +3
Blind video super-resolution (BVSR) is a low-level vision task which aims to generate high-resolution videos from low-resolution counterparts in unknown degradation scenarios. Exis…