paper-with-me

홈 › Papers

PocketSR: The Super-Resolution Expert in Your Pocket Mobiles

2025-10-03 · Haoze Sun, Linfeng Jiang, Fan Li, Renjing Pei, Zhixin Wang, Yong Guo, Jiaqi Xu, Haoyu Chen, Jin Han, Fenglong Song, Yujiu Yang, Wenbo Li arxiv

Real-world image super-resolution (RealSR) aims to enhance the visual quality of in-the-wild images, such as those captured by mobile phones. While existing methods leveraging large generative models demonstrate impressive results, the high computational cost and latency make them impractical for edge deployment. In this paper, we introduce PocketSR, an ultra-lightweight, single-step model that brings generative modeling capabilities to RealSR while maintaining high fidelity. To achieve this, we design LiteED, a highly efficient alternative to the original computationally intensive VAE in SD, reducing parameters by 97.5% while preserving high-quality encoding and decoding. Additionally, we propose online annealing pruning for the U-Net, which progressively shifts generative priors from heavy modules to lightweight counterparts, ensuring effective knowledge transfer and further optimizing efficiency. To mitigate the loss of prior knowledge during pruning, we incorporate a multi-layer feature distillation loss. Through an in-depth analysis of each design component, we provide valuable insights for future research. PocketSR, with a model size of 146M parameters, processes 4K images in just 0.8 seconds, achieving a remarkable speedup over previous methods. Notably, it delivers performance on par with state-of-the-art single-step and even multi-step RealSR models, making it a highly practical solution for edge-device applications.

📄 PDF Abstract BibTeX arXiv:2510.03012

Code (0)

등록된 구현이 없습니다.

Tasks

Image Super-Resolution

Similar Papers 제목 키워드 기반

ProFSA: Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment

2023-10-11 · Bowen Gao, Yinjun Jia, Yuanle Mo, Yuyan Ni 외

Pocket representations play a vital role in various biomedical applications, such as druggability estimation, ligand affinity prediction, and de novo drug design. While existing geometric features and pretrained represen…

Drug Design

RoboPocket: Improve Robot Policies Instantly with Your Phone

2026-03-05 · Junjie Fang, Wendi Chen, Han Xue, Fangyuan Zhou 외 arxiv

Scaling imitation learning is fundamentally constrained by the efficiency of data collection. While handheld interfaces have emerged as a scalable solution for in-the-wild data acquisition, they predominantly operate in …

From Holo Pockets to Electron Density: GPT-style Drug Design with Density

2026-05-09 · Jiahao Chen, Letian Gao, Yanhao Zhu, Wenbiao Zhou 외 arxiv

Recent advances in generative modeling have enabled significant progress in structure-based drug design (SBDD). Existing methods typically condition molecule generation on empty binding pockets from holo complexes, overl…

Point Clouds

SiteFerret: beyond simple pocket identification in proteins

2022-12-22 · Luca Gagliardi, Walter Rocchia

We present a novel method for the automatic detection of pockets on protein molecular surfaces. The algorithm is based on an ad hoc hierarchical clustering of virtual SES probe spheres obtained from the geometrical primi…

Anomaly DetectionClustering

CoSP: Co-supervised pretraining of pocket and ligand

2022-06-23 · Zhangyang Gao, Cheng Tan, Lirong Wu, Stan Z. Li

Can we inject the pocket-ligand interaction knowledge into the pre-trained model and jointly learn their chemical space? Pretraining molecules and proteins has attracted considerable attention in recent years, while most…

Contrastive LearningSpecificity