paper-with-me

홈 › Papers

Enhanced Semantic Extraction and Guidance for UGC Image Super Resolution

2025-04-14 · Yiwen Wang, Ying Liang, Yuxuan Zhang, Xinning Chai, Zhengxue Cheng, Yingsheng Qin, Yucai Yang, Rong Xie, Li Song

Due to the disparity between real-world degradations in user-generated content(UGC) images and synthetic degradations, traditional super-resolution methods struggle to generalize effectively, necessitating a more robust approach to model real-world distortions. In this paper, we propose a novel approach to UGC image super-resolution by integrating semantic guidance into a diffusion framework. Our method addresses the inconsistency between degradations in wild and synthetic datasets by separately simulating the degradation processes on the LSDIR dataset and combining them with the official paired training set. Furthermore, we enhance degradation removal and detail generation by incorporating a pretrained semantic extraction model (SAM2) and fine-tuning key hyperparameters for improved perceptual fidelity. Extensive experiments demonstrate the superiority of our approach against state-of-the-art methods. Additionally, the proposed model won second place in the CVPR NTIRE 2025 Short-form UGC Image Super-Resolution Challenge, further validating its effectiveness. The code is available at https://github.c10pom/Moonsofang/NTIRE-2025-SRlab.

📄 PDF Abstract BibTeX arXiv:2504.09887

Code (1)

moonsofang/ntire-2025-srlab 공식 구현 pytorch

Tasks

Image Super-ResolutionSuper-Resolution

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning

2025-12-04 · Wentao Wang, Chunyang Liu, Kehua Sheng, Bo Zhang 외 arxiv

The growing exploration of Large Language Models (LLM) and Vision-Language Models (VLM) has opened avenues for enhancing the effectiveness of reinforcement learning (RL). However, existing LLM-based RL methods often focu…

Reinforcement Learning

HoliSDiP: Image Super-Resolution via Holistic Semantics and Diffusion Prior

2024-11-27 · Li-Yuan Tsao, Hao-Wei Chen, Hao-Wei Chung, Deqing Sun 외

Text-to-image diffusion models have emerged as powerful priors for real-world image super-resolution (Real-ISR). However, existing methods may produce unintended results due to noisy text prompts and their lack of spatia…

Image Super-ResolutionSegmentationSemantic SegmentationSuper-Resolution

Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes

2020-03-15 · ECCV 2020 8 · Liang Liao, Jing Xiao, Zheng Wang, Chia-Wen Lin 외

Completing a corrupted image with correct structures and reasonable textures for a mixed scene remains an elusive challenge. Since the missing hole in a mixed scene of a corrupted image often contains various semantic in…

Image InpaintingSemantic SegmentationTexture Synthesis

Empowering Semantic-Sensitive Underwater Image Enhancement with VLM

2026-03-13 · Guodong Fan, Shengning Zhou, Genji Yuan, Huiyu Li 외 arxiv

In recent years, learning-based underwater image enhancement (UIE) techniques have rapidly evolved. However, distribution shifts between high-quality enhanced outputs and natural images can hinder semantic cue extraction…

Image ReconstructionImage Enhancement

Revisiting the Perception-Distortion Trade-off with Spatial-Semantic Guided Super-Resolution

2026-03-14 · Dan Wang, Haiyan Sun, Shan Du, Z. Jane Wang 외 arxiv

Image super-resolution (SR) aims to reconstruct high resolution images with both high perceptual quality and low distortion, but is fundamentally limited by the perception-distortion trade-off. GAN-based SR methods reduc…

Image Super-Resolution