paper-with-me

홈 › Papers

Leveraging Vision-Language Models to Select Trustworthy Super-Resolution Samples Generated by Diffusion Models

2025-06-25 · Cansu Korkmaz, Ahmet Murat Tekalp, Zafer Dogan

Super-resolution (SR) is an ill-posed inverse problem with many feasible solutions consistent with a given low-resolution image. On one hand, regressive SR models aim to balance fidelity and perceptual quality to yield a single solution, but this trade-off often introduces artifacts that create ambiguity in information-critical applications such as recognizing digits or letters. On the other hand, diffusion models generate a diverse set of SR images, but selecting the most trustworthy solution from this set remains a challenge. This paper introduces a robust, automated framework for identifying the most trustworthy SR sample from a diffusion-generated set by leveraging the semantic reasoning capabilities of vision-language models (VLMs). Specifically, VLMs such as BLIP-2, GPT-4o, and their variants are prompted with structured queries to assess semantic correctness, visual quality, and artifact presence. The top-ranked SR candidates are then ensembled to yield a single trustworthy output in a cost-effective manner. To rigorously assess the validity of VLM-selected samples, we propose a novel Trustworthiness Score (TWS) a hybrid metric that quantifies SR reliability based on three complementary components: semantic similarity via CLIP embeddings, structural integrity using SSIM on edge maps, and artifact sensitivity through multi-level wavelet decomposition. We empirically show that TWS correlates strongly with human preference in both ambiguous and natural images, and that VLM-guided selections consistently yield high TWS values. Compared to conventional metrics like PSNR, LPIPS, which fail to reflect information fidelity, our approach offers a principled, scalable, and generalizable solution for navigating the uncertainty of the diffusion SR space. By aligning outputs with human expectations and semantic correctness, this work sets a new benchmark for trustworthiness in generative SR.

📄 PDF Abstract BibTeX arXiv:2506.20832

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SimilaritySemantic Textual SimilaritySSIMSuper-Resolution

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
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

Label Filling via Mixed Supervision for Medical Image Segmentation from Noisy Annotations

2024-10-21 · Ming Li, Wei Shen, Qingli Li, Yan Wang

The success of medical image segmentation usually requires a large number of high-quality labels. But since the labeling process is usually affected by the raters' varying skill levels and characteristics, the estimated …

Image SegmentationLesion SegmentationMedical Image SegmentationSegmentation+1

Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning

2024-10-22 · Zongmeng Zhang, Yufeng Shi, Jinhua Zhu, Wengang Zhou 외

Trustworthiness is an essential prerequisite for the real-world application of large language models. In this paper, we focus on the trustworthiness of language models with respect to retrieval augmentation. Despite bein…

RetrievalRetrieval-augmented Generation

Know Where to Go: Make LLM a Relevant, Responsible, and Trustworthy Searcher

2023-10-19 · Xiang Shi, Jiawei Liu, Yinpeng Liu, Qikai Cheng 외

The advent of Large Language Models (LLMs) has shown the potential to improve relevance and provide direct answers in web searches. However, challenges arise in validating the reliability of generated results and the cre…

HallucinationInformation RetrievalRetrieval

Delineating Knowledge Boundaries for Honest Large Vision-Language Models

2026-04-29 · Junru Song, Yimeng Hu, Yijing Chen, Huining Li 외 arxiv

Large Vision-Language Models (VLMs) have achieved remarkable multimodal performance yet remain prone to factual hallucinations, particularly in long-tail or specialized domains. Moreover, current models exhibit a weak ca…

Spatial-aware Vision Language Model for Autonomous Driving

2025-12-30 · Weijie Wei, Zhipeng Luo, Ling Feng, Venice Erin Liong arxiv

While Vision-Language Models (VLMs) show significant promise for end-to-end autonomous driving by leveraging the common sense embedded in language models, their reliance on 2D image cues for complex scene understanding a…

Scene UnderstandingAutonomous DrivingSpatial Reasoning