paper-with-me

홈 › Papers

Trustworthy SR: Resolving Ambiguity in Image Super-resolution via Diffusion Models and Human Feedback

2024-02-12 · Cansu Korkmaz, Ege Cirakman, A. Murat Tekalp, Zafer Dogan

Super-resolution (SR) is an ill-posed inverse problem with a large set of feasible solutions that are consistent with a given low-resolution image. Various deterministic algorithms aim to find a single solution that balances fidelity and perceptual quality; however, this trade-off often causes visual artifacts that bring ambiguity in information-centric applications. On the other hand, diffusion models (DMs) excel in generating a diverse set of feasible SR images that span the solution space. The challenge is then how to determine the most likely solution among this set in a trustworthy manner. We observe that quantitative measures, such as PSNR, LPIPS, DISTS, are not reliable indicators to resolve ambiguous cases. To this effect, we propose employing human feedback, where we ask human subjects to select a small number of likely samples and we ensemble the averages of selected samples. This strategy leverages the high-quality image generation capabilities of DMs, while recognizing the importance of obtaining a single trustworthy solution, especially in use cases, such as identification of specific digits or letters, where generating multiple feasible solutions may not lead to a reliable outcome. Experimental results demonstrate that our proposed strategy provides more trustworthy solutions when compared to state-of-the art SR methods.

📄 PDF Abstract BibTeX arXiv:2402.07597

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationImage Super-ResolutionSuper-Resolution

Methods 이 논문이 사용한 방법론

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

LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network

2021-09-29 · Nitin Balachandran, Jun-Cheng Chen, Rama Chellappa

Face super-resolution is a challenging and highly ill-posed problem since a low-resolution (LR) face image may correspond to multiple high-resolution (HR) ones during the hallucination process and cause a dramatic identi…

AttributeFace HallucinationHallucinationSuper-Resolution

Instantaneous GNSS Ambiguity Resolution and Attitude Determination via Riemannian Manifold Optimization

2022-05-20 · Xing Liu, Tarig Ballal, Mohanad Ahmed, Tareq Y. Al-Naffouri

We present an ambiguity resolution method for Global Navigation Satellite System (GNSS)-based attitude determination. A GNSS attitude model with nonlinear constraints is used to rigorously incorporate a priori informatio…

Super-Resolving Very Low-Resolution Face Images With Supplementary Attributes

2018-06-01 · CVPR 2018 6 · Xin Yu, Basura Fernando, Richard Hartley, Fatih Porikli

Given a tiny face image, conventional face hallucination methods aim to super-resolve its high-resolution (HR) counterpart by learning a mapping from an exemplar dataset. Since a low-resolution (LR) input patch may corre…

AttributeFace HallucinationHallucinationSuper-Resolution

ECLAIR: Enhanced Clarification for Interactive Responses

2025-03-19 · John Murzaku, Zifan Liu, Md Mehrab Tanjim, Vaishnavi Muppala 외

We present ECLAIR (Enhanced CLArification for Interactive Responses), a novel unified and end-to-end framework for interactive disambiguation in enterprise AI assistants. ECLAIR generates clarification questions for ambi…

Question GenerationQuestion-Generation

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…

Semantic SimilaritySemantic Textual SimilaritySSIMSuper-Resolution