paper-with-me

Papers

Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception Priors

2024-12-10 · Jiangang Wang, Qingnan Fan, Qi Zhang, Haigen Liu, Yuhang Yu, Jinwei Chen, Wenqi Ren

Owing to the robust priors of diffusion models, recent approaches have shown promise in addressing real-world super-resolution (Real-SR). However, achieving semantic consistency and perceptual naturalness to meet human perception demands remains difficult, especially under conditions of heavy degradation and varied input complexities. To tackle this, we propose Hero-SR, a one-step diffusion-based SR framework explicitly designed with human perception priors. Hero-SR consists of two novel modules: the Dynamic Time-Step Module (DTSM), which adaptively selects optimal diffusion steps for flexibly meeting human perceptual standards, and the Open-World Multi-modality Supervision (OWMS), which integrates guidance from both image and text domains through CLIP to improve semantic consistency and perceptual naturalness. Through these modules, Hero-SR generates high-resolution images that not only preserve intricate details but also reflect human perceptual preferences. Extensive experiments validate that Hero-SR achieves state-of-the-art performance in Real-SR. The code will be publicly available upon paper acceptance.

📄 PDF Abstract BibTeX arXiv:2412.07152

Code (0)

등록된 구현이 없습니다.

Tasks

Super-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…
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…

Similar Papers 제목 키워드 기반

HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

2024-10-07 · Ayano Hiranaka, Shang-Fu Chen, Chieh-Hsin Lai, Dongjun Kim 외

Controllable generation through Stable Diffusion (SD) fine-tuning aims to improve fidelity, safety, and alignment with human guidance. Existing reinforcement learning from human feedback methods usually rely on predefine…

Image Generationreinforcement-learningReinforcement LearningRepresentation Learning

Single Input Multi Output Model of Molecular Communication via Diffusion with Spheroidal Receivers

2024-05-22 · Ibrahim Isik, Mitra Rezaei, Adam Noel

Spheroids are aggregates of cells that can mimic the cellular organization often found in tissues. They are typically formed through the self-assembly of cells in a culture where there is a promotion of interactions and …

OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolution

2025-09-20 · Hanting Li, Huaao Tang, Jianhong Han, Tianxiong Zhou 외 arxiv

Recently, latent diffusion models has demonstrated promising performance in real-world video super-resolution (VSR) task, which can reconstruct high-quality videos from distorted low-resolution input through multiple dif…

Image Super-ResolutionVideo Super-Resolution

An Empirical Study of Sampling Hyperparameters in Diffusion-Based Super-Resolution

2025-12-19 · Yudhistira Arief Wibowo arxiv

Diffusion models have shown strong potential for solving inverse problems such as single-image super-resolution, where a high-resolution image is recovered from a low-resolution observation using a pretrained uncondition…

Image Super-Resolution

TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution

2026-05-04 · Sowmya Vajrala, Akshay Bankar, Manjunath Arveti, Shreyas Pandith 외 arxiv

Diffusion models have recently demonstrated strong performance for image restoration tasks, including super-resolution. However, their large model size and iterative sampling procedures make them computationally expensiv…

Image Restoration