Sang-hyo Park — accepted AI-conference papers

2026

FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution

Aro Kim, Myeongjin Jang, Chaewon Moon, Youngjin Shin, Jinwoo Jeong, Sang-hyo Park

CVPR 2026

Diffusion-based approaches have recently driven remarkable progress in real-world image super-resolution (SR). However, existing methods still struggle to simultaneously preserve fine details and ensure high-fidelity reconstruction, often resulting in suboptimal visual quality. In this paper, we pro

Cited by 0 Source ↗code ↗Scholar ↗

2025

Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions

Chan Hur, Jeong-hun Hong, Dong-hun Lee, Dabin Kang, Semin Myeong, Sang-hyo Park +1

CVPR 2025poster

In recent text-video retrieval, the use of additional captions from vision-language models has shown promising effects on the performance. However, existing models using additional captions often have struggled to capture the rich semantics, including temporal changes, inherent in the video. In addi…

Cited by 1 Source ↗PDF ↗Scholar ↗