PulseAugur
EN
LIVE 14:02:51

New LPRE task and Live2K dataset tackle Live Photo quality gap

Researchers have introduced a new task called Live Photo Cover Frame Reselection and Enhancement (LPRE) to address the quality disparity between the main photo and video frames in Live Photos. This task aims to improve the visual quality of reselected frames by using the original high-quality cover image as a reference for structure and color, and adjacent video frames for temporal cues. To support this research, a new dataset named Live2K, containing 2,042 Live Photos, has been created, along with a baseline model that integrates multi-frame fusion, guided color enhancement, and super-resolution. AI

IMPACT Introduces a new benchmark and dataset for improving the visual quality of Live Photos, potentially enhancing user experience with dynamic photography.

RANK_REASON The cluster contains a research paper detailing a new task, dataset, and baseline model for image enhancement. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New LPRE task and Live2K dataset tackle Live Photo quality gap

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Junyu Lou, Kai Chen, Weiyi You, Hui Zeng, Lei Zhang, Shuhang Gu ·

    Perceiving Better Moments: Cover Frame Reselection and Enhancement for Live Photos with the Live2K Dataset

    arXiv:2607.04151v1 Announce Type: new Abstract: Modern smartphones capture Live Photos, short video bursts surrounding a still image, offering a dynamic and engaging photographic experience. However, the cover photo and video components are generated by two distinct imaging pipel…