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

2026-07-05

AI Summary

This work addresses the significant quality degradation often observed when users reselect a video frame as the cover image of a Live Photo, typically due to low resolution, color distortion, and limited dynamic range. To tackle this issue, we introduce the first Live Photo Re-selection and Enhancement (LPRE) task, which jointly optimizes spatial detail and color fidelity of the target frame by leveraging a high-quality reference cover image for structural and chromatic guidance along with temporal information from neighboring frames. We contribute Live2K, a dataset comprising 2,042 real-world Live Photos, and propose the first end-to-end unified benchmark model integrating multi-frame feature fusion, guided color enhancement, and single-stage super-resolution. Experiments demonstrate that our approach substantially outperforms existing methods in enhancing resolution, color accuracy, and overall visual quality, establishing the first public benchmark for this emerging task.

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 pipelines: the photo stream undergoes full computational photography processing, while the video stream is constrained by real-time efficiency and heavy compression. This intrinsic separation produces a substantial quality gap in resolution, color fidelity, and dynamic range between the cover photo and video frames. When users reselect an alternative frame from the video to replace an imperfect cover, the chosen frame often suffers from severe degradation, making direct replacement visually unsatisfactory. Restoring such frames requires simultaneous enhancement of spatial detail and color appearance, a task considerably more challenging than ordinary super-resolution or color enhancement. To address this, we define the Live Photo Cover Frame Reselection and Enhancement (LPRE) task, which leverages the intrinsic cues available within each Live Photo: the high-quality cover image as a structural and color reference, the user-reselected low-quality frame as the reconstruction target and several adjacent video frames providing temporal cues. Building upon this formulation, we construct Live2K, a real-world dataset of 2,042 Live Photos, and develop a unified one-stage baseline that integrates multi-frame fusion, guided color enhancement and super-resolution, establishing the first benchmark for Live Photo enhancement research.

Problem

• Live Photos
• cover frame reselection
• video enhancement
• quality gap
• computational photography

Innovation

• Live Photo enhancement
• cover frame reselection
• guided color enhancement
• multi-frame fusion
• Live2K dataset