mlsanityData to 7 Oct 2026

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

arXiv 2607.04151 ↗First posted 5 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 49 references that are in the map. First posted on arXiv 5 Jul 2026.

Builds on

37 of 49 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  5. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  6. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  7. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  8. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  9. 2022Simple Baselines for Image Restorationcited by 701
  10. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
  11. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  12. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
25 more
  1. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  2. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 346
  3. 2020BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyondcited by 303
  4. 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
  5. 2017Deep Photo Style Transfercited by 168
  6. 2020Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-timecited by 163
  7. 2019Image Super-Resolution by Neural Texture Transfercited by 119
  8. 2019Zoom To Learn, Learn To Zoomcited by 114
  9. 2021Deep Burst Super-Resolutioncited by 83
  10. 2021MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolutioncited by 79
  11. 2022AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancementcited by 70
  12. 2021Robust Reference-based Super-Resolution via C2-Matchingcited by 68
  13. 2021Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tablescited by 65
  14. 2021Burst Image Restoration and Enhancementcited by 64
  15. 2024Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionarycited by 63
  16. 2022Reference-based Image Super-Resolution with Deformable Attention Transformercited by 50
  17. 2023Neural Preset for Color Style Transfercited by 36
  18. 2023Burstormer: Burst Image Restoration and Enhancement Transformercited by 32
  19. 2024Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attentioncited by 29
  20. 2024QMambaBSR: Burst Image Super-Resolution with Query State Space Modelcited by 27
  21. 2025Progressive Focused Transformer for Single Image Super-Resolutioncited by 25
  22. 2022Reference-based Video Super-Resolution Using Multi-Camera Video Tripletscited by 19
  23. 2023LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolutioncited by 12
  24. 2024BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flowcited by 7
  25. 2025Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancementcited by 2

Built on by

Not cited yet.