mlsanityData to 7 Oct 2026

HALO: Human-Aligned End-to-end Image Retargeting with Layered Transformations

arXiv 2504.03026 ↗First posted 3 Apr 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Image retargeting aims to change the aspect-ratio of an image while maintaining its content and structure with less visual artifacts. Existing methods still generate many artifacts or fail to maintain original content or structure. To address this, we introduce HALO, an end-to-end trainable solution for image retargeting. Since humans are more sensitive to distortions in salient areas than non-salient areas of an image, HALO decomposes the input image into salient/non-salient layers and applies different wrapping fields to different layers. To further minimize the structure distortion in the output images, we propose perceptual structure similarity loss which measures the structure similarity between input and output images and aligns with human perception. Both quantitative results and a user study on the RetargetMe dataset show that HALO achieves SOTA. Especially, our method achieves an 18.4% higher user preference compared to the baselines on average.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 46 of its 67 references that are in the map. First posted on arXiv 3 Apr 2025.

Builds on

46 of 67 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2023Segment Anythingcited by 8,158
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  8. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  9. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  10. 2015Spatial Transformer Networkscited by 1,423
  11. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  12. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
34 more
  1. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  2. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  3. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  4. 2023DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Modelscited by 193
  5. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 165
  6. 2022SINE: SINgle Image Editing with Text-to-Image Diffusion Modelscited by 159
  7. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 158
  8. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  9. 2021Layered Neural Atlases for Consistent Video Editingcited by 137
  10. 2018"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priorscited by 114
  11. 2020Improved Techniques for Training Single-Image GANscited by 77
  12. 2024ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertioncited by 71
  13. 2022Pyramid Grafting Network for One-Stage High Resolution Saliency Detectioncited by 63
  14. 2023VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretrainingcited by 63
  15. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  16. 2022SinDDM: A Single Image Denoising Diffusion Modelcited by 60
  17. 2022SinFusion: Training Diffusion Models on a Single Image or Videocited by 58
  18. 2023Shape-aware Text-driven Layered Video Editingcited by 54
  19. 2020Layered Neural Rendering for Retiming People in Videocited by 51
  20. 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
  21. 2021Omnimatte: Associating Objects and Their Effects in Videocited by 50
  22. 2022SinDiffusion: Learning a Diffusion Model from a Single Natural Imagecited by 42
  23. 2024Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videoscited by 38
  24. 2023Neural Congealing: Aligning Images to a Joint Semantic Atlascited by 30
  25. 2024Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detectioncited by 29
  26. 2022Generating natural images with direct Patch Distributions Matchingcited by 26
  27. 2020Learning to See Through Obstructions with Layered Decompositioncited by 20
  28. 2017Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargetingcited by 14
  29. 2022PetsGAN: Rethinking Priors for Single Image Generationcited by 14
  30. 2019Cycle-IR: Deep Cyclic Image Retargetingcited by 13
  31. 2019DCIL: Deep Contextual Internal Learning for Image Restoration and Image Retargetingcited by 10
  32. 2020Self-Play Reinforcement Learning for Fast Image Retargetingcited by 7
  33. 2023Retargeting Visual Data with Deformation Fieldscited by 2
  34. 2024Prune and Repaint: Content-Aware Image Retargeting for any Ratiocited by 1

Built on by

Not cited yet.