mlsanityData to 7 Oct 2026

Inharmonious Region Localization via Recurrent Self-Reasoning

arXiv 2210.02036 ↗First posted 5 Oct 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Synthetic images created by image editing operations are prevalent, but the color or illumination inconsistency between the manipulated region and background may make it unrealistic. Thus, it is important yet challenging to localize the inharmonious region to improve the quality of synthetic image. Inspired by the classic clustering algorithm, we aim to group pixels into two clusters: inharmonious cluster and background cluster by inserting a novel Recurrent Self-Reasoning (RSR) module into the bottleneck of UNet structure. The mask output from RSR module is provided for the decoder as attention guidance. Finally, we adaptively combine the masks from RSR and the decoder to form our final mask. Experimental results on the image harmonization dataset demonstrate that our method achieves competitive performance both quantitatively and qualitatively.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 51 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

29 of 51 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  6. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  7. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  8. 2017On human motion prediction using recurrent neural networkscited by 336
  9. 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
  10. 2019F3Net: Fusion, Feedback and Focus for Salient Object Detectioncited by 176
  11. 2015Delving Deeper into Convolutional Networks for Learning Video Representationscited by 146
  12. 2019DoveNet: Deep Image Harmonization via Domain Verificationcited by 134
17 more
  1. 2020Suppress and Balance: A Simple Gated Network for Salient Object Detectioncited by 126
  2. 2017Deep Image Harmonizationcited by 120
  3. 2020SPAN: Spatial Pyramid Attention Network forImage Manipulation Localizationcited by 92
  4. 2019Improving the Harmony of the Composite Image by Spatial-Separated Attention Modulecited by 73
  5. 2021Region-aware Adaptive Instance Normalization for Image Harmonizationcited by 71
  6. 2017Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)cited by 64
  7. 2019Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeriescited by 59
  8. 2021CDFI: Compression-Driven Network Design for Frame Interpolationcited by 55
  9. 2021High-Resolution Image Harmonization via Collaborative Dual Transformationscited by 55
  10. 2020Foreground-aware Semantic Representations for Image Harmonizationcited by 53
  11. 2020BargainNet: Background-Guided Domain Translation for Image Harmonizationcited by 52
  12. 2018Generate, Segment and Refine: Towards Generic Manipulation Segmentationcited by 33
  13. 2019Constrained R-CNN: A general image manipulation detection modelcited by 29
  14. 2022SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonizationcited by 24
  15. 2021Deep Image Harmonization by Bridging the Reality Gapcited by 11
  16. 2021Deep Image-based Illumination Harmonizationcited by 11
  17. 2021Inharmonious Region Localizationcited by 5

Built on by

Not cited yet.