mlsanityData to 7 Oct 2026

Multi-Projection Fusion and Refinement Network for Salient Object Detection in 360deg Omnidirectional Image

arXiv 2212.12378 ↗First posted 23 Dec 2022cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Salient object detection (SOD) aims to determine the most visually attractive objects in an image. With the development of virtual reality technology, 360deg omnidirectional image has been widely used, but the SOD task in 360deg omnidirectional image is seldom studied due to its severe distortions and complex scenes. In this paper, we propose a Multi-Projection Fusion and Refinement Network (MPFR-Net) to detect the salient objects in 360deg omnidirectional image. Different from the existing methods, the equirectangular projection image and four corresponding cube-unfolding images are embedded into the network simultaneously as inputs, where the cube-unfolding images not only provide supplementary information for equirectangular projection image, but also ensure the object integrity of the cube-map projection. In order to make full use of these two projection modes, a Dynamic Weighting Fusion (DWF) module is designed to adaptively integrate the features of different projections in a complementary and dynamic manner from the perspective of inter and intra features. Furthermore, in order to fully explore the way of interaction between encoder and decoder features, a Filtration and Refinement (FR) module is designed to suppress the redundant information between the feature itself and the feature. Experimental results on two omnidirectional datasets demonstrate that the proposed approach outperforms the state-of-the-art methods both qualitatively and quantitatively.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 44 of its 101 references that are in the map. First posted on arXiv 23 Dec 2022.

Builds on

44 of 101 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  5. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  6. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  7. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 410
  8. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  9. 2019Cascaded Partial Decoder for Fast and Accurate Salient Object Detectioncited by 216
  10. 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
  11. 2019A Simple Pooling-Based Design for Real-Time Salient Object Detectioncited by 211
  12. 2016Deeply supervised salient object detection with short connectionscited by 196
32 more
  1. 2019F3Net: Fusion, Feedback and Focus for Salient Object Detectioncited by 176
  2. 2019Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarkscited by 133
  3. 2020Global Context-Aware Progressive Aggregation Network for Salient Object Detectioncited by 109
  4. 2019Towards High-Resolution Salient Object Detectioncited by 92
  5. 2020Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Imagescited by 61
  6. 2021Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baselinecited by 61
  7. 2018Review of Visual Saliency Detection with Comprehensive Informationcited by 60
  8. 2019Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Imagescited by 51
  9. 2017Video Salient Object Detection via Fully Convolutional Networkscited by 46
  10. 2020DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detectioncited by 45
  11. 2018SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Imagescited by 40
  12. 2022CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detectioncited by 38
  13. 2022Does Thermal Really Always Matter for RGB-T Salient Object Detection?cited by 37
  14. 2021Disentangled High Quality Salient Object Detectioncited by 35
  15. 2021Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detectioncited by 34
  16. 2021RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Imagescited by 34
  17. 2015Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Networkcited by 31
  18. 2020CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detectioncited by 30
  19. 2017SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumescited by 29
  20. 2022Global-and-Local Collaborative Learning for Co-Salient Object Detectioncited by 24
  21. 2017SalNet360: Saliency Maps for omni-directional images with CNNcited by 21
  22. 2022A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labelscited by 20
  23. 2017Co-saliency Detection for RGBD Images Based on Multi-constraint Feature Matching and Cross Label Propagationcited by 18
  24. 2020Exploring Rich and Efficient Spatial Temporal Interactions for Real Time Video Salient Object Detectioncited by 18
  25. 2021Few-Cost Salient Object Detection with Adversarial-Paced Learningcited by 17
  26. 2018HSCS: Hierarchical Sparsity Based Co-saliency Detection for RGBD Imagescited by 15
  27. 2019Distortion-adaptive Salient Object Detection in 360^circ Omnidirectional Imagescited by 15
  28. 2017An Iterative Co-Saliency Framework for RGBD Imagescited by 14
  29. 2022PSNet: Parallel Symmetric Network for Video Salient Object Detectioncited by 12
  30. 2018Contrast-Oriented Deep Neural Networks for Salient Object Detectioncited by 5
  31. 2018Movie Editing and Cognitive Event Segmentation in Virtual Reality Videocited by 5
  32. 2015DISC: Deep Image Saliency Computing via Progressive Representation Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 3; 2025: 2; 2026: 2.

13 papers.

Sort:

  1. 2023PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminatorscited by 49
  2. 2023Frequency Perception Network for Camouflaged Object Detectioncited by 37
  3. 2023Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detectioncited by 25
  4. 2024Query-guided Prototype Evolution Network for Few-Shot Segmentationcited by 12
  5. 2023SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detectioncited by 11
  6. 2024SGFormer: Spherical Geometry Transformer for 360 Depth Estimationcited by 9
  7. 2023Distortion-aware Transformer in 360deg Salient Object Detectioncited by 5
  8. 2023WinDB: HMD-free and Distortion-free Panoptic Video Fixation Learningcited by 1
  9. 2024LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field Camerascited by 1
  10. 2025Sphere-GAN: a GAN-based Approach for Saliency Estimation in 360deg Videoscited by 1
  11. 2026TDFNet: Tri-projection Deformable Fusion Network for Panoramic Salient Object Detectioncited by 1
  12. 2025Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approachcited by 0
1 more
  1. 2026SphereSOD: Geometry-Structure Coupled Learning for 360 Salient Object Detectioncited by 0