mlsanityData to 7 Oct 2026

Occlusion-Aware Seamless Segmentation

arXiv 2407.02182 ↗First posted 2 Jul 2024cs.CV cs.RO eess.IVcited by 6

Not on the map. Why?

Abstract (arXiv)

Panoramic images can broaden the Field of View (FoV), occlusion-aware prediction can deepen the understanding of the scene, and domain adaptation can transfer across viewing domains. In this work, we introduce a novel task, Occlusion-Aware Seamless Segmentation (OASS), which simultaneously tackles all these three challenges. For benchmarking OASS, we establish a new human-annotated dataset for Blending Panoramic Amodal Seamless Segmentation, i.e., BlendPASS. Besides, we propose the first solution UnmaskFormer, aiming at unmasking the narrow FoV, occlusions, and domain gaps all at once. Specifically, UnmaskFormer includes the crucial designs of Unmasking Attention (UA) and Amodal-oriented Mix (AoMix). Our method achieves state-of-the-art performance on the BlendPASS dataset, reaching a remarkable mAPQ of 26.58% and mIoU of 43.66%. On public panoramic semantic segmentation datasets, i.e., SynPASS and DensePASS, our method outperforms previous methods and obtains 45.34% and 48.08% in mIoU, respectively. The fresh BlendPASS dataset and our source code are available at https://github.com/yihong-97/OASS.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 76 of its 98 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

76 of 98 references.

References · 76

  1. 2023Segment Anythingcited by 8,158
  2. 2017Mask R-CNNcited by 7,259
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  5. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  6. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  7. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  8. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  9. 2018Panoptic Segmentationcited by 796
  10. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  11. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  12. 2019Confidence Regularized Self-Trainingcited by 418
38 more
  1. 2019Panoptic-DeepLabcited by 362
  2. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  3. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  4. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  5. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  6. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 176
  7. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  8. 2014Simultaneous Detection and Segmentationcited by 158
  9. 2022Understanding The Robustness in Vision Transformerscited by 144
  10. 2019WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingcited by 142
  11. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  12. 2019Fast-SCNN: Fast Semantic Segmentation Networkcited by 124
  13. 2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
  14. 2015Semantic Amodal Segmentationcited by 102
  15. 2022PanoFormer: Panorama Transformer for Indoor 360 Depth Estimationcited by 94
  16. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  17. 2022Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentationcited by 71
  18. 2016Amodal Instance Segmentationcited by 63
  19. 2018Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentationcited by 62
  20. 2022Waymo Open Dataset: Panoramic Video Panoptic Segmentationcited by 57
  21. 2021Capturing Omni-Range Context for Omnidirectional Segmentationcited by 49
  22. 2022Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentationcited by 46
  23. 2023Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentationcited by 46
  24. 2021Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modelingcited by 43
  25. 2020Amodal Segmentation Based on Visible Region Segmentation and Shape Priorcited by 42
  26. 2022Review on Panoramic Imaging and Its Applications in Scene Understandingcited by 42
  27. 2014Convolutional Feature Masking for Joint Object and Stuff Segmentationcited by 41
  28. 2022Deep Learning for Omnidirectional Vision: A Survey and New Perspectivescited by 38
  29. 2022Amodal Panoptic Segmentationcited by 37
  30. 2023Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentationcited by 37
  31. 2021DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context Exchangecited by 35
  32. 2022AISFormer: Amodal Instance Segmentation with Transformercited by 35
  33. 2021Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptationcited by 34
  34. 2021DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimizationcited by 33
  35. 2019Learning Instance Occlusion for Panoptic Segmentationcited by 30
  36. 2019DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensingcited by 30
  37. 2020Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Modelcited by 29
  38. 2023Coarse-to-Fine Amodal Segmentation with Shape Priorcited by 29

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025Omnidirectional Multi-Object Trackingcited by 12
  2. 2026More than the Sum: Panorama-Language Models for Adverse Omni-Scenescited by 4
  3. 2025Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentationcited by 3
  4. 2025OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedbackcited by 2
  5. 2025Panoramic Out-of-Distribution Segmentationcited by 0
  6. 2026Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentationcited by 0