# Learning Instance Occlusion for Panoptic Segmentation

arXiv: https://arxiv.org/abs/1906.05896 · HTML: https://mlsanity.com/paper/1906.05896/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2019.

## Built on by (most cited first, 30 of 30)

- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [Open-Vocabulary Universal Image Segmentation with MaskCLIP](https://mlsanity.com/paper/2208.08984/) (2022)
- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [Part-aware Panoptic Segmentation](https://mlsanity.com/paper/2106.06351/) (2021)
- [Exemplar-Based Open-Set Panoptic Segmentation Network](https://mlsanity.com/paper/2105.08336/) (2021)
- [CLUSTSEG: Clustering for Universal Segmentation](https://mlsanity.com/paper/2305.02187/) (2023)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)
- [Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation](https://mlsanity.com/paper/2112.08949/) (2021)
- [DFormer: Diffusion-guided Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2306.03437/) (2023)
- [Panoptic Segmentation: A Review](https://mlsanity.com/paper/2111.10250/) (2021)
- [PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation](https://mlsanity.com/paper/2206.00468/) (2022)
- [RFMask: A Simple Baseline for Human Silhouette Segmentation with Radio Signals](https://mlsanity.com/paper/2201.10175/) (2022)
- [Enhancing Vision-Language Pre-training with Rich Supervisions](https://mlsanity.com/paper/2403.03346/) (2024)
- [Occlusion-Aware Seamless Segmentation](https://mlsanity.com/paper/2407.02182/) (2024)
- [Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning](https://mlsanity.com/paper/2307.14786/) (2023)
- [Occlusion-Aware Instance Segmentation via BiLayer Network Architectures](https://mlsanity.com/paper/2208.04438/) (2022)
- [Non-autoregressive Sequence-to-Sequence Vision-Language Models](https://mlsanity.com/paper/2403.02249/) (2024)
- [Hierarchical Lov'asz Embeddings for Proposal-free Panoptic Segmentation](https://mlsanity.com/paper/2106.04555/) (2021)
- [Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation](https://mlsanity.com/paper/2210.03686/) (2022)
- [Towards Panoptic 3D Parsing for Single Image in the Wild](https://mlsanity.com/paper/2111.03039/) (2021)
- [SE-PSNet: Silhouette-based Enhancement Feature for Panoptic Segmentation Network](https://mlsanity.com/paper/2107.05093/) (2021)
- [CFNet: Learning Correlation Functions for One-Stage Panoptic Segmentation](https://mlsanity.com/paper/2201.04796/) (2022)
- [SUNet: Scale-aware Unified Network for Panoptic Segmentation](https://mlsanity.com/paper/2209.02877/) (2022)
- [Unified Perception: Efficient Depth-Aware Video Panoptic Segmentation with Minimal Annotation Costs](https://mlsanity.com/paper/2303.01991/) (2023)
- [Improving Panoptic Segmentation for Nighttime or Low-Illumination Urban Driving Scenes](https://mlsanity.com/paper/2306.13725/) (2023)
- [Hybrid Deep Learning-Based for Enhanced Occlusion Segmentation in PICU Patient Monitoring](https://mlsanity.com/paper/2407.13341/) (2024)
- [Occlusion-Ordered Semantic Instance Segmentation](https://mlsanity.com/paper/2504.14054/) (2025)
- [PICS: Pairwise Image Compositing with Spatial Interactions](https://mlsanity.com/paper/2603.06873/) (2026)

## Abstract (arXiv)

Panoptic segmentation requires segments of both "things" (countable object instances) and "stuff" (uncountable and amorphous regions) within a single output. A common approach involves the fusion of instance segmentation (for "things") and semantic segmentation (for "stuff") into a non-overlapping placement of segments, and resolves overlaps. However, instance ordering with detection confidence do not correlate well with natural occlusion relationship. To resolve this issue, we propose a branch that is tasked with modeling how two instance masks should overlap one another as a binary relation. Our method, named OCFusion, is lightweight but particularly effective in the instance fusion process. OCFusion is trained with the ground truth relation derived automatically from the existing dataset annotations. We obtain state-of-the-art results on COCO and show competitive results on the Cityscapes panoptic segmentation benchmark.