# Monocular Object Instance Segmentation and Depth Ordering with CNNs

arXiv: https://arxiv.org/abs/1505.03159 · HTML: https://mlsanity.com/paper/1505.03159/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2015.

## Built on by (most cited first, 14 of 14)

- [Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition](https://mlsanity.com/paper/2104.05367/) (2021)
- [MonoGRNet: A General Framework for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.08797/) (2021)
- [Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey](https://mlsanity.com/paper/2406.19675/) (2024)
- [Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review](https://mlsanity.com/paper/2203.10939/) (2022)
- [SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation](https://mlsanity.com/paper/2203.13312/) (2022)
- [VideoClick: Video Object Segmentation with a Single Click](https://mlsanity.com/paper/2101.06545/) (2021)
- [2.5D Visual Relationship Detection](https://mlsanity.com/paper/2104.12727/) (2021)
- [MT-ORL: Multi-Task Occlusion Relationship Learning](https://mlsanity.com/paper/2108.05722/) (2021)
- [Image Vectorization with Depth: convexified shape layers with depth ordering](https://mlsanity.com/paper/2409.06648/) (2024)
- [GPT-4 for Occlusion Order Recovery](https://mlsanity.com/paper/2509.22383/) (2025)
- [Holistic Order Prediction in Natural Scenes](https://mlsanity.com/paper/2510.01704/) (2025)
- [Illustrator's Depth: Monocular Layer Index Prediction for Image Decomposition](https://mlsanity.com/paper/2511.17454/) (2025)
- [MSFNet:Multi-scale features network for monocular depth estimation](https://mlsanity.com/paper/2107.06445/) (2021)
- [Occlusion-Ordered Semantic Instance Segmentation](https://mlsanity.com/paper/2504.14054/) (2025)

## Abstract (arXiv)

In this paper we tackle the problem of instance-level segmentation and depth ordering from a single monocular image. Towards this goal, we take advantage of convolutional neural nets and train them to directly predict instance-level segmentations where the instance ID encodes the depth ordering within image patches. To provide a coherent single explanation of an image we develop a Markov random field which takes as input the predictions of convolutional neural nets applied at overlapping patches of different resolutions, as well as the output of a connected component algorithm. It aims to predict accurate instance-level segmentation and depth ordering. We demonstrate the effectiveness of our approach on the challenging KITTI benchmark and show good performance on both tasks.