# Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling

Source: [Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling](<https://www.sota2.com/research/paper/68fa629b1e209131ce9fa1f9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:22:26.903Z

Authors: Jonas Uhrig, Marius Cordts, Uwe Franke, Thomas Brox

Published: 2016-04-18T11:24:39.000Z

## Abstract

Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel's direction towards its corresponding instance center. Subsequently, we apply low-level computer vision techniques to generate state-of-the-art instance segmentation on the street scene datasets KITTI and Cityscapes. Our approach outperforms existing works by a large margin and can additionally predict absolute distances of individual instances from a monocular image as well as a pixel-level semantic labeling.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Instance Segmentation on Cityscapes (test)](<https://www.sota2.com/research/sota/instance-segmentation-on-cityscapes-test.md>): Instance Segmentation; Cityscapes (test); AP (Overall): 8.9.

- [Instance Segmentation on Cityscapes (val)](<https://www.sota2.com/research/sota/instance-segmentation-on-cityscapes-val.md>): Instance Segmentation; Cityscapes (val); AP: 9.9.

- [Semantic Segmentation on Cityscapes (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-test.md>): Semantic segmentation; Cityscapes (test); mIoU: 64.3.

- [Panoptic Segmentation on Cityscapes (val)](<https://www.sota2.com/research/sota/panoptic-segmentation-on-cityscapes-val.md>): Panoptic Segmentation; Cityscapes (val); PQ: not recorded.

- [Panoptic Segmentation on Cityscapes (test)](<https://www.sota2.com/research/sota/panoptic-segmentation-on-cityscapes-test.md>): Panoptic Segmentation; Cityscapes (test); PQ: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1604.05096>)

[PDF](<https://arxiv.org/pdf/1604.05096.pdf>)
