Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation

05/30/2019
by   Ziheng Zhang, et al.
0

In this work, we demonstrate yet another approach to tackle the amodal segmentation problem. Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our target for amodal segmentation instead of the commonly used masks and heatmaps. The sem-dist map is a kind of level-set representation, of which the different regions of an object are placed into different levels on the map according to their visibility. It is a natural extension of masks and heatmaps, where modal, amodal segmentation, as well as depth order information, are all well-described. Then we also introduce a novel convolutional neural network (CNN) architecture, which we refer to as semantic layering network, to estimate sem-dist maps layer by layer, from the global-level to the instance-level, for all objects in an image. Extensive experiments on the COCOA and D2SA datasets have demonstrated that our framework can predict amodal segmentation, occlusion and depth order with state-of-the-art performance.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 7

page 8

research
04/03/2018

Weakly Supervised Instance Segmentation using Class Peak Response

Weakly supervised instance segmentation with image-level labels, instead...
research
12/09/2016

Boundary-aware Instance Segmentation

We address the problem of instance-level semantic segmentation, which ai...
research
05/29/2022

Perceiving the Invisible: Proposal-Free Amodal Panoptic Segmentation

Amodal panoptic segmentation aims to connect the perception of the world...
research
06/01/2022

PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation

This paper presents a unified framework for depth-aware panoptic segment...
research
03/05/2022

Towards Robust Part-aware Instance Segmentation for Industrial Bin Picking

Industrial bin picking is a challenging task that requires accurate and ...
research
05/12/2015

Monocular Object Instance Segmentation and Depth Ordering with CNNs

In this paper we tackle the problem of instance-level segmentation and d...
research
06/11/2021

Part-aware Panoptic Segmentation

In this work, we introduce the new scene understanding task of Part-awar...

Please sign up or login with your details

Forgot password? Click here to reset