Bicameral Structuring and Synthetic Imagery for Jointly Predicting Instance Boundaries and Nearby Occlusions from a Single Image

by   Matthieu Grard, et al.

Oriented boundary detection is a challenging task aimed at both delineating category-agnostic object instances and inferring their spatial layout from a single RGB image. State-of-the-art deep convolutional networks for this task rely on two independent streams that predict boundaries and occlusions respectively, although both require similar local and global cues, and occlusions cause boundaries. We therefore propose a fully convolutional bicameral structuring, composed of two cascaded decoders sharing one deep encoder, linked altogether by skip connections to combine local and global features, for jointly predicting instance boundaries and their unoccluded side. Furthermore, state-of-the-art datasets contain real images with few instances and occlusions mostly due to objects occluding the background, thereby missing meaningful occlusions between instances. For evaluating the missing scenario of dense piles of objects as well, we introduce synthetic data (Mikado), which extensibly contains more instances and inter-instance occlusions per image than the PASCAL Instance Occlusion Dataset (PIOD), the COCO Amodal dataset (COCOA), and the Densely Segmented Supermarket Amodal dataset (D2SA). We show that the proposed network design outperforms the two-stream baseline and alternative archiectures for oriented boundary detection on both PIOD and Mikado, and the amodal segmentation approach on COCOA as well. Our experiments on D2SA also show that Mikado is plausible in the sense that it enables the learning of performance-enhancing representations transferable to real data, while drastically reducing the need of hand-made annotations for finetuning.


page 2

page 3

page 7

page 8

page 15

page 17

page 19

page 22


CoReNet: Coherent 3D scene reconstruction from a single RGB image

Advances in deep learning techniques have allowed recent work to reconst...

MVTec D2S: Densely Segmented Supermarket Dataset

We introduce the Densely Segmented Supermarket (D2S) dataset, a novel be...

Convolutional Oriented Boundaries

We present Convolutional Oriented Boundaries (COB), which produces multi...

Detecting Semantic Parts on Partially Occluded Objects

In this paper, we address the task of detecting semantic parts on partia...

A Pyramid CNN for Dense-Leaves Segmentation

Automatic detection and segmentation of overlapping leaves in dense foli...

Learning to predict crisp boundaries

Recent methods for boundary or edge detection built on Deep Convolutiona...

Unsupervised Layered Image Decomposition into Object Prototypes

We present an unsupervised learning framework for decomposing images int...