Segmentation and Recovery of Superquadric Models using Convolutional Neural Networks

01/28/2020
by   Jaka Šircelj, et al.
51

In this paper we address the problem of representing 3D visual data with parameterized volumetric shape primitives. Specifically, we present a (two-stage) approach built around convolutional neural networks (CNNs) capable of segmenting complex depth scenes into the simpler geometric structures that can be represented with superquadric models. In the first stage, our approach uses a Mask RCNN model to identify superquadric-like structures in depth scenes and then fits superquadric models to the segmented structures using a specially designed CNN regressor. Using our approach we are able to describe complex structures with a small number of interpretable parameters. We evaluated the proposed approach on synthetic as well as real-world depth data and show that our solution does not only result in competitive performance in comparison to the state-of-the-art, but is able to decompose scenes into a number of superquadric models at a fraction of the time required by competing approaches. We make all data and models used in the paper available from https://lmi.fe.uni-lj.si/en/research/resources/sq-seg.

READ FULL TEXT

page 1

page 3

page 5

page 7

research
04/13/2019

Recovery of Superquadrics from Range Images using Deep Learning: A Preliminary Study

It has been a longstanding goal in computer vision to describe the 3D ph...
research
02/17/2015

SA-CNN: Dynamic Scene Classification using Convolutional Neural Networks

The task of classifying videos of natural dynamic scenes into appropriat...
research
05/19/2020

Focus on defocus: bridging the synthetic to real domain gap for depth estimation

Data-driven depth estimation methods struggle with the generalization ou...
research
05/03/2019

MeshDepth: Disconnected Mesh-based Deep Depth Prediction

We propose a novel method for mesh-based single-view depth estimation us...
research
05/11/2023

Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation

Shape learning, or the ability to leverage shape information, could be a...
research
05/05/2021

Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images

Humans perceive and construct the surrounding world as an arrangement of...
research
09/18/2019

Probabilistic Atlases to Enforce Topological Constraints

Probabilistic atlases (PAs) have long been used in standard segmentation...

Please sign up or login with your details

Forgot password? Click here to reset