Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts

06/11/2019
by   Zhile Ren, et al.
3

We develop new representations and algorithms for three-dimensional (3D) object detection and spatial layout prediction in cluttered indoor scenes. We first propose a clouds of oriented gradient (COG) descriptor that links the 2D appearance and 3D pose of object categories, and thus accurately models how perspective projection affects perceived image gradients. To better represent the 3D visual styles of large objects and provide contextual cues to improve the detection of small objects, we introduce latent support surfaces. We then propose a "Manhattan voxel" representation which better captures the 3D room layout geometry of common indoor environments. Effective classification rules are learned via a latent structured prediction framework. Contextual relationships among categories and layout are captured via a cascade of classifiers, leading to holistic scene hypotheses that exceed the state-of-the-art on the SUN RGB-D database.

READ FULL TEXT

page 3

page 4

page 5

page 6

page 8

page 9

page 10

page 11

research
12/05/2017

Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene

The goal of this paper is to take a single 2D image of a scene and recov...
research
04/09/2015

Predicting Complete 3D Models of Indoor Scenes

One major goal of vision is to infer physical models of objects, surface...
research
08/07/2018

Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image

We propose a computational framework to jointly parse a single RGB image...
research
02/02/2020

Fast 3D Indoor Scene Synthesis with Discrete and Exact Layout Pattern Extraction

We present a fast framework for indoor scene synthesis, given a room geo...
research
06/18/2015

A Spatial Layout and Scale Invariant Feature Representation for Indoor Scene Classification

Unlike standard object classification, where the image to be classified ...
research
04/19/2021

LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments

We present LaLaLoc to localise in environments without the need for prio...
research
01/09/2017

Information Pursuit: A Bayesian Framework for Sequential Scene Parsing

Despite enormous progress in object detection and classification, the pr...

Please sign up or login with your details

Forgot password? Click here to reset