ASIST: Automatic Semantically Invariant Scene Transformation

12/04/2015
by   Or Litany, et al.
0

We present ASIST, a technique for transforming point clouds by replacing objects with their semantically equivalent counterparts. Transformations of this kind have applications in virtual reality, repair of fused scans, and robotics. ASIST is based on a unified formulation of semantic labeling and object replacement; both result from minimizing a single objective. We present numerical tools for the efficient solution of this optimization problem. The method is experimentally assessed on new datasets of both synthetic and real point clouds, and is additionally compared to two recent works on object replacement on data from the corresponding papers.

READ FULL TEXT

page 11

page 12

page 14

page 15

page 16

research
01/21/2013

Toward the Automatic Generation of a Semantic VRML Model from Unorganized 3D Point Clouds

This paper presents our experience regarding the creation of 3D semantic...
research
06/04/2018

Learning Scene Flow in 3D Point Clouds

Many applications in robotics and human-computer interaction can benefit...
research
04/23/2018

Constructing Locally Dense Point Clouds Using OpenSfM and ORB-SLAM2

This paper aims at finding a method to register two different point clou...
research
04/11/2018

Visualization and Labeling of Point Clouds in Virtual Reality

We present a Virtual Reality (VR) application for labeling and handling ...
research
11/13/2018

Hallucinating Point Cloud into 3D Sculptural Object

Our team of artists and machine learning researchers designed a creative...
research
05/10/2018

Multi-View Semantic Labeling of 3D Point Clouds for Automated Plant Phenotyping

Semantic labeling of 3D point clouds is important for the derivation of ...

Please sign up or login with your details

Forgot password? Click here to reset