Paper Info
Title
Seeing Beyond Appearance - Mapping Real Images Into Geometrical Domains For Unsupervised Cad-Based Recognition
Abstract
While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their training. Therefore, it has become common practice to use available synthetic samples along domain adaptation schemes to prepare algorithms for the target domain. Tackling this problem from a different angle, we introduce a pipeline to map unseen target samples into the synthetic domain used to train task-specific methods. Denoising the data and retaining only the features these recognition algorithms are familiar with, our solution greatly improves their performance. As this mapping is easier to learn than the opposite one (i.e., to generate realistic features to augment the source samples), we demonstrate how our whole solution can be trained purely on augmented synthetic data and still performs better than methods trained with domain-relevant information (e.g., real images or realistic textures for the 3D models). Applying our approach to object recognition from texture-less CAD data, we present a custom generative network which fully utilizes the purely geometrical information to learn robust features and to achieve a more refined mapping for unseen color images.
Year
DOI
Venue
2019
10.1109/IROS40897.2019.8967829
2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
Field
DocType
Volume
Noise reduction,CAD,Computer vision,Computer science,Convolutional neural network,Synthetic data,Artificial intelligence,Generative grammar,Recognition algorithm,Real image,Cognitive neuroscience of visual object recognition
Conference
abs/1810.04158
ISSN
Citations 
PageRank 
2153-0858
0
0.34
References 
Authors
23
6
Name
Order
Citations
PageRank
Benjamin Planche162.46
Sergey Zakharov2113.27
Ziyan Wu323121.99
Andreas Hutter429729.47
Harald Kosch5775116.64
Slobodan Ilic6130767.56