Generative modeling of audible shapes for object perception

TitleGenerative modeling of audible shapes for object perception
Publication TypeConference Paper
Year of Publication2017
AuthorsZhang, Z, Wu, J, Li, Q, Huang, Z, Traer, J, McDermott, JH, Tenenbaum, JB, Freeman, WT
Conference NameThe IEEE International Conference on Computer Vision (ICCV)
Date Published10/2017
Conference LocationVenice, Italy
Abstract

Humans infer rich knowledge of objects from both auditory and visual cues. Building a machine of such competency, however, is very challenging, due to the great difficulty in capturing large-scale, clean data of objects with both their appearance and the sound they make. In this paper, we present a novel, open-source pipeline that generates audio-visual data, purely from 3D object shapes and their physical properties. Through comparison with audio recordings and human behavioral studies, we validate the accuracy of the sounds it generates. Using this generative model, we are able to construct a synthetic audio-visual dataset, namely Sound-20K, for object perception tasks. We demonstrate that auditory and visual information play complementary roles in object perception, and further, that the representation learned on synthetic audio-visual data can transfer to real-world scenarios.

URLhttp://openaccess.thecvf.com/content_iccv_2017/html/Zhang_Generative_Modeling_of_ICCV_2017_paper.html

Research Area: 

CBMM Relationship: 

  • CBMM Related