Poster (Scientific congresses and symposiums)
Dynamic NeRFs for Soccer Scenes
Lewin, Sacha; Vandegar, Maxime; Hoyoux, Thomas et al.
20236th International ACM Workshop on Multimedia Content Analysis in Sports
Peer reviewed
 

Files


Full Text
_mmsp015-lewin.pdf
Publisher postprint (11.45 MB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
3D reconstruction; scene representation; dynamic; neural radiance fields; sports; soccer
Abstract :
[en] The long-standing problem of novel view synthesis has many applications, notably in sports broadcasting. Photorealistic novel view synthesis of soccer actions, in particular, is of enormous interest to the broadcast industry. Yet only a few industrial solutions have been proposed, and even fewer that achieve near-broadcast quality of the synthetic replays. Except for their setup of multiple static cameras around the playfield, the best proprietary systems disclose close to no information about their inner workings. Leveraging multiple static cameras for such a task indeed presents a challenge rarely tackled in the literature, for a lack of public datasets: the reconstruction of a large-scale, mostly static environment, with small, fast-moving elements. Recently, the emergence of neural radiance fields has induced stunning progress in many novel view synthesis applications, leveraging deep learning principles to produce photorealistic results in the most challenging settings. In this work, we investigate the feasibility of basing a solution to the task on dynamic NeRFs, i.e., neural models purposed to reconstruct general dynamic content. We compose synthetic soccer environments and conduct multiple experiments using them, identifying key components that help reconstruct soccer scenes with dynamic NeRFs. We show that, although this approach cannot fully meet the quality requirements for the target application, it suggests promising avenues toward a cost-efficient, automatic solution. We also make our work dataset and code publicly available, with the goal to encourage further efforts from the research community on the task of novel view synthesis for dynamic soccer scenes. For code, data, and video results, please see https://soccernerfs.isach.be.
Research center :
EVS Broadcast Equipment
Disciplines :
Computer science
Author, co-author :
Lewin, Sacha  ;  Université de Liège - ULiège > Département d'aérospatiale et mécanique > Mathématiques générales
Vandegar, Maxime ;  Université de Liège - ULiège > Département d'astrophysique, géophysique et océanographie (AGO) > MAST (Modeling for Aquatic Systems) ; EVS Broadcast Equipment Liège, Belgium
Hoyoux, Thomas ;  Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Exploitation des signaux et images ; EVS Broadcast Equipment Liège, Belgium
Barnich, Olivier ;  Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Techniques du son et de l'image ; EVS Broadcast Equipment Liège, Belgium
Louppe, Gilles  ;  Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Big Data
Language :
English
Title :
Dynamic NeRFs for Soccer Scenes
Publication date :
2023
Number of pages :
9
Event name :
6th International ACM Workshop on Multimedia Content Analysis in Sports
Event organizer :
Association for Computing Machinery
Event place :
Ottawa, Canada
Event date :
29 October 2023
Audience :
International
Peer reviewed :
Peer reviewed
Funders :
EVS Broadcast Equipment [BE]
Available on ORBi :
since 13 October 2023

Statistics


Number of views
47 (26 by ULiège)
Number of downloads
29 (6 by ULiège)

Scopus citations®
 
0
Scopus citations®
without self-citations
0

Bibliography


Similar publications



Contact ORBi