TL;DR
This paper explores the use of dynamic NeRFs for synthesizing novel views of soccer scenes, aiming to improve sports broadcasting visuals through a cost-effective, automated approach, despite current quality limitations.
Contribution
It introduces a synthetic soccer dataset and evaluates dynamic NeRFs for large-scale, fast-moving sports scenes, highlighting key components and challenges.
Findings
Dynamic NeRFs show promise for soccer scene reconstruction.
Current methods do not yet meet broadcast quality standards.
The work provides a new dataset and code for further research.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
