From Meshes to Gaussians: Evolving 3D Scene Rendering for Broadcast Applications

Metadata

Publisher: SMPTE — Pasadena, CA
Doc Type: Conference Paper
Content Type: Original Research
Volume: 00, pp. 2–17
Abstract: This paper presents a technical overview of the evolving landscape of 3D scene representation and rendering, with a focus on photorealistic content generation in broadcast. While traditional polygon meshes offer highly efficient rendering, attaining convincing photorealism with them requires extensive manual modeling or complex capture setups. Breakthrough computer vision approaches have, however, recently enabled high photorealistic fidelity by jointly learning scene geometry, lighting, and appearance directly from images. A Neural Radiance Field (NeRF) encodes a scene implicitly as a continuous volumetric function, whereas 3D Gaussian Splatting (3DGS) provides an explicit representation through a set of Gaussian primitives. We introduce the fundamental principles of polygon meshes, NeRF and 3DGS, then examine the applicability of NeRF and 3DGS in the broadcast domain, emphasizing both the progress realized by the research community and the challenges that remain for large-scale adoption in time-critical live production environments. Finally, we illustrate the potential of 3DGS through a preliminary case study in the demanding context of sports broadcasting.
Publication Date: 2025-10-13
ISBN: [object Object]
Author(s): Floriane Magera
Cedric Hons
Quentin Massoz
Thomas Hoyoux
Antoine Houet
Olivier Barnich
Keyword(s): 3d Rendering, 3d Scene Reconstruction, Meshes, Neural Radiance Fields, Gaussian Splatting, Virtual Sets, Virtual Cameras, Free Viewpoint, Immersive Replays, Live Production, Broadcast Applications
Copyright: © 2025 SMPTE

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/978-1-61482-966-9-20.json

Reference this Doc

Plain text (ISO 690 compliant)

Preview:

Floriane Magera, Cedric Hons, Quentin Massoz, Thomas Hoyoux, Antoine Houet, and Olivier Barnich; From Meshes to Gaussians: Evolving 3D Scene Rendering for Broadcast Applications, MTS 2025, Article 20 (pp. 2 to 17); SMPTE, 2025, ISBN: [object Object]

Snippet:

Floriane Magera, Cedric Hons, Quentin Massoz, Thomas Hoyoux, Antoine Houet, and Olivier Barnich; From Meshes to Gaussians: Evolving 3D Scene Rendering for Broadcast Applications, MTS 2025, Article 20 (pp. 2 to 17); SMPTE, 2025, ISBN: [object Object]

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">Floriane Magera, Cedric Hons, Quentin Massoz, Thomas Hoyoux, Antoine Houet, and Olivier Barnich; <cite>From Meshes to Gaussians: Evolving 3D Scene Rendering for Broadcast Applications</cite>, MTS 2025, Article 20 (pp. 2 to 17); SMPTE, 2025, ISBN: [object Object]</span>

SMPTE's HTML Pub

Preview:

Snippet:

<li>
Floriane Magera, Cedric Hons, Quentin Massoz, Thomas Hoyoux, Antoine Houet, and Olivier Barnich; <cite id="bib-978-1-61482-966-9-20">From Meshes to Gaussians: Evolving 3D Scene Rendering for Broadcast Applications</cite>, MTS 2025, Article 20 (pp. 2 to 17); SMPTE, 2025, ISBN: [object Object]
</li>