{rfName}
IR

Indexed in

License and Use

Icono OpenAccess

Citations

2

Altmetrics

Analysis of institutional authors

Rivas-Manzaneque, FernandoAuthor

Share

December 24, 2024
Publications
>
Proceedings Paper
Sí

IReNe: Instant Recoloring of Neural Radiance Fields

Publicated to: Proceedings Of The Ieee Computer Society Conference On Computer Vision And Pattern Recognition. 5937-5946 - 2024-01-01 (), DOI: 10.1109/CVPR52733.2024.00567

Authors:

Mazzucchelli, A; Garcia-Garcia, A; Garces, E; Rivas-Manzaneque, F; Moreno-Noguer, F; Penate-Sanchez, A
[+]

Affiliations

Arquimea Res Ctr, San Cristobal La Laguna, Spain - Author
SEDDI, Madrid, Spain - Author
Univ Las Palmas Gran Canaria, IUSIANI, Las Palmas Gran Canaria, Spain - Author
Univ Politecn Cataluna, Barcelona, Spain - Author
Univ Politecn Madrid, Madrid, Spain - Author
Univ Rey Juan Carlos, Mostoles, Spain - Author
UPC, Inst Robot & Informat Ind, CSIC, Barcelona, Spain - Author
Volinga AI, Los Angeles, CA USA - Author
See more

Abstract

Advances in NERFs have allowed for 3D scene reconstructions and novel view synthesis. Yet, efficiently editing these representations while retaining photorealism is an emerging challenge. Recent methods face three primary limitations: they're slow for interactive use, lack precision at object boundaries, and struggle to ensure multi-view consistency. We introduce IReNe to address these limitations, enabling swift, near real-time color editing in NeRF. Leveraging a pre-trained NeRF model and a single training image with user-applied color edits, IReNe swiftly adjusts network parameters in seconds. This adjustment allows the model to generate new scene views, accurately representing the color changes from the training image while also controlling object boundaries and view-specific effects. Object boundary control is achieved by integrating a trainable segmentation module into the model. The process gains efficiency by retraining only the weights of the last network layer. We observed that neurons in this layer can be classified into those responsible for view-dependent appearance and those contributing to diffuse appearance. We introduce an automated classification approach to identify these neuron types and exclusively fine-tune the weights of the diffuse neurons. This further accelerates training and ensures consistent color edits across different views. A thorough validation on a new dataset, with edited object colors, shows significant quantitative and qualitative advancements over competitors, accelerating speeds by 5x to 500x.
[+]

Keywords

ColorDeep learningEditingEditing in neural radiance fieldNerfNeural radiance fieldRecoloringSegmentation

Quality index

Bibliometric impact. Analysis of the contribution and dissemination channel

The work has been published in the journal Proceedings Of The Ieee Computer Society Conference On Computer Vision And Pattern Recognition due to its progression and the good impact it has achieved in recent years, according to the agency Scopus (SJR), it has become a reference in its field. In the year of publication of the work, 2024 there are still no calculated indicators, but in 2023, it was in position , thus managing to position itself as a Q1 (Primer Cuartil), in the category Software. Notably, the journal is positioned above the 90th percentile.

[+]

Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2025-12-22:

  • The use, from an academic perspective evidenced by the Altmetric agency indicator referring to aggregations made by the personal bibliographic manager Mendeley, gives us a total of: 20.
  • The use of this contribution in bookmarks, code forks, additions to favorite lists for recurrent reading, as well as general views, indicates that someone is using the publication as a basis for their current work. This may be a notable indicator of future more formal and academic citations. This claim is supported by the result of the "Capture" indicator, which yields a total of: 19 (PlumX).

With a more dissemination-oriented intent and targeting more general audiences, we can observe other more global scores such as:

  • The Total Score from Altmetric: 3.

It is essential to present evidence supporting full alignment with institutional principles and guidelines on Open Science and the Conservation and Dissemination of Intellectual Heritage. A clear example of this is:

  • The work has been submitted to a journal whose editorial policy allows open Open Access publication.
[+]

Leadership analysis of institutional authors

This work has been carried out with international collaboration, specifically with researchers from: United States of America.

[+]

Awards linked to the item

This work is supported by Arquimea Research Center and Horizon Europe, Teaming for Excellence, under grant agreement No 101059999, project QCircle, and by project MoHuCo (PID2020-120049RB-I00). Elena Garces was partially supported by a Juan de la Cierva - Incorporacion Fellowship (IJC2020-044192-I).
[+]