NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics Evaluation
Neural radiance fields (NeRF) are a groundbreaking computer vision technology that enables the generation of high-quality, immersive visual content from multiple viewpoints. This capability has significant advantages for applications such as virtual/augmented reality, 3D modelling, and content creat...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10815957/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841563283017957376 |
|---|---|
| author | Pedro Martin Antonio Rodrigues Joao Ascenso Maria Paula Queluz |
| author_facet | Pedro Martin Antonio Rodrigues Joao Ascenso Maria Paula Queluz |
| author_sort | Pedro Martin |
| collection | DOAJ |
| description | Neural radiance fields (NeRF) are a groundbreaking computer vision technology that enables the generation of high-quality, immersive visual content from multiple viewpoints. This capability has significant advantages for applications such as virtual/augmented reality, 3D modelling, and content creation for the film and entertainment industry. However, the evaluation of NeRF methods poses several challenges, including a lack of comprehensive datasets, reliable assessment methodologies, and objective quality metrics. This paper addresses the problem of NeRF view synthesis (NVS) quality assessment thoroughly, by conducting a rigorous subjective quality assessment test that considers several scene classes and recently proposed NVS methods. Additionally, the performance of a wide range of state-of-the-art conventional and learning-based full-reference 2D image and video quality assessment metrics is evaluated against the subjective scores of the subjective study. This study found that errors in camera pose estimation can result in spatial misalignments between synthesized and reference images, which need to be corrected before applying an objective quality metric. The experimental results are analyzed in depth, providing a comparative evaluation of several NVS methods and objective quality metrics, across different classes of visual scenes, including real and synthetic content for front-face and 360° camera trajectories. |
| format | Article |
| id | doaj-art-497ff4d744ad415ab8e4a2bf140b7adc |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-497ff4d744ad415ab8e4a2bf140b7adc2025-01-03T00:01:43ZengIEEEIEEE Access2169-35362025-01-0113264110.1109/ACCESS.2024.352276810815957NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics EvaluationPedro Martin0https://orcid.org/0009-0004-5106-8483Antonio Rodrigues1https://orcid.org/0000-0003-2115-7245Joao Ascenso2https://orcid.org/0000-0001-9902-5926Maria Paula Queluz3https://orcid.org/0000-0003-0266-4022Instituto de Telecomunicações/Instituto Superior Técnico, University of Lisbon, Lisbon, PortugalInstituto de Telecomunicações/Instituto Superior Técnico, University of Lisbon, Lisbon, PortugalInstituto de Telecomunicações/Instituto Superior Técnico, University of Lisbon, Lisbon, PortugalInstituto de Telecomunicações/Instituto Superior Técnico, University of Lisbon, Lisbon, PortugalNeural radiance fields (NeRF) are a groundbreaking computer vision technology that enables the generation of high-quality, immersive visual content from multiple viewpoints. This capability has significant advantages for applications such as virtual/augmented reality, 3D modelling, and content creation for the film and entertainment industry. However, the evaluation of NeRF methods poses several challenges, including a lack of comprehensive datasets, reliable assessment methodologies, and objective quality metrics. This paper addresses the problem of NeRF view synthesis (NVS) quality assessment thoroughly, by conducting a rigorous subjective quality assessment test that considers several scene classes and recently proposed NVS methods. Additionally, the performance of a wide range of state-of-the-art conventional and learning-based full-reference 2D image and video quality assessment metrics is evaluated against the subjective scores of the subjective study. This study found that errors in camera pose estimation can result in spatial misalignments between synthesized and reference images, which need to be corrected before applying an objective quality metric. The experimental results are analyzed in depth, providing a comparative evaluation of several NVS methods and objective quality metrics, across different classes of visual scenes, including real and synthetic content for front-face and 360° camera trajectories.https://ieeexplore.ieee.org/document/10815957/NeRFobjective quality metricssubjective quality assessmentview synthesis |
| spellingShingle | Pedro Martin Antonio Rodrigues Joao Ascenso Maria Paula Queluz NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics Evaluation IEEE Access NeRF objective quality metrics subjective quality assessment view synthesis |
| title | NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics Evaluation |
| title_full | NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics Evaluation |
| title_fullStr | NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics Evaluation |
| title_full_unstemmed | NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics Evaluation |
| title_short | NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics Evaluation |
| title_sort | nerf view synthesis subjective quality assessment and objective metrics evaluation |
| topic | NeRF objective quality metrics subjective quality assessment view synthesis |
| url | https://ieeexplore.ieee.org/document/10815957/ |
| work_keys_str_mv | AT pedromartin nerfviewsynthesissubjectivequalityassessmentandobjectivemetricsevaluation AT antoniorodrigues nerfviewsynthesissubjectivequalityassessmentandobjectivemetricsevaluation AT joaoascenso nerfviewsynthesissubjectivequalityassessmentandobjectivemetricsevaluation AT mariapaulaqueluz nerfviewsynthesissubjectivequalityassessmentandobjectivemetricsevaluation |