Saved in:
Bibliographic Details
Main Authors: Shivakumara, Shreyas, Eilertsen, Gabriel, Palmerius, Karljohan Lundin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.12836
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915496845115392
author Shivakumara, Shreyas
Eilertsen, Gabriel
Palmerius, Karljohan Lundin
author_facet Shivakumara, Shreyas
Eilertsen, Gabriel
Palmerius, Karljohan Lundin
contents Neural Radiance Fields (NeRFs) have demonstrated significant potential in synthesizing novel viewpoints. Evaluating the NeRF-generated outputs, however, remains a challenge due to the unique artifacts they exhibit, and no individual metric performs well across all datasets. We hypothesize that combining two successful metrics, Deep Image Structure and Texture Similarity (DISTS) and Video Multi-Method Assessment Fusion (VMAF), based on different perceptual methods, can overcome the limitations of individual metrics and achieve improved correlation with subjective quality scores. We experiment with two normalization strategies for the individual metrics and two fusion strategies to evaluate their impact on the resulting correlation with the subjective scores. The proposed pipeline is tested on two distinct datasets, Synthetic and Outdoor, and its performance is evaluated across three different configurations. We present a detailed analysis comparing the correlation coefficients of fusion methods and individual scores with subjective scores to demonstrate the robustness and generalizability of the fusion metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12836
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Metric Fusion for Evaluation of NeRFs
Shivakumara, Shreyas
Eilertsen, Gabriel
Palmerius, Karljohan Lundin
Computer Vision and Pattern Recognition
Neural Radiance Fields (NeRFs) have demonstrated significant potential in synthesizing novel viewpoints. Evaluating the NeRF-generated outputs, however, remains a challenge due to the unique artifacts they exhibit, and no individual metric performs well across all datasets. We hypothesize that combining two successful metrics, Deep Image Structure and Texture Similarity (DISTS) and Video Multi-Method Assessment Fusion (VMAF), based on different perceptual methods, can overcome the limitations of individual metrics and achieve improved correlation with subjective quality scores. We experiment with two normalization strategies for the individual metrics and two fusion strategies to evaluate their impact on the resulting correlation with the subjective scores. The proposed pipeline is tested on two distinct datasets, Synthetic and Outdoor, and its performance is evaluated across three different configurations. We present a detailed analysis comparing the correlation coefficients of fusion methods and individual scores with subjective scores to demonstrate the robustness and generalizability of the fusion metrics.
title Exploring Metric Fusion for Evaluation of NeRFs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.12836