Exploring Metric Fusion for Evaluation of NeRFs
This work addresses the problem of accurate quality assessment for NeRF-generated outputs, which is incremental as it combines existing metrics rather than introducing a new paradigm.
The paper tackled the challenge of evaluating Neural Radiance Fields (NeRFs) by proposing a fusion of DISTS and VMAF metrics to improve correlation with subjective quality scores, achieving robust performance across two datasets and three configurations.
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.