Image Valuation in NeRF-based 3D reconstruction
This addresses data valuation for 3D reconstruction in domains like XR and digital media, but is incremental as it applies existing metrics to a specific bottleneck.
The paper tackles the problem of uneven image utility in NeRF-based 3D reconstruction by proposing a method to quantify each image's contribution using PSNR and MSE metrics, and validates it by removing low-contributing images to measure impact on fidelity.
Data valuation and monetization are becoming increasingly important across domains such as eXtended Reality (XR) and digital media. In the context of 3D scene reconstruction from a set of images -- whether casually or professionally captured -- not all inputs contribute equally to the final output. Neural Radiance Fields (NeRFs) enable photorealistic 3D reconstruction of scenes by optimizing a volumetric radiance field given a set of images. However, in-the-wild scenes often include image captures of varying quality, occlusions, and transient objects, resulting in uneven utility across inputs. In this paper we propose a method to quantify the individual contribution of each image to NeRF-based reconstructions of in-the-wild image sets. Contribution is assessed through reconstruction quality metrics based on PSNR and MSE. We validate our approach by removing low-contributing images during training and measuring the resulting impact on reconstruction fidelity.