Image Valuation in NeRF-based 3D reconstruction

TL;DR

This paper introduces a method to evaluate the contribution of individual images in NeRF-based 3D scene reconstruction, helping identify and remove less useful images to improve reconstruction quality.

Contribution

It proposes a novel approach to quantify image contributions in NeRF reconstructions using quality metrics, addressing uneven input utility in real-world scenes.

Findings

Removing low-contributing images improves reconstruction fidelity.

The method effectively identifies less useful images based on PSNR and MSE.

Validation shows enhanced 3D reconstruction quality after input filtering.

Abstract

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.