RePose-NeRF: Robust Radiance Fields for Mesh Reconstruction under Noisy Camera Poses

TL;DR

RePose-NeRF introduces a robust method for reconstructing high-quality, editable 3D meshes from multi-view images with noisy camera poses, enhancing practical robotic applications by jointly refining poses and scene representation.

Contribution

It presents a novel framework that simultaneously refines camera poses and learns implicit scene representations to produce accurate, editable 3D meshes from noisy multi-view data.

Findings

Achieves accurate 3D reconstruction under pose noise

Produces meshes compatible with standard 3D tools

Demonstrates robustness on benchmark datasets

Abstract

Accurate 3D reconstruction from multi-view images is essential for downstream robotic tasks such as navigation, manipulation, and environment understanding. However, obtaining precise camera poses in real-world settings remains challenging, even when calibration parameters are known. This limits the practicality of existing NeRF-based methods that rely heavily on accurate extrinsic estimates. Furthermore, their implicit volumetric representations differ significantly from the widely adopted polygonal meshes, making rendering and manipulation inefficient in standard 3D software. In this work, we propose a robust framework that reconstructs high-quality, editable 3D meshes directly from multi-view images with noisy extrinsic parameters. Our approach jointly refines camera poses while learning an implicit scene representation that captures fine geometric detail and photorealistic appearance. The resulting meshes are compatible with common 3D graphics and robotics tools, enabling efficient downstream use. Experiments on standard benchmarks demonstrate that our method achieves accurate and robust 3D reconstruction under pose uncertainty, bridging the gap between neural implicit representations and practical robotic applications.