Neural Multi-View Self-Calibrated Photometric Stereo without Photometric Stereo Cues

TL;DR

This paper introduces a neural inverse rendering method that jointly reconstructs geometry, reflectance, and lighting from multi-view images without relying on traditional photometric cues or light calibration, using neural implicit fields and shadow-aware rendering.

Contribution

It presents a unified neural approach that jointly estimates all scene parameters directly from raw images, eliminating the need for intermediate cues or calibration steps.

Findings

Outperforms state-of-the-art in shape and lighting accuracy

Generalizes to view-unaligned multi-light images

Handles complex geometry and reflectance

Abstract

We propose a neural inverse rendering approach that jointly reconstructs geometry, spatially varying reflectance, and lighting conditions from multi-view images captured under varying directional lighting. Unlike prior multi-view photometric stereo methods that require light calibration or intermediate cues such as per-view normal maps, our method jointly optimizes all scene parameters from raw images in a single stage. We represent both geometry and reflectance as neural implicit fields and apply shadow-aware volume rendering. A spatial network first predicts the signed distance and a reflectance latent code for each scene point. A reflectance network then estimates reflectance values conditioned on the latent code and angularly encoded surface normal, view, and light directions. The proposed method outperforms state-of-the-art normal-guided approaches in shape and lighting estimation accuracy, generalizes to view-unaligned multi-light images, and handles objects with challenging geometry and reflectance.