Self-calibrating deep photometric stereo networks
This paper proposes an uncalibrated photometric stereo method for non-Lambertian scenes
based on deep learning. Unlike previous approaches that heavily rely on assumptions of …
based on deep learning. Unlike previous approaches that heavily rely on assumptions of …
Universal photometric stereo network using global lighting contexts
S Ikehata - Proceedings of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
This paper tackles a new photometric stereo task, named universal photometric stereo.
Unlike existing tasks that assumed specific physical lighting models; hence, drastically …
Unlike existing tasks that assumed specific physical lighting models; hence, drastically …
What is learned in deep uncalibrated photometric stereo?
This paper targets at discovering what a deep uncalibrated photometric stereo network
learns to resolve the problem's inherent ambiguity, and designing an effective network …
learns to resolve the problem's inherent ambiguity, and designing an effective network …
PS-FCN: A flexible learning framework for photometric stereo
This paper addresses the problem of photometric stereo for non-Lambertian surfaces.
Existing approaches often adopt simplified reflectance models to make the problem more …
Existing approaches often adopt simplified reflectance models to make the problem more …
Learning conditional photometric stereo with high-resolution features
Photometric stereo aims to reconstruct 3D geometry by recovering the dense surface
orientation of a 3D object from multiple images under differing illumination. Traditional …
orientation of a 3D object from multiple images under differing illumination. Traditional …
Learning to minify photometric stereo
Photometric stereo estimates the surface normal given a set of images acquired under
different illumination conditions. To deal with diverse factors involved in the image formation …
different illumination conditions. To deal with diverse factors involved in the image formation …
Recovering surface normal and arbitrary images: A dual regression network for photometric stereo
Photometric stereo recovers three-dimensional (3D) object surface normal from multiple
images under different illumination directions. Traditional photometric stereo methods suffer …
images under different illumination directions. Traditional photometric stereo methods suffer …
Px-net: Simple and efficient pixel-wise training of photometric stereo networks
Retrieving accurate 3D reconstructions of objects from the way they reflect light is a very
challenging task in computer vision. Despite more than four decades since the definition of …
challenging task in computer vision. Despite more than four decades since the definition of …
Deep photometric stereo for non-lambertian surfaces
This paper addresses the problem of photometric stereo, in both calibrated and uncalibrated
scenarios, for non-Lambertian surfaces based on deep learning. We first introduce a fully …
scenarios, for non-Lambertian surfaces based on deep learning. We first introduce a fully …
Neural radiance fields approach to deep multi-view photometric stereo
We present a modern solution to the multi-view photometric stereo problem (MVPS). Our
work suitably exploits the image formation model in a MVPS experimental setup to recover …
work suitably exploits the image formation model in a MVPS experimental setup to recover …