Uncalibrated neural inverse rendering for photometric stereo of general surfaces
This paper presents an uncalibrated deep neural network framework for the photometric
stereo problem. For training models to solve the problem, existing neural network-based …
stereo problem. For training models to solve the problem, existing neural network-based …
Shape and material capture at home
In this paper, we present a technique for estimating the geometry and reflectance of objects
using only a camera, flashlight, and optionally a tripod. We propose a simple data capture …
using only a camera, flashlight, and optionally a tripod. We propose a simple data capture …
Shape from sky: Polarimetric normal recovery under the sky
The sky exhibits a unique spatial polarization pattern by scattering the unpolarized sun light.
Just like insects use this unique angular pattern to navigate, we use it to map pixels to …
Just like insects use this unique angular pattern to navigate, we use it to map pixels to …
Calibration of position and orientation for point light source synchronously with single image in photometric stereo
L Ma, J Liu, X Pei, Y Hu, F Sun - Optics express, 2019 - opg.optica.org
In this paper, a calibration method for non-isotropic point light source is developed, which is
capable of calibrating position and orientation of the point light source with a single image …
capable of calibrating position and orientation of the point light source with a single image …
Low-rank registration of images captured under unknown, varying lighting
Photometric stereo infers the 3D-shape of a surface from a sequence of images captured
under moving lighting and a static camera. However, in real-world scenarios the viewing …
under moving lighting and a static camera. However, in real-world scenarios the viewing …
On the well-posedness of uncalibrated photometric stereo under general lighting
Uncalibrated photometric stereo aims at estimating the 3D-shape of a surface, given a set of
images captured from the same viewing angle, but under unknown, varying illumination …
images captured from the same viewing angle, but under unknown, varying illumination …
Photometric segmentation: Simultaneous photometric stereo and masking
This work is concerned with both the 3D-reconstruction of an object using photometric
stereo, and its 2D-segmentation from the background. In contrast with previous works on …
stereo, and its 2D-segmentation from the background. In contrast with previous works on …
Methods for Surface Understanding from Multi-Modal Imagery
M Purri - 2022 - search.proquest.com
A fundamental goal within the field of computer vision is to develop a system capable of
understanding all aspects of a given visual input. Since the (re) emergence of convolutional …
understanding all aspects of a given visual input. Since the (re) emergence of convolutional …
[PDF][PDF] 深度学**技术在光度立体三维重建中的应用
王国珲， 卢彦汀 - Laser & Optoelectronics Progress, 2023 - researching.cn
摘要光度立体三维(3D) 重建是机器视觉和光度学领域中研究的热点问题, 由于设备简单,
成本低廉, 分辨率高, 得到广泛的应用. **年来, 伴随着人工智能与深度学**技术的蓬勃发展 …
成本低廉, 分辨率高, 得到广泛的应用. **年来, 伴随着人工智能与深度学**技术的蓬勃发展 …
On the well-posedness of uncalibrated photometric stereo under general lighting
Uncalibrated photometric stereo aims at estimating the 3D-shape of a surface, given a set of
images captured from the same viewing angle, but under unknown, varying illumination …
images captured from the same viewing angle, but under unknown, varying illumination …