首页|Uni MS-PS: A multi-scale encoder-decoder transformer for universal photometric stereo
Uni MS-PS: A multi-scale encoder-decoder transformer for universal photometric stereo
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Elsevier
Photometric Stereo (PS) addresses the challenge of reconstructing a three-dimensional (3D) representation of an object by estimating the 3D normals at all points on the object's surface。 This is achieved through the analysis of at least three photographs， all taken from the same viewpoint but with distinct lighting conditions。 This paper introduces a novel approach for Universal PS， i。e。， when both the active lighting conditions and the ambient illumination are unknown。 Our method employs a multi-scale encoder-decoder architecture based on Transformers that allows to accommodates images of any resolutions as well as varying number of input images。 We are able to scale up to very high resolution images like 6000 pixels by 8000 pixels without losing performance and maintaining a decent memory footprint。 Moreover， experiments on publicly available datasets establish that our proposed architecture improves the accuracy of the estimated normal field by a significant factor compared to state-of-the-art methods。
NETL
NSTL
Elsevier
