Photometric Depth Super-Resolution

Autor: Songyou Peng, Daniel Cremers, Alok Verma, Bjoern Haefner, Yvain Quéau

Publikováno v: IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2020, 42 (10), pp.2453--2464. ⟨10.1109/TPAMI.2019.2923621⟩

This study explores the use of photometric techniques (shape-from-shading and uncalibrated photometric stereo) for upsampling the low-resolution depth map from an RGB-D sensor to the higher resolution of the companion RGB image. A single-shot variati

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bdace47494b8dec198cedcc7d65af0dd
https://doi.org/10.1109/tpami.2019.2923621

Sublabel-Accurate Multilabeling Meets Product Label Spaces

Autor: Zhenzhang Ye, Bjoern Haefner, Yvain Quéau, Thomas Möllenhoff, Daniel Cremers

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030926588
43rd DAGM German Conference on Pattern Recognition
43rd DAGM German Conference on Pattern Recognition, 2021, Bonn (online event), Germany

International audience; Functional lifting methods are a promising approach to determine optimal or near-optimal solutions to difficult nonconvex variational problems. Yet, they come with increased memory demands, limiting their practicability. To ov

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8487d1e8599a708e009ee9088f506763
https://doi.org/10.1007/978-3-030-92659-5_1

On the well-posedness of uncalibrated photometric stereo under general lighting

Autor: Daniel Cremers, Mohammed Brahimi, Bjoern Haefner, Yvain Quéau

Publikováno v: Advances in Photometric 3D-Reconstruction
Durou, Jean-Denis; Falcone, Maurizio; Queau, Yvain; Tozza, Silvia. Advances in Photometric 3D-Reconstruction, Springer International Publishing, pp.147--176, 2020, Advances in Computer Vision and Pattern Recognition, ⟨10.1007/978-3-030-51866-0_5⟩
Advances in Photometric 3D-Reconstruction ISBN: 9783030518653

International audience; 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. While the theoretical foundations of this inver

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b9a6f1760dcd21efddcf26d3d8c45f8
https://hal-normandie-univ.archives-ouvertes.fr/hal-02297643v2/document

Variational Uncalibrated Photometric Stereo under General Lighting

Autor: Maolin Gao, Tao Wu, Daniel Cremers, Bjoern Haefner, Yvain Quéau, Zhenzhang Ye

Publikováno v: The IEEE International Conference on Computer Vision (ICCV 2019)
The IEEE International Conference on Computer Vision (ICCV 2019), Oct 2019, Seoul, South Korea. pp.8539-8548, ⟨10.1109/ICCV.2019.00863⟩
ICCV

Photometric stereo (PS) techniques nowadays remain constrained to an ideal laboratory setup where modeling and calibration of lighting is amenable. To eliminate such restrictions, we propose an efficient principled variational approach to uncalibrate

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c0433bd8444891807624756af313712
http://arxiv.org/abs/1904.03942

Depth Super-Resolution Meets Uncalibrated Photometric Stereo

Autor: Yvain Quéau, Daniel Cremers, Bjoern Haefner, Songyou Peng

Publikováno v: 2017 IEEE International Conference on Computer Vision Workshop (ICCVW)
2017 IEEE International Conference on Computer Vision Workshop (ICCVW), Oct 2017, Venice, Italy. pp.2961-2968, ⟨10.1109/ICCVW.2017.349⟩
ICCV Workshops

A novel depth super-resolution approach for RGB-D sensors is presented. It disambiguates depth super-resolution through high-resolution photometric clues and, symmetrically, it disambiguates uncalibrated photometric stereo through low-resolution dept

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0b1e54f79a067f881aee6cf07dfab8e2