The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Le champ lumineux de surface fait progresser les techniques conventionnelles de rendu de champ lumineux en utilisant les informations géométriques. Grâce au champ lumineux de surface, des objets du monde réel d’apparence complexe ont pu être fidèlement représentés. Cette capacité pourrait jouer un rôle important dans de nombreuses applications VR/AR. Cependant, un modèle géométrique précis est nécessaire pour l'échantillonnage et le traitement du champ lumineux de surface, ce qui limite son utilisation à grande échelle, car de nombreux objets d'intérêt sont difficiles à reconstruire en raison de leur apparence généralement très complexe. Nous proposons un nouveau cadre d'optimisation en deux étapes pour réduire la dépendance à une géométrie précise. L’idée clé est de traiter l’échantillonnage du champ lumineux de surface comme un problème d’optimisation multi-vues et multi-textures. Notre approche peut gérer à la fois l'inexactitude du modèle et le désalignement image par modèle, ce qui permet de créer des modèles de champ lumineux de surface haute fidélité sans utiliser de matériel spécial de haute précision.
Wei LI
Nanjing University of Aeronautics and Astronautics
Huajun GONG
Nanjing University of Aeronautics and Astronautics
Chunlin SHEN
Nanjing University of Aeronautics and Astronautics
Yi WU
Nanjing University of Aeronautics and Astronautics
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Wei LI, Huajun GONG, Chunlin SHEN, Yi WU, "Patch Optimization for Surface Light Field Reconstruction" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 12, pp. 3267-3271, December 2018, doi: 10.1587/transinf.2018EDL8072.
Abstract: Surface light field advances conventional light field rendering techniques by utilizing geometry information. Using surface light field, real-world objects with complex appearance could be faithfully represented. This capability could play an important role in many VR/AR applications. However, an accurate geometric model is needed for surface light field sampling and processing, which limits its wide usage since many objects of interests are difficult to reconstruct with their usually very complex appearances. We propose a novel two-step optimization framework to reduce the dependency of accurate geometry. The key insight is to treat surface light field sampling as a multi-view multi-texture optimization problem. Our approach can deal with both model inaccuracy and image to model misalignment, making it possible to create high-fidelity surface light field models without using high-precision special hardware.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8072/_p
Copier
@ARTICLE{e101-d_12_3267,
author={Wei LI, Huajun GONG, Chunlin SHEN, Yi WU, },
journal={IEICE TRANSACTIONS on Information},
title={Patch Optimization for Surface Light Field Reconstruction},
year={2018},
volume={E101-D},
number={12},
pages={3267-3271},
abstract={Surface light field advances conventional light field rendering techniques by utilizing geometry information. Using surface light field, real-world objects with complex appearance could be faithfully represented. This capability could play an important role in many VR/AR applications. However, an accurate geometric model is needed for surface light field sampling and processing, which limits its wide usage since many objects of interests are difficult to reconstruct with their usually very complex appearances. We propose a novel two-step optimization framework to reduce the dependency of accurate geometry. The key insight is to treat surface light field sampling as a multi-view multi-texture optimization problem. Our approach can deal with both model inaccuracy and image to model misalignment, making it possible to create high-fidelity surface light field models without using high-precision special hardware.},
keywords={},
doi={10.1587/transinf.2018EDL8072},
ISSN={1745-1361},
month={December},}
Copier
TY - JOUR
TI - Patch Optimization for Surface Light Field Reconstruction
T2 - IEICE TRANSACTIONS on Information
SP - 3267
EP - 3271
AU - Wei LI
AU - Huajun GONG
AU - Chunlin SHEN
AU - Yi WU
PY - 2018
DO - 10.1587/transinf.2018EDL8072
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2018
AB - Surface light field advances conventional light field rendering techniques by utilizing geometry information. Using surface light field, real-world objects with complex appearance could be faithfully represented. This capability could play an important role in many VR/AR applications. However, an accurate geometric model is needed for surface light field sampling and processing, which limits its wide usage since many objects of interests are difficult to reconstruct with their usually very complex appearances. We propose a novel two-step optimization framework to reduce the dependency of accurate geometry. The key insight is to treat surface light field sampling as a multi-view multi-texture optimization problem. Our approach can deal with both model inaccuracy and image to model misalignment, making it possible to create high-fidelity surface light field models without using high-precision special hardware.
ER -