.png){kind=icon}
Return
Physics-based learning: Adaptive structured light for active stereo depth estimation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.optlaseng.2023.107883.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Active stereo systems based on structured light are widely used for 3D vision in various applications, which project specially designed patterns onto object surfaces to encode each position in space for accurate 3D measurements. However, existing approaches use pre-determined patterns that are isolated from the scene properties (object reflectivity, distance, ambient light, inter-reflection), equipment (projector, camera), and reconstruction. Meanwhile, the parameters of the structured light are determined through empirical analysis or several experiments. In this paper, we propose a novel structured light design approach, named Physics-Based Learning Adaptive Structured Light (PBL-ASL), which directly learns the optimal structured light patterns from the scene. To this end, (1) we design a decoder with a non-sinusoidal error suppression module for PBL-ASL, which can accurately estimate the disparity during structured light optimization; (2) we propose a physics-based learning algorithm consisting of a self-supervised objective function and a differentiable imaging model, which computes the disparity error and back-propagates the gradient to the encoding vector to optimize the structured light. Our experiments demonstrate that PBL-ASL can significantly improve the depth estimation accuracy of active stereo systems over several state-of-art methods.
Keywords:
Adaptive structured light
Depth estimation
Physics-based learning
Journal
IF:
3.7
Papers:
7.3K
Citations:
1.7W
Organization
Cited Papers
ShareSaveShareSaveOptimal biologic dose of metronomic chemotherapy regimens is associated with maximum antiangiogenic activity.png)
Blood
OAAI
BloodIF0
OAAIShareSaveDune vegetation dynamics from 1937 to 1976 in the Mlalazi-Richards Bay area of Natal, South AfricaBothalia
OAAI
BothaliaIF0
OAAIShareSaveShareSaveShareSaveGeneralized framework for non-sinusoidal fringe analysis using deep learningPHOTONICS RESEARCH
PHOTONICS RESEARCHIF7.2
PREAI
ShareSaveA state of the art in structured light patterns for surface profilometryPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveHigh-efficiency dynamic three-dimensional shape measurement based on misaligned Gray-code light
PREAI
ShareSaveShareSave
View more