Iterative Occlusion-Aware Light Field Depth Estimation using 4D Geometrical Cues

• URL: http://arxiv.org/abs/2403.02043v1
• Date: Mon, 4 Mar 2024 13:47:49 GMT
• Title: Iterative Occlusion-Aware Light Field Depth Estimation using 4D Geometrical Cues
• Authors: Rui Louren\c{c}o, Lucas Thomaz, Eduardo A. B. Silva, Sergio M. M. Faria
• Abstract summary: This paper focuses on explicitly understanding and exploiting 4D geometric cues for light field depth estimation. A 4D model performs depth/disparity estimation by determining the orientations and analysing the intersections of key 2D planes in 4D space. Experimental results show that the proposed method outperforms both learning-based and non-learning-based state-of-the-art methods.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Light field cameras and multi-camera arrays have emerged as promising solutions for accurately estimating depth by passively capturing light information. This is possible because the 3D information of a scene is embedded in the 4D light field geometry. Commonly, depth estimation methods extract this information relying on gradient information, heuristic-based optimisation models, or learning-based approaches. This paper focuses mainly on explicitly understanding and exploiting 4D geometrical cues for light field depth estimation. Thus, a novel method is proposed, based on a non-learning-based optimisation approach for depth estimation that explicitly considers surface normal accuracy and occlusion regions by utilising a fully explainable 4D geometric model of the light field. The 4D model performs depth/disparity estimation by determining the orientations and analysing the intersections of key 2D planes in 4D space, which are the images of 3D-space points in the 4D light field. Experimental results show that the proposed method outperforms both learning-based and non-learning-based state-of-the-art methods in terms of surface normal angle accuracy, achieving a Median Angle Error on planar surfaces, on average, 26.3\% lower than the state-of-the-art, and still being competitive with state-of-the-art methods in terms of Mean Squared Error $\vc{\times}$ 100 and Badpix 0.07.

Related papers

• Surface Normal Reconstruction Using Polarization-Unet [0.0]
  Shape from polarization (SfP) is one of the best solutions for high-resolution three-dimensional reconstruction of objects. In this paper, an end-to-end deep learning approach has been presented to produce the surface normal of objects.
  arXiv  Detail & Related papers  (2024-06-21T13:09:58Z)
• GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection [95.8940731298518]
  We propose a novel Geometry Uncertainty Propagation Network (GUPNet++) It models the uncertainty propagation relationship of the geometry projection during training, improving the stability and efficiency of the end-to-end model learning. Experiments show that the proposed approach not only obtains (state-of-the-art) SOTA performance in image-based monocular 3D detection but also demonstrates superiority in efficacy with a simplified framework.
  arXiv  Detail & Related papers  (2023-10-24T08:45:15Z)
• Coupled Iterative Refinement for 6D Multi-Object Pose Estimation [64.7198752089041]
  Given a set of known 3D objects and an RGB or RGB-D input image, we detect and estimate the 6D pose of each object. Our approach iteratively refines both pose and correspondence in a tightly coupled manner, allowing us to dynamically remove outliers to improve accuracy.
  arXiv  Detail & Related papers  (2022-04-26T18:00:08Z)
• Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo [103.08512487830669]
  We present a modern solution to the multi-view photometric stereo problem (MVPS) We procure the surface orientation using a photometric stereo (PS) image formation model and blend it with a multi-view neural radiance field representation to recover the object's surface geometry. Our method performs neural rendering of multi-view images while utilizing surface normals estimated by a deep photometric stereo network.
  arXiv  Detail & Related papers  (2021-10-11T20:20:03Z)
• Learning Stereopsis from Geometric Synthesis for 6D Object Pose Estimation [11.999630902627864]
  Current monocular-based 6D object pose estimation methods generally achieve less competitive results than RGBD-based methods. This paper proposes a 3D geometric volume based pose estimation method with a short baseline two-view setting. Experiments show that our method outperforms state-of-the-art monocular-based methods, and is robust in different objects and scenes.
  arXiv  Detail & Related papers  (2021-09-25T02:55:05Z)
• Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection [70.71934539556916]
  We learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection. Specifically, a principled geometry formula with projective modeling of 2D and 3D depth predictions in the monocular 3D object detection network is devised. Our method remarkably improves the detection performance of the state-of-the-art monocular-based method without extra data by 2.80% on the moderate test setting.
  arXiv  Detail & Related papers  (2021-07-29T12:30:39Z)
• 3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimation [3.103806775802078]
  We propose a method for coarse camera pose computation which is robust to viewing conditions. It exploits the ability of deep learning techniques to reliably detect objects regardless of viewing conditions.
  arXiv  Detail & Related papers  (2021-05-24T18:40:18Z)
• LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo [30.31403197697561]
  We introduce LUCES, the first real-world 'dataset for near-fieLd point light soUrCe photomEtric Stereo' of 14 objects of a varying of materials. A device counting 52 LEDs has been designed to lit each object positioned 10 to 30 centimeters away from the camera. We evaluate the performance of the latest near-field Photometric Stereo algorithms on the proposed dataset.
  arXiv  Detail & Related papers  (2021-04-27T12:30:42Z)
• Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction [87.08227378010874]
  We show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, we significantly improve the accuracy and robustness of monocular depth estimation. We show state-of-the-art results of learning metric depth on NYU Depth-V2 and KITTI.
  arXiv  Detail & Related papers  (2021-03-07T00:08:21Z)
• Deep learning with 4D spatio-temporal data representations for OCT-based force estimation [59.405210617831656]
  We extend the problem of deep learning-based force estimation to 4D volumetric-temporal data with streams of 3D OCT volumes. We show that using 4Dterm-temporal data outperforms all previously used data representations with a mean absolute error of 10.7mN.
  arXiv  Detail & Related papers  (2020-05-20T13:30:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.