Iterative Occlusion-Aware Light Field Depth Estimation using 4D Geometrical Cues
Instituto de Telecomunicações, Portugal（葡萄牙电信研究所）；ESTG - Polytechnic University of Leiria（莱里亚理工学院）；PEE, COPPE, Federal University of Rio de Janeiro（里约热内卢联邦大学）
Rui Lourenço, Lucas Thomaz, Eduardo A. B. Silva, Sergio M. M. Faria
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 MSE ${\times}$ 100 and Badpix 0.07.
University of Washington（华盛顿大学）；ByteDance AI Lab（字节跳动人工智能实验室）
Recently, significant progress has been made in single-view depth estimation thanks to increasingly large and diverse depth datasets. However, these datasets are largely limited to specific application domains (e.g. indoor, autonomous driving) or static in-the-wild scenes due to hardware constraints or technical limitations of 3D reconstruction. In this paper, we introduce the first depth dataset DynOcc consisting of dynamic in-the-wild scenes. Our approach leverages the occlusion cues in these dynamic scenes to infer depth relationships between points of selected video frames. To achieve accu…
LIGM（LIGM实验室）；Ecole des Ponts（巴黎路桥学院）；Univ Gustave Eiffel（古斯塔夫·埃菲尔大学）；CNRS（法国国家科学研究中心）
Current methods for depth map prediction from monocular images tend to predict smooth, poorly localized contours for the occlusion boundaries in the input image. This is unfortunate as occlusion boundaries are important cues to recognize objects, and as we show, may lead to a way to discover new objects from scene reconstruction. To improve predicted depth maps, recent methods rely on various forms of filtering or predict an additive residual depth map to refine a first estimate. We instead learn to predict, given a depth map predicted by some reconstruction method, a 2D displacement field abl…
Localizing stereo boundaries and predicting nearby disparities are difficult because stereo boundaries induce occluded regions where matching cues are absent. Most modern computer vision algorithms treat occlusions secondarily (e.g., via left-right consistency checks after matching) or rely on high-level cues to improve nearby disparities (e.g., via deep networks and large training sets). They ignore the geometry of stereo occlusions, which dictates that the spatial extent of occlusion must equal the amplitude of the disparity jump that causes it. This paper introduces an energy and level-set …
GenHOI: Generalized Hand-Object Pose Estimation with Occlusion Awareness
Hunan University（湖南大学）；Lancaster University（兰卡斯特大学）；University of Western Australia（西澳大学）；University of Trento（特伦托大学）；National University of Singapore（新加坡国立大学）
The human visual system uses numerous cues for depth perception, including disparity, accommodation, motion parallax and occlusion. It is incumbent upon virtual-reality displays to satisfy these cues to provide an immersive user experience. Multifocal displays, one of the classic approaches to satisfy the accommodation cue, place virtual content at multiple focal planes, each at a di erent depth. However, the content on focal planes close to the eye do not occlude those farther away; this deteriorates the occlusion cue as well as reduces contrast at depth discontinuities due to leakage of the …
Classification and segmentation of 3D point clouds are important tasks in computer vision. Because of the irregular nature of point clouds, most of the existing methods convert point clouds into regular 3D voxel grids before they are used as input for ConvNets. Unfortunately, voxel representations are highly insensitive to the geometrical nature of 3D data. More recent methods encode point clouds to higher dimensional features to cover the global 3D space. However, these models are not able to sufficiently capture the local structures of point clouds. Therefore, in this paper, we propose a met…
Tsinghua University（清华大学）；BNRist（北京国家信息科学与技术研究中心）；Google Inc.（谷歌公司）；Technical University of Munich（慕尼黑工业大学）
6D object pose estimation is a fundamental yet challenging problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even under monocular settings. Nonetheless, CNNs are identified as being extremely data-driven, and acquiring adequate annotations is oftentimes very time-consuming and labor intensive. To overcome this limitation, we propose a novel monocular 6D pose estimation approach by means of self-supervised learning, removing the need for real annotations. After training our proposed network fully supervis…
MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image
Faculty of Computer Science and Technology, Ocean University of China（中国海洋大学计算机科学与技术学院）；School of Information Science and Engineering, Shandong University（山东大学信息科学与工程学院）
Korea Advanced Institute of Science and Technology（韩国科学技术院）；School of Electrical Engineering（电气工程学院）
Self-supervised depth estimators have recently shown results comparable to the supervised methods on the challenging single image depth estimation (SIDE) task, by exploiting the geometrical relations between target and reference views in the training data. However, previous methods usually learn forward or backward image synthesis, but not depth estimation, as they cannot effectively neglect occlusions between the target and the reference images. Previous works rely on rigid photometric assumptions or the SIDE network to infer depth and occlusions, resulting in limited performance. On the othe…
Existing light field representations, such as epipolar plane image (EPI) and sub-aperture images, do not consider the structural characteristics across the views, so they usually require additional disparity and spatial structure cues for follow-up tasks. Besides, they have difficulties dealing with occlusions or larger disparity scenes. To this end, this paper proposes a novel Epipolar Focus Spectrum (EFS) representation by rearranging the EPI spectrum. Different from the classical EPI representation where an EPI line corresponds to a specific depth, there is a one-to-one mapping from the EFS…
To get clear street-view and photo-realistic simulation in autonomous driving, we present an automatic video inpainting algorithm that can remove traffic agents from videos and synthesize missing regions with the guidance of depth/point cloud. By building a dense 3D map from stitched point clouds, frames within a video are geometrically correlated via this common 3D map. In order to fill a target inpainting area in a frame, it is straightforward to transform pixels from other frames into the current one with correct occlusion. Furthermore, we are able to fuse multiple videos through 3D point c…
