International audienceThis paper proposes a learning based solution to disparity (depth) estimation for either densely or sparsely sampled light fields. Disparity between stereo pairs among a sparse subset of anchor views is first estimated by a fine-tuned FlowNet 2.0 network adapted to disparity prediction task. These coarse estimates are fused by exploiting the photo-consistency warping error, and refined by a Multi-view Stereo Refinement Network (MSRNet). The propagation of disparity from anchor viewpoints towards other viewpoints is performed by an occlusion-aware soft 3D reconstruction method. The experiments show that, both for dense and sparse light fields, our algorithm outperforms significantly the state-of-the-art algorithms, espe...
Recent deep learning-based light field disparity estimation algorithms require millions of parameter...
Recent deep learning-based light field disparity estimation algorithms require millions of parameter...
A light field samples the scene from different perspectives, and the directional information contain...
International audienceThis paper proposes a learning based solution to disparity (depth) estimation ...
International audienceThis paper proposes a learning based solution to disparity (depth) estimation ...
International audienceThis paper proposes a learning based solution to disparity (depth) estimation ...
International audienceThis paper addresses the problem of depth estimation for every viewpoint of a ...
An occlusion-aware framework is proposed to robustly estimate the disparities of light field images....
International audienceThis paper addresses the problem of depth estimation for every viewpoint of a ...
International audienceThis paper addresses the problem of depth estimation for every viewpoint of a ...
International audienceThis paper addresses the problem of depth estimation for every viewpoint of a ...
Light fields have been populated as a new geometry representation of 3D scenes, which is composed of...
Light Field (LF) imaging, since it conveys both spatial and angular scene information, can facilitat...
Light Field (LF) imaging, since it conveys both spatial and angular scene information, can facilitat...
International audienceThis paper describes a lightweight neural network architecture with an adversa...
Recent deep learning-based light field disparity estimation algorithms require millions of parameter...
Recent deep learning-based light field disparity estimation algorithms require millions of parameter...
A light field samples the scene from different perspectives, and the directional information contain...
International audienceThis paper proposes a learning based solution to disparity (depth) estimation ...
International audienceThis paper proposes a learning based solution to disparity (depth) estimation ...
International audienceThis paper proposes a learning based solution to disparity (depth) estimation ...
International audienceThis paper addresses the problem of depth estimation for every viewpoint of a ...
An occlusion-aware framework is proposed to robustly estimate the disparities of light field images....
International audienceThis paper addresses the problem of depth estimation for every viewpoint of a ...
International audienceThis paper addresses the problem of depth estimation for every viewpoint of a ...
International audienceThis paper addresses the problem of depth estimation for every viewpoint of a ...
Light fields have been populated as a new geometry representation of 3D scenes, which is composed of...
Light Field (LF) imaging, since it conveys both spatial and angular scene information, can facilitat...
Light Field (LF) imaging, since it conveys both spatial and angular scene information, can facilitat...
International audienceThis paper describes a lightweight neural network architecture with an adversa...
Recent deep learning-based light field disparity estimation algorithms require millions of parameter...
Recent deep learning-based light field disparity estimation algorithms require millions of parameter...
A light field samples the scene from different perspectives, and the directional information contain...