The Experts below are selected from a list of 69 Experts worldwide ranked by ideXlab platform
Edgar A. Bernal - One of the best experts on this subject based on the ideXlab platform.
-
Generative Adversarial Networks for Depth Map Estimation from RGB Video
2018 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018Co-Authors: Kin Gwn Lore, Kishore Reddy, Michael Giering, Edgar A. BernalAbstract:Depth cues are essential to achieving high-level scene understanding, and in particular to determining geometric relations between objects. The ability to reason about depth information in scene analysis tasks can often result in improved decision-making capabilities. Unfortunately, depth-capable sensors are not as ubiquitous as traditional RGB cameras, which limits the availability of depth-related cues. In this work, we investigate data-driven approaches for depth estimation from images or videos captured with monocular cameras. We propose three different approaches and demonstrate their efficacy through extensive experimental validation. The proposed methods rely on processing of (i) a single 3-channel RGB image Frame, (ii) a sequence of RGB Frames, and (iii) a single RGB Frame plus the optical flow field computed between the Frame and a Neighboring Frame in the video stream, and map the respective inputs to an estimated depth map representation. In contrast to existing literature, the input-output mapping is not directly regressed; rather, it is learned through adversarial techniques that leverage conditional generative adversarial networks (cGANs).
-
CVPR Workshops - Generative Adversarial Networks for Depth Map Estimation from RGB Video
2018 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018Co-Authors: Kishore K. Reddy, Michael Giering, Edgar A. BernalAbstract:Depth cues are essential to achieving high-level scene understanding, and in particular to determining geometric relations between objects. The ability to reason about depth information in scene analysis tasks can often result in improved decision-making capabilities. Unfortunately, depth-capable sensors are not as ubiquitous as traditional RGB cameras, which limits the availability of depth-related cues. In this work, we investigate data-driven approaches for depth estimation from images or videos captured with monocular cameras. We propose three different approaches and demonstrate their efficacy through extensive experimental validation. The proposed methods rely on processing of (i) a single 3-channel RGB image Frame, (ii) a sequence of RGB Frames, and (iii) a single RGB Frame plus the optical flow field computed between the Frame and a Neighboring Frame in the video stream, and map the respective inputs to an estimated depth map representation. In contrast to existing literature, the input-output mapping is not directly regressed; rather, it is learned through adversarial techniques that leverage conditional generative adversarial networks (cGANs).
Kin Gwn Lore - One of the best experts on this subject based on the ideXlab platform.
-
Generative Adversarial Networks for Depth Map Estimation from RGB Video
2018 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018Co-Authors: Kin Gwn Lore, Kishore Reddy, Michael Giering, Edgar A. BernalAbstract:Depth cues are essential to achieving high-level scene understanding, and in particular to determining geometric relations between objects. The ability to reason about depth information in scene analysis tasks can often result in improved decision-making capabilities. Unfortunately, depth-capable sensors are not as ubiquitous as traditional RGB cameras, which limits the availability of depth-related cues. In this work, we investigate data-driven approaches for depth estimation from images or videos captured with monocular cameras. We propose three different approaches and demonstrate their efficacy through extensive experimental validation. The proposed methods rely on processing of (i) a single 3-channel RGB image Frame, (ii) a sequence of RGB Frames, and (iii) a single RGB Frame plus the optical flow field computed between the Frame and a Neighboring Frame in the video stream, and map the respective inputs to an estimated depth map representation. In contrast to existing literature, the input-output mapping is not directly regressed; rather, it is learned through adversarial techniques that leverage conditional generative adversarial networks (cGANs).
Michael Giering - One of the best experts on this subject based on the ideXlab platform.
-
Generative Adversarial Networks for Depth Map Estimation from RGB Video
2018 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018Co-Authors: Kin Gwn Lore, Kishore Reddy, Michael Giering, Edgar A. BernalAbstract:Depth cues are essential to achieving high-level scene understanding, and in particular to determining geometric relations between objects. The ability to reason about depth information in scene analysis tasks can often result in improved decision-making capabilities. Unfortunately, depth-capable sensors are not as ubiquitous as traditional RGB cameras, which limits the availability of depth-related cues. In this work, we investigate data-driven approaches for depth estimation from images or videos captured with monocular cameras. We propose three different approaches and demonstrate their efficacy through extensive experimental validation. The proposed methods rely on processing of (i) a single 3-channel RGB image Frame, (ii) a sequence of RGB Frames, and (iii) a single RGB Frame plus the optical flow field computed between the Frame and a Neighboring Frame in the video stream, and map the respective inputs to an estimated depth map representation. In contrast to existing literature, the input-output mapping is not directly regressed; rather, it is learned through adversarial techniques that leverage conditional generative adversarial networks (cGANs).
-
CVPR Workshops - Generative Adversarial Networks for Depth Map Estimation from RGB Video
2018 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018Co-Authors: Kishore K. Reddy, Michael Giering, Edgar A. BernalAbstract:Depth cues are essential to achieving high-level scene understanding, and in particular to determining geometric relations between objects. The ability to reason about depth information in scene analysis tasks can often result in improved decision-making capabilities. Unfortunately, depth-capable sensors are not as ubiquitous as traditional RGB cameras, which limits the availability of depth-related cues. In this work, we investigate data-driven approaches for depth estimation from images or videos captured with monocular cameras. We propose three different approaches and demonstrate their efficacy through extensive experimental validation. The proposed methods rely on processing of (i) a single 3-channel RGB image Frame, (ii) a sequence of RGB Frames, and (iii) a single RGB Frame plus the optical flow field computed between the Frame and a Neighboring Frame in the video stream, and map the respective inputs to an estimated depth map representation. In contrast to existing literature, the input-output mapping is not directly regressed; rather, it is learned through adversarial techniques that leverage conditional generative adversarial networks (cGANs).
Shuigeng Zhou - One of the best experts on this subject based on the ideXlab platform.
-
ICCV - Non-Local ConvLSTM for Video Compression Artifact Reduction
2019 IEEE CVF International Conference on Computer Vision (ICCV), 2019Co-Authors: Yi Xu, Kai Tian, Shuigeng ZhouAbstract:Video compression artifact reduction aims to recover high-quality videos from low-quality compressed videos. Most existing approaches use a single Neighboring Frame or a pair of Neighboring Frames (preceding and/or following the target Frame) for this task. Furthermore, as Frames of high quality overall may contain low-quality patches, and high-quality patches may exist in Frames of low quality overall, current methods focusing on nearby peak-quality Frames (PQFs) may miss high-quality details in low-quality Frames. To remedy these shortcomings, in this paper we propose a novel end-to-end deep neural network called non-local ConvLSTM (NL-ConvLSTM in short) that exploits multiple consecutive Frames. An approximate non-local strategy is introduced in NL-ConvLSTM to capture global motion patterns and trace the spatiotemporal dependency in a video sequence. This approximate strategy makes the non-local module work in a fast and low space-cost way. Our method uses the preceding and following Frames of the target Frame to generate a residual, from which a higher quality Frame is reconstructed. Experiments on two datasets show that NL-ConvLSTM outperforms the existing methods.
-
Non-Local ConvLSTM for Video Compression Artifact Reduction
2019 IEEE CVF International Conference on Computer Vision (ICCV), 2019Co-Authors: Yi Xu, Kai Tian, Shuigeng ZhouAbstract:Video compression artifact reduction aims to recover high-quality videos from low-quality compressed videos. Most existing approaches use a single Neighboring Frame or a pair of Neighboring Frames (preceding and/or following the target Frame) for this task. Furthermore, as Frames of high quality overall may contain low-quality patches, and high-quality patches may exist in Frames of low quality overall, current methods focusing on nearby peak-quality Frames (PQFs) may miss high-quality details in low-quality Frames. To remedy these shortcomings, in this paper we propose a novel end-to-end deep neural network called non-local ConvLSTM (NL-ConvLSTM in short) that exploits multiple consecutive Frames. An approximate non-local strategy is introduced in NL-ConvLSTM to capture global motion patterns and trace the spatiotemporal dependency in a video sequence. This approximate strategy makes the non-local module work in a fast and low space-cost way. Our method uses the preceding and following Frames of the target Frame to generate a residual, from which a higher quality Frame is reconstructed. Experiments on two datasets show that NL-ConvLSTM outperforms the existing methods.
Kishore Reddy - One of the best experts on this subject based on the ideXlab platform.
-
Generative Adversarial Networks for Depth Map Estimation from RGB Video
2018 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018Co-Authors: Kin Gwn Lore, Kishore Reddy, Michael Giering, Edgar A. BernalAbstract:Depth cues are essential to achieving high-level scene understanding, and in particular to determining geometric relations between objects. The ability to reason about depth information in scene analysis tasks can often result in improved decision-making capabilities. Unfortunately, depth-capable sensors are not as ubiquitous as traditional RGB cameras, which limits the availability of depth-related cues. In this work, we investigate data-driven approaches for depth estimation from images or videos captured with monocular cameras. We propose three different approaches and demonstrate their efficacy through extensive experimental validation. The proposed methods rely on processing of (i) a single 3-channel RGB image Frame, (ii) a sequence of RGB Frames, and (iii) a single RGB Frame plus the optical flow field computed between the Frame and a Neighboring Frame in the video stream, and map the respective inputs to an estimated depth map representation. In contrast to existing literature, the input-output mapping is not directly regressed; rather, it is learned through adversarial techniques that leverage conditional generative adversarial networks (cGANs).
