PlaneRCNN: 3D plane detection and reconstruction from a single image. Liu, C., Kim, K., Gu, J., Furukawa, Y., & Kautz, J. arXiv, 2018.
abstract   bibtex   
This paper proposes a deep neural architecture, PlaneRCNN, that detects and reconstructs piecewise planar surfaces from a single RGB image. PlaneRCNN employs a variant of Mask R-CNN to detect planes with their plane parameters and segmentation masks. PlaneRCNN then jointly refines all the segmentation masks with a novel loss enforcing the consistency with a nearby view during training. The paper also presents a new benchmark with more fine-grained plane segmentations in the ground-truth, in which, PlaneRCNN outperforms existing state-of-the-art methods with significant margins in the plane detection, segmentation, and reconstruction metrics. PlaneRCNN makes an important step towards robust plane extraction, which would have an immediate impact on a wide range of applications including Robotics, Augmented Reality, and Virtual Reality.
@article{
 title = {PlaneRCNN: 3D plane detection and reconstruction from a single image},
 type = {article},
 year = {2018},
 pages = {4450-4459},
 id = {6bf3e100-eb62-3208-a456-1079b34d1deb},
 created = {2020-12-10T09:42:26.395Z},
 file_attached = {true},
 profile_id = {f3d36c73-062b-3738-9a74-d09e4e83eb1e},
 group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
 last_modified = {2020-12-11T06:48:57.761Z},
 read = {true},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 folder_uuids = {2a0475f2-facb-4360-917f-00c5f8541f47},
 private_publication = {false},
 abstract = {This paper proposes a deep neural architecture, PlaneRCNN, that detects and reconstructs piecewise planar surfaces from a single RGB image. PlaneRCNN employs a variant of Mask R-CNN to detect planes with their plane parameters and segmentation masks. PlaneRCNN then jointly refines all the segmentation masks with a novel loss enforcing the consistency with a nearby view during training. The paper also presents a new benchmark with more fine-grained plane segmentations in the ground-truth, in which, PlaneRCNN outperforms existing state-of-the-art methods with significant margins in the plane detection, segmentation, and reconstruction metrics. PlaneRCNN makes an important step towards robust plane extraction, which would have an immediate impact on a wide range of applications including Robotics, Augmented Reality, and Virtual Reality.},
 bibtype = {article},
 author = {Liu, Chen and Kim, Kihwan and Gu, Jinwei and Furukawa, Yasutaka and Kautz, Jan},
 journal = {arXiv}
}

Downloads: 0