2
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image

      Preprint

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          We present a deep reinforcement learning method of progressive view inpainting for 3D point scene completion under volume guidance, achieving high-quality scene reconstruction from only a single depth image with severe occlusion. Our approach is end-to-end, consisting of three modules: 3D scene volume reconstruction, 2D depth map inpainting, and multi-view selection for completion. Given a single depth image, our method first goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view depth, and integrating all depth into the point cloud. Since the occluded areas are unavailable, we resort to a deep Q-Network to glance around and pick the next best view for large hole completion progressively until a scene is adequately reconstructed while guaranteeing validity. All steps are learned jointly to achieve robust and consistent results. We perform qualitative and quantitative evaluations with extensive experiments on the SUNCG data, obtaining better results than the state of the art.

          Related collections

          Most cited references 25

          • Record: found
          • Abstract: not found
          • Article: not found

          Globally and locally consistent image completion

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            Context Encoders: Feature Learning by Inpainting

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              Semantic Scene Completion from a Single Depth Image

                Bookmark

                Author and article information

                Journal
                10 March 2019
                2019-03-11
                Article
                1903.04019

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                Custom metadata
                Accepted as CVPR 2019 Oral
                cs.CV

                Computer vision & Pattern recognition

                Comments

                Comment on this article