Self-Supervised Point Cloud Completion via Inpainting
When navigating in urban environments, many of the objects that need to be tracked and avoided are heavily occluded. Planning and tracking using these partial scans can be challenging. The aim of this work is to learn to complete these partial point clouds, giving us a full understanding of the object's geometry using only partial observations. Previous methods achieve this with the help of complete, ground-truth annotations of the target objects, which are available only for simulated datasets. However, such ground truth is unavailable for real-world LiDAR data. In this work, we present a self-supervised point cloud completion algorithm, PointPnCNet, which is trained only on partial scans without assuming access to complete, ground-truth annotations. Our method achieves this via inpainting. We remove a portion of the input data and train the network to complete the missing region. As it is difficult to determine which regions were occluded in the initial cloud and which were synthetically removed, our network learns to complete the full cloud, including the missing regions in the initial partial cloud. We show that our method outperforms previous unsupervised and weakly-supervised methods on both the synthetic dataset, ShapeNet, and real-world LiDAR dataset, Semantic KITTI.
Code (1)
Tasks
Point Cloud CompletionSimilar Papers 제목 키워드 기반
Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration
Point cloud completion helps restore partial incomplete point clouds suffering occlusions. Current self-supervised methods fail to give high fidelity completion for large objects with missing surfaces and unbalanced …
Point Cloud CompletionSelf-Supervised Point Cloud Completion based on Multi-View Augmentations of Single Partial Point Cloud
Point cloud completion aims to reconstruct complete shapes from partial observations. Although current methods have achieved remarkable performance, they still have some limitations: Supervised methods heavily rely on gr…
Point Cloud CompletionPoint CloudsACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion
Point cloud completion addresses filling in the missing parts of a partial point cloud obtained from depth sensors and generating a complete point cloud. Although there has been steep progress in the supervised methods o…
Point Cloud CompletionSelf-Supervised LearningReconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion
Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important. However, most existing completion methods rely on large paired datasets for training, …
Point Cloud CompletionPoint Cloud Scene Completion with Joint Color and Semantic Estimation from Single RGB-D Image
We present a deep reinforcement learning method of progressive view inpainting for colored semantic point cloud scene completion under volume guidance, achieving high-quality scene reconstruction from only a single RGB-D…
Deep Reinforcement LearningImage InpaintingSegmentationSemantic Segmentation