Cascaded Refinement Network for Point Cloud Completion with Self-supervision
This work addresses the challenge of incomplete and sparse point clouds for real-world applications like robotics and 3D modeling, offering a novel self-supervised approach that reduces reliance on ground truth data.
The paper tackles the problem of generating fine-grained details in point cloud completion by introducing a two-branch network with a cascaded shape completion sub-network and an auto-encoder, achieving superior performances in self-supervised, semi-supervised, and fully supervised settings with more realistic outputs than state-of-the-art methods.
Point clouds are often sparse and incomplete, which imposes difficulties for real-world applications. Existing shape completion methods tend to generate rough shapes without fine-grained details. Considering this, we introduce a two-branch network for shape completion. The first branch is a cascaded shape completion sub-network to synthesize complete objects, where we propose to use the partial input together with the coarse output to preserve the object details during the dense point reconstruction. The second branch is an auto-encoder to reconstruct the original partial input. The two branches share a same feature extractor to learn an accurate global feature for shape completion. Furthermore, we propose two strategies to enable the training of our network when ground truth data are not available. This is to mitigate the dependence of existing approaches on large amounts of ground truth training data that are often difficult to obtain in real-world applications. Additionally, our proposed strategies are also able to improve the reconstruction quality for fully supervised learning. We verify our approach in self-supervised, semi-supervised and fully supervised settings with superior performances. Quantitative and qualitative results on different datasets demonstrate that our method achieves more realistic outputs than state-of-the-art approaches on the point cloud completion task.