Completion Consistency for Point Cloud Completion Enhancement
Primary Area: representation learning for computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: point cloud completion
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: A new loss function for point cloud completion that can be easily integrated into existing networks.
Abstract: Point cloud completion networks are conventionally trained to minimize the disparities between the completed point cloud and the ground-truth counterpart. However, an incomplete object-level point cloud can have multiple valid completion solutions when it is examined in isolation. This one-to-many mapping issue can cause contradictory supervision signals to the network, because the loss function may produce various values for identical input-output pairs of the network. And in many cases, this issue could adversely impact the network optimization process. In this work, we propose to enhance the conventional learning objective using a novel completion consistency loss to mitigate the one-to-many mapping problem. Specifically, the proposed consistency loss imposes a constraint to ensure that a point cloud completion network generates a consistent completion solution for incomplete objects originating from the same source point cloud. Experimental results across multiple well-established datasets and benchmarks demonstrate the excellent capability of the proposed completion consistency loss to enhance the completion performance of various existing networks without any modification to the design of the networks.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 2420
Loading