Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learning

TL;DR

This paper introduces a meta-learning based test-time adaptation method for point cloud upsampling, significantly improving model generality and performance on unseen data distributions without prior test data information.

Contribution

It proposes a novel meta-learning framework enabling point cloud upsampling models to adapt at test time, enhancing robustness across different data distributions.

Findings

Improves state-of-the-art upsampling performance on diverse datasets.

Enables models to adapt quickly with few gradient updates.

Does not require prior knowledge of test data.

Abstract

Affordable 3D scanners often produce sparse and non-uniform point clouds that negatively impact downstream applications in robotic systems. While existing point cloud upsampling architectures have demonstrated promising results on standard benchmarks, they tend to experience significant performance drops when the test data have different distributions from the training data. To address this issue, this paper proposes a test-time adaption approach to enhance model generality of point cloud upsampling. The proposed approach leverages meta-learning to explicitly learn network parameters for test-time adaption. Our method does not require any prior information about the test data. During meta-training, the model parameters are learned from a collection of instance-level tasks, each of which consists of a sparse-dense pair of point clouds from the training data. During meta-testing, the trained model is fine-tuned with a few gradient updates to produce a unique set of network parameters for each test instance. The updated model is then used for the final prediction. Our framework is generic and can be applied in a plug-and-play manner with existing backbone networks in point cloud upsampling. Extensive experiments demonstrate that our approach improves the performance of state-of-the-art models.