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

by   Ahmed Hatem, et al.

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.


page 1

page 3

page 5

page 6


Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learning

We present Point-TTA, a novel test-time adaptation framework for point c...

MATE: Masked Autoencoders are Online 3D Test-Time Learners

We propose MATE, the first Test-Time-Training (TTT) method designed for ...

Effective Utilisation of Multiple Open-Source Datasets to Improve Generalisation Performance of Point Cloud Segmentation Models

Semantic segmentation of aerial point cloud data can be utilised to diff...

AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration

In the current deep learning paradigm, the amount and quality of trainin...

Meta-Auxiliary Learning for Adaptive Human Pose Prediction

Predicting high-fidelity future human poses, from a historically observe...

Orderly Disorder in Point Cloud Domain

In the real world, out-of-distribution samples, noise and distortions ex...

Meta-Registration: Learning Test-Time Optimization for Single-Pair Image Registration

Neural networks have been proposed for medical image registration by lea...

Please sign up or login with your details

Forgot password? Click here to reset