Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions

TL;DR

This paper introduces AdaptPoint, an auto-augmentation framework that adaptively transforms point clouds based on their structure to improve robustness against real-world corruptions, achieving state-of-the-art results.

Contribution

We propose a novel sample-adaptive augmentation method for point cloud recognition that leverages structural information and a discriminator to simulate realistic corruptions.

Findings

Achieves state-of-the-art performance on multiple corruption benchmarks.

Introduces a new real-world corrupted dataset, ScanObjectNN-C.

Effectively enhances robustness of 3D perception models against corruptions.

Abstract

Robust 3D perception under corruption has become an essential task for the realm of 3D vision. While current data augmentation techniques usually perform random transformations on all point cloud objects in an offline way and ignore the structure of the samples, resulting in over-or-under enhancement. In this work, we propose an alternative to make sample-adaptive transformations based on the structure of the sample to cope with potential corruption via an auto-augmentation framework, named as AdaptPoint. Specially, we leverage a imitator, consisting of a Deformation Controller and a Mask Controller, respectively in charge of predicting deformation parameters and producing a per-point mask, based on the intrinsic structural information of the input point cloud, and then conduct corruption simulations on top. Then a discriminator is utilized to prevent the generation of excessive corruption that deviates from the original data distribution. In addition, a perception-guidance feedback mechanism is incorporated to guide the generation of samples with appropriate difficulty level. Furthermore, to address the paucity of real-world corrupted point cloud, we also introduce a new dataset ScanObjectNN-C, that exhibits greater similarity to actual data in real-world environments, especially when contrasted with preceding CAD datasets. Experiments show that our method achieves state-of-the-art results on multiple corruption benchmarks, including ModelNet-C, our ScanObjectNN-C, and ShapeNet-C.