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

by   Jie Wang, et al.

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.


page 1

page 2

page 3

page 4


Point Cloud Augmentation with Weighted Local Transformations

Despite the extensive usage of point clouds in 3D vision, relatively lim...

Convex Relaxations for Isometric and Equiareal NRSfM

Extensible objects form a challenging case for NRSfM, owing to the lack ...

Regularization Strategy for Point Cloud via Rigidly Mixed Sample

Data augmentation is an effective regularization strategy to alleviate t...

Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion

Given the prominence of current 3D sensors, a fine-grained analysis on t...

Part-Aware Data Augmentation for 3D Object Detection in Point Cloud

Data augmentation has greatly contributed to improving the performance i...

Fast Point Cloud Generation with Straight Flows

Diffusion models have emerged as a powerful tool for point cloud generat...

Please sign up or login with your details

Forgot password? Click here to reset