3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining

• URL: http://arxiv.org/abs/2304.06911v2
• Date: Sun, 28 Apr 2024 18:36:19 GMT
• Title: 3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
• Authors: Siming Yan, Yuqi Yang, Yuxiao Guo, Hao Pan, Peng-shuai Wang, Xin Tong, Yang Liu, Qixing Huang,
• Abstract summary: Masked autoencoders (MAEs) have recently been introduced to 3D self-supervised pretraining for point clouds. We propose to ignore point position reconstruction and recover high-order features at masked points through a novel attention-based decoder. We validate our pretext task and decoder design using different encoder structures for 3D training and demonstrate the advantages of our pretrained networks on various point cloud analysis tasks.
• Score: 45.58631796379208
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore features at the masked pixels, such as colors, the existing 3D MAE works reconstruct the missing geometry only, i.e, the location of the masked points. In contrast to previous studies, we advocate that point location recovery is inessential and restoring intrinsic point features is much superior. To this end, we propose to ignore point position reconstruction and recover high-order features at masked points including surface normals and surface variations, through a novel attention-based decoder which is independent of the encoder design. We validate the effectiveness of our pretext task and decoder design using different encoder structures for 3D training and demonstrate the advantages of our pretrained networks on various point cloud analysis tasks.

Related papers

• MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysis [1.19658449368018]
  This paper develops, for the first time, a rotation-invariant self-supervised pretraining framework for practical 3D point set analysis. The proposed algorithm, called MaskLRF, learns rotation-invariant and highly generalizable latent features via masked autoencoding of 3D points. I confirm that MaskLRF achieves new state-of-the-art accuracies in analyzing 3D point sets having inconsistent orientations.
  arXiv  Detail & Related papers  (2024-03-01T00:42:49Z)
• Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding [106.0876425365599]
  Masked Shape Prediction (MSP) is a new framework to conduct masked signal modeling in 3D scenes. MSP uses the essential 3D semantic cue, i.e., geometric shape, as the prediction target for masked points.
  arXiv  Detail & Related papers  (2023-05-08T20:09:19Z)
• Ponder: Point Cloud Pre-training via Neural Rendering [93.34522605321514]
  We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural encoders. The learned point-cloud can be easily integrated into various downstream tasks, including not only high-level rendering tasks like 3D detection and segmentation, but low-level tasks like 3D reconstruction and image rendering.
  arXiv  Detail & Related papers  (2022-12-31T08:58:39Z)
• MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds [13.426810473131642]
  Masked AutoEncoder for LiDAR point clouds (MAELi) intuitively leverages the sparsity of LiDAR point clouds in both the encoder and decoder during reconstruction. In a novel reconstruction approach, MAELi distinguishes between empty and occluded space. Thereby, without any ground truth whatsoever and trained on single frames only, MAELi obtains an understanding of the underlying 3D scene geometry and semantics.
  arXiv  Detail & Related papers  (2022-12-14T13:10:27Z)
• Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training [56.81809311892475]
  Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for language and 2D image transformers. We propose Point-M2AE, a strong Multi-scale MAE pre-training framework for hierarchical self-supervised learning of 3D point clouds.
  arXiv  Detail & Related papers  (2022-05-28T11:22:53Z)
• Self-Supervised Point Cloud Representation Learning with Occlusion Auto-Encoder [63.77257588569852]
  We present 3D Occlusion Auto-Encoder (3D-OAE) for learning representations for point clouds. Our key idea is to randomly occlude some local patches of the input point cloud and establish the supervision via recovering the occluded patches. In contrast with previous methods, our 3D-OAE can remove a large proportion of patches and predict them only with a small number of visible patches.
  arXiv  Detail & Related papers  (2022-03-26T14:06:29Z)
• Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning [39.521374237630766]
  The most popular and accessible 3D representation, i.e., point clouds, involves discrete samples of the underlying continuous 3D surface. This discretization process introduces sampling variations on the 3D shape, making it challenging to develop transferable knowledge of the true 3D geometry. In the standard autoencoding paradigm, the encoder is compelled to encode not only the 3D geometry but also information on the specific discrete sampling of the 3D shape into the latent code. This is because the point cloud reconstructed by the decoder is considered unacceptable unless there is a perfect mapping between the original and the reconstructed
  arXiv  Detail & Related papers  (2022-01-03T18:05:52Z)
• Deep Point Cloud Reconstruction [74.694733918351]
  Point cloud obtained from 3D scanning is often sparse, noisy, and irregular. To cope with these issues, recent studies have been separately conducted to densify, denoise, and complete inaccurate point cloud. We propose a deep point cloud reconstruction network consisting of two stages: 1) a 3D sparse stacked-hourglass network as for the initial densification and denoising, 2) a refinement via transformers converting the discrete voxels into 3D points.
  arXiv  Detail & Related papers  (2021-11-23T07:53:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.