Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning
This paper advocates the use of implicit surface representation in autoencoder-based self-supervised 3D representation learning. 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 point clouds. This paper introduces the Implicit AutoEncoder (IAE), a simple yet effective method that addresses the sampling variation issue by replacing the commonly-used point-cloud decoder with an implicit decoder. The implicit decoder reconstructs a continuous representation of the 3D shape, independent of the imperfections in the discrete samples. Extensive experiments demonstrate that the proposed IAE achieves state-of-the-art performance across various self-supervised learning benchmarks.
Code (1)
Tasks
3D geometry3D Point Cloud Classification3D Point Cloud Linear ClassificationDecoderInductive BiasRepresentation LearningSelf-Supervised LearningSimilar Papers 제목 키워드 기반
SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds
We present SeRP, a framework for Self-Supervised Learning of 3D point clouds. SeRP consists of encoder-decoder architecture that takes perturbed or corrupted point clouds as inputs and aims to reconstruct the original po…
DecoderQuantizationRepresentation LearningSelf-Supervised LearningJoint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training
Masked Autoencoders (MAE) have shown promising performance in self-supervised learning for both 2D and 3D computer vision. However, existing MAE-style methods can only learn from the data of a single modality, i.e., eith…
DecoderPoint Cloud Pre-trainingRepresentation LearningSelf-Supervised LearningMasked Autoencoders for Point Cloud Self-supervised Learning
As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a neat scheme of masked autoencoders for poi…
3D Part Segmentation3D Point Cloud ClassificationFew-Shot 3D Point Cloud ClassificationFew-Shot Learning+1LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds
We present LBS-AE; a self-supervised autoencoding algorithm for fitting articulated mesh models to point clouds. As input, we take a sequence of point clouds to be registered as well as an artist-rigged mesh, i.e. a temp…
Masked Autoencoders in 3D Point Cloud Representation Learning
Transformer-based Self-supervised Representation Learning methods learn generic features from unlabeled datasets for providing useful network initialization parameters for downstream tasks. Recently, self-supervised lear…
Point Cloud CompletionPoint cloud reconstructionRepresentation LearningSelf-Supervised Learning