Related papers: Unsupervised Learning of 3D Semantic Keypoints wit…
Semantic segmentation of point clouds usually requires exhausting efforts of human annotations, hence it attracts wide attention to the challenging topic of learning from unlabeled or weaker forms of annotations. In this paper, we take the…
Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. Moreover, there is…
Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…
Semantic understanding of 3D point clouds is important for various robotics applications. Given that point-wise semantic annotation is expensive, in this paper, we address the challenge of learning models with extremely sparse labels. The…
Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large…
In perception, multiple sensory information is integrated to map visual information from 2D views onto 3D objects, which is beneficial for understanding in 3D environments. But in terms of a single 2D view rendered from different angles,…
Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods. However, data augmentation is not ideal as it requires a careful selection of the type of…
Self-supervised 3D representation learning aims to learn effective representations from large-scale unlabeled point clouds. Most existing approaches adopt point discrimination as the pretext task, which assigns matched points in two…
In this paper, we propose a method for keypoint discovery from a 2D image using image-level supervision. Recent works on unsupervised keypoint discovery reliably discover keypoints of aligned instances. However, when the target instances…
Learning sensorimotor control policies from high-dimensional images crucially relies on the quality of the underlying visual representations. Prior works show that structured latent space such as visual keypoints often outperforms…
This paper proposes a new method to infer keypoints from arbitrary object categories in practical scenarios where point cloud data (PCD) are noisy, down-sampled and arbitrarily rotated. Our proposed model adheres to the following…
Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…
3D anomaly detection targets the detection and localization of defects in 3D point clouds trained solely on normal data. While a unified model improves scalability by learning across multiple categories, it often suffers from Inter-Category…
We propose a new fast fully unsupervised method to discover semantic patterns. Our algorithm is able to hierarchically find visual categories and produce a segmentation mask where previous methods fail. Through the modeling of what is a…
This paper proposes a novel paradigm for the unsupervised learning of object landmark detectors. Contrary to existing methods that build on auxiliary tasks such as image generation or equivariance, we propose a self-training approach where,…
While deep learning-based methods have demonstrated outstanding results in numerous domains, some important functionalities are missing. Resolution scalability is one of them. In this work, we introduce a novel architecture, dubbed…
A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or…
Understanding point clouds is of great importance. Many previous methods focus on detecting salient keypoints to identity structures of point clouds. However, existing methods neglect the semantics of points selected, leading to poor…
For the semantic segmentation of images, state-of-the-art deep neural networks (DNNs) achieve high segmentation accuracy if that task is restricted to a closed set of classes. However, as of now DNNs have limited ability to operate in an…
Various 3D semantic attributes such as segmentation masks, geometric features, keypoints, and materials can be encoded as per-point probe functions on 3D geometries. Given a collection of related 3D shapes, we consider how to jointly…