相关论文: Global-Local Bidirectional Reasoning for Unsupervi…

We are interested in reconstructing the mesh representation of object surfaces from point clouds. Surface reconstruction is a prerequisite for downstream applications such as rendering, collision avoidance for planning, animation, etc.…

In this work, we propose a novel method for generating 3D point clouds that leverage properties of hyper networks. Contrary to the existing methods that learn only the representation of a 3D object, our approach simultaneously finds a…

Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense…

Self-supervised learning can extract representations of good quality from solely unlabeled data, which is appealing for point cloud videos due to their high labelling cost. In this paper, we propose a contrastive mask prediction (PointCMP)…

Manipulating articulated objects with robotic arms is challenging due to the complex kinematic structure, which requires precise part segmentation for efficient manipulation. In this work, we introduce a novel superpoint-based perception…

Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…

Local discriminative representation is needed in many medical image analysis tasks such as identifying sub-types of lesion or segmenting detailed components of anatomical structures. However, the commonly applied supervised representation…

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and…

Anomaly detection based on 3D point cloud data is an important research problem and receives more and more attention recently. Untrained anomaly detection based on only one sample is an emerging research problem motivated by real…

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner. However, very few explore geometric properties revealing…

Self-supervised methods have been proven effective for learning deep representations of 3D point cloud data. Although recent methods in this domain often rely on random masking of inputs, the results of this approach can be improved. We…

Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data,…

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks,…

Robots have the capability to collect large amounts of data autonomously by interacting with objects in the world. However, it is often not obvious \emph{how} to learning from autonomously collected data without human-labeled supervision.…

Existing point cloud representation learning methods primarily rely on data-driven strategies to extract geometric information from large amounts of scattered data. However, most methods focus solely on the spatial distribution features of…

We learn a self-supervised, single-view 3D reconstruction model that predicts the 3D mesh shape, texture and camera pose of a target object with a collection of 2D images and silhouettes. The proposed method does not necessitate 3D…

We propose a generative model of unordered point sets, such as point clouds, in the form of an energy-based model, where the energy function is parameterized by an input-permutation-invariant bottom-up neural network. The energy function…

In this paper, we question whether we have a reliable self-supervised point cloud model that can be used for diverse 3D tasks via simple linear probing, even with limited data and minimal computation. We find that existing 3D…

Point cloud completion aims to recover the complete shape based on a partial observation. Existing methods require either complete point clouds or multiple partial observations of the same object for learning. In contrast to previous…

This work proposes a self-supervised learning system for segmenting rigid objects in RGB images. The proposed pipeline is trained on unlabeled RGB-D videos of static objects, which can be captured with a camera carried by a mobile robot. A…