More Like this

1. Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering with Graph Convolutional Neural Network

   Zhang, Ling; Zhu, Zhigang (June 2019, CVPR Workshop on 3D Scene Understanding for Vision, Graphics, and Robotics)

   To alleviate the cost of collecting and annotating large- scale point cloud datasets for 3D scene understanding tasks, we propose an unsupervised learning approach to learn features from unlabeled point cloud ”3D object” dataset by using part contrasting and object clustering with deep graph neural networks (GNNs). In the contrast learn- ing step, all the samples in the 3D object dataset are cut into two parts and put into a ”part” dataset. Then a contrast learning GNN (ContrastNet) is trained to verify whether two randomly sampled parts from the part dataset belong to the same object. In the cluster learning step, the trained ContrastNet is applied to all the samples in the original 3D object dataset to extract features, which are used to group the samples into clusters. Then another GNN for cluster- ing learning (ClusterNet) is trained to predict the cluster IDs of all the training samples. The contrasting learning forces the ContrastNet to learn high-level semantic features of objects but probably ignores low-level features, while the ClusterNet improves the quality of learned features by be- ing trained to discover objects that belong to the same se- mantic categories by using cluster IDs. We have conducted extensive experiments to evaluate the proposed framework on point cloud classification tasks. The proposed unsupervised learning approach obtained comparable performance to the state-of-the-art unsupervised learning methods that used much more complicated network structures. The code and an extended version of this work is publicly available via: https://github.com/lingzhang1/ContrastNet 

   more » « less
2. Self-supervised Feature Learning by Cross-modality and Cross-view Correspondences

   Jing, L; Zhang, L; Tian, Y (June 2021, The 4th Multimodal Learning and Applications (MULA) Workshop in conjunction with CVPR 2021)

   null (Ed.)

   The success of supervised learning requires large-scale ground truth labels which are very expensive, time- consuming, or may need special skills to annotate. To address this issue, many self- or un-supervised methods are developed. Unlike most existing self-supervised methods to learn only 2D image features or only 3D point cloud features, this paper presents a novel and effective self-supervised learning approach to jointly learn both 2D image features and 3D point cloud features by exploiting cross-modality and cross-view correspondences without using any human annotated labels. Specifically, 2D image features of rendered images from different views are extracted by a 2D convolutional neural network, and 3D point cloud features are extracted by a graph convolution neural network. Two types of features are fed into a two-layer fully connected neural network to estimate the cross-modality correspondence. The three networks are jointly trained (i.e. cross-modality) by verifying whether two sampled data of different modalities belong to the same object, meanwhile, the 2D convolutional neural network is additionally optimized through minimizing intra-object distance while maximizing inter-object distance of rendered images in different views (i.e. cross-view). The effectiveness of the learned 2D and 3D features is evaluated by transferring them on five different tasks including multi-view 2D shape recognition, 3D shape recognition, multi-view 2D shape retrieval, 3D shape retrieval, and 3D part-segmentation. Extensive evaluations on all the five different tasks across different datasets demonstrate strong generalization and effectiveness of the learned 2D and 3D features by the proposed self-supervised method. 

   more » « less
3. A Snapshot-based Approach for Self-supervised Feature Learning and Weakly-supervised Classification on Point Cloud Data

   https://doi.org/10.5220/0010230103990408  

   Li, Xingye; Zhu, Zhigang (January 2021, VISAPP 2021, the 16th International Conference on Computer Vision Theory and Applications)

   null (Ed.)

   Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, we propose a snapshot-based self-supervised method to enable direct feature learning on the unlabeled point cloud of a complex 3D scene. A snapshot is defined as a collection of points sampled from the point cloud scene. It could be a real view of a local 3D scan directly captured from the real scene, or a virtual view of such from a large 3D point cloud dataset. First the snapshots go through a self-supervised pipeline including both part contrasting and snapshot clustering for feature learning. Then a weakly-supervised approach is implemented by training a standard SVM classifier on the learned features with a small fraction of labeled data. We evaluate the weakly-supervised approach for point cloud classification by using varying numbers of labeled data and study the minimal numbers of labeled data for a successful classification. Experiments are conducted on three public point cloud datasets, and the results have shown that our method is capable of learning effective features from the complex scene data without any labels. 

   more » « less
4. Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views

   https://doi.org/10.24963/ijcai.2019/108  

   Han, Zhizhong; Liu, Xinhai; Liu, Yu-Shen; Zwicker, Matthias (August 2019, Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI 2019))

   Deep learning has achieved remarkable results in 3D shape analysis by learning global shape features from the pixel-level over multiple views. Previous methods, however, compute low-level features for entire views without considering part-level information. In contrast, we propose a deep neural network, called Parts4Feature, to learn 3D global features from part-level information in multiple views. We introduce a novel definition of generally semantic parts, which Parts4Feature learns to detect in multiple views from different 3D shape segmentation benchmarks. A key idea of our architecture is that it transfers the ability to detect semantically meaningful parts in multiple views to learn 3D global features. Parts4Feature achieves this by combining a local part detection branch and a global feature learning branch with a shared region proposal module. The global feature learning branch aggregates the detected parts in terms of learned part patterns with a novel multi-attention mechanism, while the region proposal module enables locally and globally discriminative information to be promoted by each other. We demonstrate that Parts4Feature outperforms the state-of-the-art under three large-scale 3D shape benchmarks. 

   more » « less
5. LocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot grasping

   Vijayaraghavan, Sujal; Alqasemi, Redwan; Dubey, Rajiv; Sarkar, Sudeep (October 2022, European Conference on Computer Vision)

   Robot grasp typically follows five stages: object detection, object localisation, object pose estimation, grasp pose estimation, and grasp planning. We focus on object pose estimation. Our approach relies on three pieces of information: multiple views of the object, the camera’s extrinsic parameters at those viewpoints, and 3D CAD models of objects. The first step involves a standard deep learning backbone (FCN ResNet) to estimate the object label, semantic segmentation, and a coarse estimate of the object pose with respect to the camera. Our novelty is using a refinement module that starts from the coarse pose estimate and refines it by optimisation through differentiable rendering. This is a purely vision-based approach that avoids the need for other information such as point cloud or depth images. We evaluate our object pose estimation approach on the ShapeNet dataset and show improvements over the state of the art. We also show that the estimated object pose results in 99.65% grasp accuracy with the ground truth grasp candidates on the Object Clutter Indoor Dataset (OCID) Grasp dataset, as computed using standard practice. 

   more » « less