Related papers: RISA-Net: Rotation-Invariant Structure-Aware Netwo…

Dense 3D shape correspondence remains a central challenge in computer vision and graphics as many deep learning approaches still rely on intermediate geometric features or handcrafted descriptors, limiting their effectiveness under…

Rotation-invariant recognition of shapes is a common challenge in computer vision. Recent approaches have significantly improved the accuracy of rotation-invariant recognition by encoding the rotational invariance of shapes as hand-crafted…

Fine-grained 3D shape classification is important for shape understanding and analysis, which poses a challenging research problem. However, the studies on the fine-grained 3D shape classification have rarely been explored, due to the lack…

Understanding and extracting 3D information of objects from monocular 2D images is a fundamental problem in computer vision. In the task of 3D object pose estimation, recent data driven deep neural network based approaches suffer from…

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down…

Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations,…

Recently researchers have been shifting their focus towards learned 3D shape descriptors from hand-craft ones to better address challenging issues of the deformation and structural variation inherently present in 3D objects. 3D geometric…

3D shape is a crucial but heavily underutilized cue in today's computer vision systems, mostly due to the lack of a good generic shape representation. With the recent availability of inexpensive 2.5D depth sensors (e.g. Microsoft Kinect),…

Despite the progress on 3D point cloud deep learning, most prior works focus on learning features that are invariant to translation and point permutation, and very limited efforts have been devoted for rotation invariant property. Several…

We propose a data-driven method for recovering miss-ing parts of 3D shapes. Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement…

3D reconstruction from a single view image is a long-standing prob-lem in computer vision. Various methods based on different shape representations(such as point cloud or volumetric representations) have been proposed. However,the 3D shape…

Reconstructing 3D shapes from single-view images has been a long-standing research problem. In this paper, we present DISN, a Deep Implicit Surface Network which can generate a high-quality detail-rich 3D mesh from an 2D image by predicting…

3D image reconstruction from a limited number of 2D images has been a long-standing challenge in computer vision and image analysis. While deep learning-based approaches have achieved impressive performance in this area, existing deep…

D shape generation is a fundamental operation in computer graphics. While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric…

We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is able to predict both…

This paper presents a novel appearance and shape feature, RISAS, which is robust to viewpoint, illumination, scale and rotation variations. RISAS consists of a keypoint detector and a feature descriptor both of which utilise texture and…

Grasp synthesis is one of the challenging tasks for any robot object manipulation task. In this paper, we present a new deep learning-based grasp synthesis approach for 3D objects. In particular, we propose an end-to-end 3D Convolutional…

Traditional computer graphics rendering pipeline is designed for procedurally generating 2D quality images from 3D shapes with high performance. The non-differentiability due to discrete operations such as visibility computation makes it…

We present the first single-view 3D reconstruction network aimed at recovering geometric details from an input image which encompass both topological shape structures and surface features. Our key idea is to train the network to learn a…

We present RoarNet, a new approach for 3D object detection from a 2D image and 3D Lidar point clouds. Based on two-stage object detection framework with PointNet as our backbone network, we suggest several novel ideas to improve 3D object…