Related papers: ARO-Net: Learning Implicit Fields from Anchored Ra…

Template 3D shapes are useful for many tasks in graphics and vision, including fitting observation data, analyzing shape collections, and transferring shape attributes. Because of the variety of geometry and topology of real-world shapes,…

Implicit 3D surface reconstruction of an object from its partial and noisy 3D point cloud scan is the classical geometry processing and 3D computer vision problem. In the literature, various 3D shape representations have been developed,…

Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects. We introduce FroDO, a method for accurate 3D reconstruction…

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…

Monocular 3D object parsing is highly desirable in various scenarios including occlusion reasoning and holistic scene interpretation. We present a deep convolutional neural network (CNN) architecture to localize semantic parts in 2D image…

Our world can be succinctly and compactly described as structured scenes of objects and relations. A typical room, for example, contains salient objects such as tables, chairs and books, and these objects typically relate to each other by…

Uncorrelated optical space observation association represents a classic needle in a haystack problem. The objective being to find small groups of observations that are likely of the same resident space objects (RSOs) from amongst the much…

We propose a novel shape representation useful for analyzing and processing shape collections, as well for a variety of learning and inference tasks. Unlike most approaches that capture variability in a collection by using a template model…

CodeNeRF is an implicit 3D neural representation that learns the variation of object shapes and textures across a category and can be trained, from a set of posed images, to synthesize novel views of unseen objects. Unlike the original…

Neural fields such as implicit surfaces have recently enabled avatar modeling from raw scans without explicit temporal correspondences. In this work, we exploit autoregressive modeling to further extend this notion to capture dynamic…

This paper proposes a category-level 6D object pose and shape estimation approach iCaps, which allows tracking 6D poses of unseen objects in a category and estimating their 3D shapes. We develop a category-level auto-encoder network using…

Current object detection approaches predict bounding boxes, but these provide little instance-specific information beyond location, scale and aspect ratio. In this work, we propose to directly regress to objects' shapes in addition to their…

Neural shape representation generally refers to representing 3D geometry using neural networks, e.g., computing a signed distance or occupancy value at a specific spatial position. In this paper we present a neural-network architecture…

Almost all existing amodal segmentation methods make the inferences of occluded regions by using features corresponding to the whole image. This is against the human's amodal perception, where human uses the visible part and the shape prior…

Learning node representations that incorporate information from graph structure benefits wide range of tasks on graph. The majority of existing graph neural networks (GNNs) have limited power in capturing position information for a given…

We present a method for estimating neural scenes representations of objects given only a single image. The core of our method is the estimation of a geometric scaffold for the object and its use as a guide for the reconstruction of the…

In this paper, we propose Attention Based Decomposition Network (ABD-Net), for point cloud decomposition into basic geometric shapes namely, plane, sphere, cone and cylinder. We show improved performance of 3D object classification using…

Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the strong invariance properties that are key to the success of…

In this paper, we propose a novel encoder-decoder architecture, named SABER, to learn the 6D pose of the object in the embedding space by learning shape representation at a given pose. This model enables us to learn pose by performing shape…

Amodal segmentation aims to infer the complete shape of occluded objects, even when the occluded region's appearance is unavailable. However, current amodal segmentation methods lack the capability to interact with users through text input…