Related papers: Learning Canonical View Representation for 3D Shap…
Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment. However, robots often have to tackle unstructured environments and their onboard visual sensors can only…
Single-view 3D shape retrieval is a challenging task that is increasingly important with the growth of available 3D data. Prior work that has studied this task has not focused on evaluating how realistic occlusions impact performance, and…
Existing deep learning-based approaches for monocular 3D object detection in autonomous driving often model the object as a rotated 3D cuboid while the object's geometric shape has been ignored. In this work, we propose an approach for…
In view-based 3D shape recognition, extracting discriminative visual representation of 3D shapes from projected images is considered the core problem. Projections with low discriminative ability can adversely influence the final 3D shape…
We present a mathematical and algorithmic scheme for learning the principal geometric elements in an image or 3D object. We build on recent work that convexifies the basic problem of finding a combination of a small number shapes that…
This paper is about reducing the cost of building good large-scale 3D reconstructions post-hoc. We render 2D views of an existing reconstruction and train a convolutional neural network (CNN) that refines inverse-depth to match a…
In this paper, we aim to transfer CLIP's robust 2D generalization capabilities to identify 3D anomalies across unseen objects of highly diverse class semantics. To this end, we propose a unified framework to comprehensively detect and…
Humans are able to recognize objects based on both local texture cues and the configuration of object parts, yet contemporary vision models primarily harvest local texture cues, yielding brittle, non-compositional features. Work on…
It is widely accepted that reasoning about object shape is important for object recognition. However, the most powerful object recognition methods today do not explicitly make use of object shape during learning. In this work, motivated by…
We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects. Our goal is to enable information aggregation over time and the interrogation of object state…
With the proliferation of small aerial vehicles, acquiring close up aerial imagery for high quality reconstruction of complex scenes is gaining importance. We present an adaptive view planning method to collect such images in an automated…
In this paper, we revisit the classical representation of 3D point clouds as linear shape models. Our key insight is to leverage deep learning to represent a collection of shapes as affine transformations of low-dimensional linear shape…
We study the problem of novel view synthesis from sparse source observations of a scene comprised of 3D objects. We propose a simple yet effective approach that is neither continuous nor implicit, challenging recent trends on view…
We propose a novel deep reinforcement learning-based approach for 3D object reconstruction from monocular images. Prior works that use mesh representations are template based. Thus, they are limited to the reconstruction of objects that…
We introduce PlatonicGAN to discover the 3D structure of an object class from an unstructured collection of 2D images, i.e., where no relation between photos is known, except that they are showing instances of the same category. The key…
For image recognition and labeling tasks, recent results suggest that machine learning methods that rely on manually specified feature representations may be outperformed by methods that automatically derive feature representations based on…
Low-cost autonomous agents including autonomous driving vehicles chiefly adopt monocular 3D object detection to perceive surrounding environment. This paper studies 3D intermediate representation methods which generate intermediate 3D…
This paper investigates the problem of modeling Internet images and associated text or tags for tasks such as image-to-image search, tag-to-image search, and image-to-tag search (image annotation). We start with canonical correlation…
We propose a data-driven 3D shape design method that can learn a generative model from a corpus of existing designs, and use this model to produce a wide range of new designs. The approach learns an encoding of the samples in the training…
In this paper we investigate the problem of inducing a distribution over three-dimensional structures given two-dimensional views of multiple objects taken from unknown viewpoints. Our approach called "projective generative adversarial…