Related papers: Learning 3D Object Categories by Looking Around Th…

Visual object localization is the key step in a series of object detection tasks. In the literature, high localization accuracy is achieved with the mainstream strongly supervised frameworks. However, such methods require object-level…

In this thesis we discuss architectural designs and training methods for a neural network to have the ability of dissecting an image into objects of interest without supervision. The main challenge in 2D unsupervised object segmentation is…

We present a network architecture which compares RGB images and untextured 3D models by the similarity of the represented shape. Our system is optimised for zero-shot retrieval, meaning it can recognise shapes never shown in training. We…

We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a bird-eye view image in autonomous driving scenarios. In…

Given a single scene image, this paper proposes a method of Category-level 6D Object Pose and Size Estimation (COPSE) from the point cloud of the target object, without external real pose-annotated training data. Specifically, beyond the…

When presented with one or a few photos of a previously unseen object, humans can instantly recognize it in different scenes. Although the human brain mechanism behind this phenomenon is still not fully understood, this work introduces a…

Existing object pose estimation datasets are related to generic object types and there is so far no dataset for fine-grained object categories. In this work, we introduce a new large dataset to benchmark pose estimation for fine-grained…

Robotic manipulation systems operating in complex environments rely on perception systems that provide information about the geometry (pose and 3D shape) of the objects in the scene along with other semantic information such as object…

We propose a new method named OnePose for object pose estimation. Unlike existing instance-level or category-level methods, OnePose does not rely on CAD models and can handle objects in arbitrary categories without instance- or…

Rotation estimation of high precision from an RGB-D object observation is a huge challenge in 6D object pose estimation, due to the difficulty of learning in the non-linear space of SO(3). In this paper, we propose a novel rotation…

To date, most instance segmentation approaches are based on supervised learning that requires a considerable amount of annotated object contours as training ground truth. Here, we propose a framework that searches for the target object…

Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier. Such approaches have been…

In order to interact with the world, agents must be able to predict the results of the world's dynamics. A natural approach to learn about these dynamics is through video prediction, as cameras are ubiquitous and powerful sensors. Direct…

We introduce a new method for category-level pose estimation which produces a distribution over predicted poses by integrating 3D shape estimates from a generative object model with segmentation information. Given an input depth-image of an…

How can we extract complete geometric models of objects that we encounter in our daily life, without having access to commercial 3D scanners? In this paper we present an automated system for generating geometric models of objects from two…

By estimating 3D shape and instances from a single view, we can capture information about an environment quickly, without the need for comprehensive scanning and multi-view fusion. Solving this task for composite scenes (such as object…

Category-level articulated object pose estimation aims to estimate a hierarchy of articulation-aware object poses of an unseen articulated object from a known category. To reduce the heavy annotations needed for supervised learning methods,…

Current CNN-based algorithms for recovering the 3D pose of an object in an image assume knowledge about both the object category and its 2D localization in the image. In this paper, we relax one of these constraints and propose to solve the…

Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited. In this paper, we attempt to enrich such categories by addressing the one-shot object detection…

Actions as simple as grasping an object or navigating around it require a rich understanding of that object's 3D shape from a given viewpoint. In this paper we repurpose powerful learning machinery, originally developed for object…