相关论文: ShapeY: Measuring Shape Recognition Capacity Using…

Gaze and face tracking algorithms have traditionally battled a compromise between computational complexity and accuracy; the most accurate neural net algorithms cannot be implemented in real time, but less complex real-time algorithms…

Seemingly simple natural language requests to a robot are generally underspecified, for example "Can you bring me the wireless mouse?" Flat images of candidate mice may not provide the discriminative information needed for "wireless." The…

A major bottleneck of pedestrian detection lies on the sharp performance deterioration in the presence of small-size pedestrians that are relatively far from the camera. Motivated by the observation that pedestrians of disparate spatial…

3D human pose and shape estimation (a.k.a. "human mesh recovery") has achieved substantial progress. Researchers mainly focus on the development of novel algorithms, while less attention has been paid to other critical factors involved.…

Perceiving accurate 3D object shape is important for robots to interact with the physical world. Current research along this direction has been primarily relying on visual observations. Vision, however useful, has inherent limitations due…

Human pose estimation (HPE) is one of the most challenging tasks in computer vision as humans are deformable by nature and thus their pose has so much variance. HPE aims to correctly identify the main joint locations of a single person or…

Transparent objects present multiple distinct challenges to visual perception systems. First, their lack of distinguishing visual features makes transparent objects harder to detect and localize than opaque objects. Even humans find certain…

Deep neural networks demonstrate to have a high performance on image classification tasks while being more difficult to train. Due to the complexity and vanishing gradient problem, it normally takes a lot of time and more computational…

Image classification has become one of the main tasks in the field of computer vision technologies. In this context, a recent algorithm called CapsNet that implements an approach based on activity vectors and dynamic routing between…

Despite the importance of shape perception in human vision, early neural image classifiers relied less on shape information for object recognition than other (often spurious) features. While recent research suggests that current large…

Shapes and textures are the basic building blocks of visual perception. The ability to identify shapes regardless of orientation, texture, or context, and to recognize textures and materials independently of their associated objects, is…

This paper proposes a universal framework, called OVE6D, for model-based 6D object pose estimation from a single depth image and a target object mask. Our model is trained using purely synthetic data rendered from ShapeNet, and, unlike most…

Visual Place Recognition (VPR) is a critical task in computer vision, traditionally enhanced by re-ranking retrieval results with image matching. However, recent advancements in VPR methods have significantly improved performance,…

We propose a system that learns to detect objects and infer their 3D poses in RGB-D images. Many existing systems can identify objects and infer 3D poses, but they heavily rely on human labels and 3D annotations. The challenge here is to…

The shape of objects is an important source of visual information in a wide range of applications. One of the core challenges of shape quantification is to ensure that the extracted measurements remain invariant to transformations that…

3D reconstruction from a single RGB image is a challenging problem in computer vision. Previous methods are usually solely data-driven, which lead to inaccurate 3D shape recovery and limited generalization capability. In this work, we focus…

For robot manipulation, a complete and accurate object shape is desirable. Here, we present a method that combines visual and haptic reconstruction in a closed-loop pipeline. From an initial viewpoint, the object shape is reconstructed…

Inspired by CapsNet's routing-by-agreement mechanism with its ability to learn object properties, we explore if those properties in turn can determine new properties of the objects, such as the locations. We then propose a CapsNet…

Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification. The existing approaches for person, vehicle, or animal re-identification tasks suffer from high intra-class…

Reconstructing 3D shape and pose of static objects from a single image is an essential task for various industries, including robotics, augmented reality, and digital content creation. This can be done by directly predicting 3D shape in…