Related papers: SupeRGB-D: Zero-shot Instance Segmentation in Clut…
Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes. Existing approaches predominantly focus on learning the proper mapping function for…
Segmentation of unseen industrial parts is essential for autonomous industrial systems. However, industrial components are texture-less, reflective, and often found in cluttered and unstructured environments with heavy occlusion, which…
We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pixels. Capturing both…
We present a novel end-to-end single-shot method that segments countable object instances (things) as well as background regions (stuff) into a non-overlapping panoptic segmentation at almost video frame rate. Current state-of-the-art…
Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…
Robotic grasping is a cornerstone capability of embodied systems. Many methods directly output grasps from partial information without modeling the geometry of the scene, leading to suboptimal motion and even collisions. To address these…
Human beings not only have the ability to recognize novel unseen classes, but also can incrementally incorporate the new classes to existing knowledge preserved. However, zero-shot learning models assume that all seen classes should be…
The ability to segment unknown objects in depth images has potential to enhance robot skills in grasping and object tracking. Recent computer vision research has demonstrated that Mask R-CNN can be trained to segment specific categories of…
This paper presents a new multi-view RGB-D dataset of nine kitchen scenes, each containing several objects in realistic cluttered environments including a subset of objects from the BigBird dataset. The viewpoints of the scenes are densely…
Online object segmentation and tracking in Lidar point clouds enables autonomous agents to understand their surroundings and make safe decisions. Unfortunately, manual annotations for these tasks are prohibitively costly. We tackle this…
Developing robot perception systems for recognizing objects in the real-world requires computer vision algorithms to be carefully scrutinized with respect to the expected operating domain. This demands large quantities of ground truth data…
Both indoor and outdoor scene perceptions are essential for embodied intelligence. However, current sparse supervised 3D object detection methods focus solely on outdoor scenes without considering indoor settings. To this end, we propose a…
In this paper, we introduce a new task: Zero-Shot 3D Reasoning Segmentation for parts searching and localization for objects, which is a new paradigm to 3D segmentation that transcends limitations for previous category-specific 3D semantic…
Independently exploring unknown spaces or finding objects in an indoor environment is a daily but challenging task for visually impaired people. However, common 2D assistive systems lack depth relationships between various objects,…
Automated sorting is crucial for improving the efficiency and scalability of textile recycling, but accurately identifying material composition and detecting contaminants from sensor data remains challenging. This paper investigates the use…
Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple, yet effective framework (NIDS-Net) comprising object proposal…
Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which…
Despite significant advancements, segmentation based on deep neural networks in medical and surgical imaging faces several challenges, two of which we aim to address in this work. First, acquiring complete pixel-level segmentation labels…
Early-stage visual quality inspection is vital for achieving Zero-Defect Manufacturing and minimizing production waste in modern industrial environments. However, the complexity of robust visual inspection systems and their extensive data…
An autonomous system's perception engine must provide an accurate understanding of the environment for it to make decisions. Deep learning based object detection networks experience degradation in the performance and robustness for small…