Related papers: SORNet: Spatial Object-Centric Representations for…
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…
Algorithms based on deep network models are being used for many pattern recognition and decision-making tasks in robotics and AI. Training these models requires a large labeled dataset and considerable computational resources, which are not…
We tackle the task of scalable unsupervised object-centric representation learning on 3D scenes. Existing approaches to object-centric representation learning show limitations in generalizing to larger scenes as their learning processes…
Geometry-aware modules are widely applied in recent deep learning architectures for scene representation and rendering. However, these modules require intrinsic camera information that might not be obtained accurately. In this paper, we…
Surgical robotics holds much promise for improving patient safety and clinician experience in the Operating Room (OR). However, it also comes with new challenges, requiring strong team coordination and effective OR management. Automatic…
Robot planning in partially observable domains is difficult, because a robot needs to estimate the current state and plan actions at the same time. When the domain includes many objects, reasoning about the objects and their relationships…
The ability for robots to comprehend and execute manipulation tasks based on natural language instructions is a long-term goal in robotics. The dominant approaches for language-guided manipulation use 2D image representations, which face…
Recognizing precise geometrical configurations of groups of objects is a key capability of human spatial cognition, yet little studied in the deep learning literature so far. In particular, a fundamental problem is how a machine can learn…
The ability to decompose complex natural scenes into meaningful object-centric abstractions lies at the core of human perception and reasoning. In the recent culmination of unsupervised object-centric learning, the Slot-Attention module has…
This paper presents a novel joint neural networks approach to address the challenging one-shot object recognition and detection tasks. Inspired by Siamese neural networks and state-of-art multi-box detection approaches, the joint neural…
Representing a scene and its constituent objects from raw sensory data is a core ability for enabling robots to interact with their environment. In this paper, we propose a novel approach for scene understanding, leveraging a hierarchical…
Learning structured task representations from human demonstrations is essential for understanding long-horizon manipulation behaviors, particularly in bimanual settings where action ordering, object involvement, and interaction geometry can…
Accurate knowledge of object poses is crucial to successful robotic manipulation tasks, and yet most current approaches only work in laboratory settings. Noisy sensors and cluttered scenes interfere with accurate pose recognition, which is…
Autonomous driving perception faces significant challenges due to occlusions and incomplete scene data in the environment. To overcome these issues, the task of semantic occupancy prediction (SOP) is proposed, which aims to jointly infer…
Zero-shot object-goal navigation aims to find target objects in unseen environments using only egocentric observation. Recent methods leverage foundation models' comprehension and reasoning capabilities to enhance navigation performance.…
We study zero-shot instance navigation, in which the agent navigates to a specific object without using object annotations for training. Previous object navigation approaches apply the image-goal navigation (ImageNav) task (go to the…
Models based on Convolutional Neural Networks (CNNs) have been proven very successful for semantic segmentation and object parsing that yield hierarchies of features. Our key insight is to build convolutional networks that take input of…
We present a simple, flexible, and general framework titled Partial Registration Network (PRNet), for partial-to-partial point cloud registration. Inspired by recently-proposed learning-based methods for registration, we use deep networks…
Self-supervision allows learning meaningful representations of natural images, which usually contain one central object. How well does it transfer to multi-entity scenes? We discuss key aspects of learning structured object-centric…
We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…