Related papers: JoinABLe: Learning Bottom-up Assembly of Parametri…

Multimodal fusion is crucial in joint decision-making systems for rendering holistic judgments. Since multimodal data changes in open environments, dynamic fusion has emerged and achieved remarkable progress in numerous applications.…

Self-assembly of complex and functional materials remains a grand challenge in soft material science. Efficient assembly depends on a delicate balance between thermodynamic and kinetic effects, requiring fine-tuning affinities and…

Sequential assembly with geometric primitives has drawn attention in robotics and 3D vision since it yields a practical blueprint to construct a target shape. However, due to its combinatorial property, a greedy method falls short of…

In this paper, we introduce the problem of jointly learning feed-forward neural networks across a set of relevant but diverse datasets. Compared to learning a separate network from each dataset in isolation, joint learning enables us to…

Combinatorial assembly uses standardized unit primitives to build objects that satisfy user specifications. This paper studies assembly sequence planning (ASP) for physical combinatorial assembly. Given the shape of the desired object, the…

Despite the success of deep functional maps in non-rigid 3D shape matching, there exists no learning framework that models both self-symmetry and shape matching simultaneously. This is despite the fact that errors due to symmetry mismatch…

Proteins are the basic building blocks of life. They usually perform functions by folding to a particular structure. Understanding the folding process could help the researchers to understand the functions of proteins and could also help to…

Articulation modeling enables robots to learn joint parameters of articulated objects for effective manipulation which can then be used downstream for skill learning or planning. Existing approaches often rely on prior knowledge about the…

With the availability of egocentric 3D hand-object interaction datasets, there is increasing interest in developing unified models for hand-object pose estimation and action recognition. However, existing methods still struggle to recognise…

In recommendation systems, items are likely to be exposed to various users and we would like to learn about the familiarity of a new user with an existing item. This can be formulated as an anomaly detection (AD) problem distinguishing…

The problem of mating two parts with low clearance remains difficult for autonomous robots. We present bi-level belief assembly (BILBA), a model-based planner that computes a sequence of compliant motions which can leverage contact with the…

Significant progress in robotics reveals new opportunities to advance manufacturing. Next-generation industrial automation will require both integration of distinct robotic technologies and their application to challenging industrial…

We present ImageBind, an approach to learn a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. We show that all combinations of paired data are not necessary to train such a joint…

Articulated objects used in simulation and embodied AI are typically specified by geometry and kinematic structure, but lack the fine-grained dynamical effects that govern realistic mechanical behavior, such as frictional holding, detents,…

Federated learning is a paradigm of distributed machine learning in which multiple clients coordinate with a central server to learn a model, without sharing their own training data. Standard federated optimization methods such as Federated…

Object detection with multimodal inputs can improve many safety-critical systems such as autonomous vehicles (AVs). Motivated by AVs that operate in both day and night, we study multimodal object detection with RGB and thermal cameras,…

Extrapolating fine-grained pixel-level correspondences in a fully unsupervised manner from a large set of misaligned images can benefit several computer vision and graphics problems, e.g. co-segmentation, super-resolution, image edit…

3D reassembly is a challenging spatial intelligence task with broad applications across scientific domains. While large-scale synthetic datasets have fueled promising learning-based approaches, their generalizability to different domains is…

Most recent approaches to monocular 3D human pose estimation rely on Deep Learning. They typically involve regressing from an image to either 3D joint coordinates directly or 2D joint locations from which 3D coordinates are inferred. Both…

We introduce an approach to building a custom model from ready-made self-supervised models via their associating instead of training and fine-tuning. We demonstrate it with an example of a humanoid robot looking at the mirror and learning…