Related papers: Shadow: Leveraging Segmentation Masks for Cross-Em…

Text-to-image diffusion models excel at generating diverse portraits, but lack intuitive shadow control. Existing editing approaches, as post-processing, struggle to offer effective manipulation across diverse styles. Additionally, these…

Shadow boundaries can be confused with material boundaries as both exhibit sharp changes in luminance or contrast within a scene. However, shadows do not modify the intrinsic color or texture of surfaces. Therefore, on both sides of shadow…

Data augmentation improves the generalization power of deep learning models by synthesizing more training samples. Sample-mixing is a popular data augmentation approach that creates additional data by combining existing samples. Recent…

Illumination effects in images, specifically cast shadows and shading, have been shown to decrease the performance of deep neural networks on a large number of vision-based detection, recognition and segmentation tasks in urban driving…

In the robotics literature, different knowledge transfer approaches have been proposed to leverage the experience from a source task or robot -- real or virtual -- to accelerate the learning process on a new task or robot. A commonly made…

Generalizing control policies to novel embodiments remains a fundamental challenge in enabling scalable and transferable learning in robotics. While prior works have explored this in locomotion, a systematic study in the context of…

Enabling robots to quickly learn manipulation skills is an important, yet challenging problem. Such manipulation skills should be flexible, e.g., be able adapt to the current workspace configuration. Furthermore, to accomplish complex…

Robotic learning for navigation in unfamiliar environments needs to provide policies for both task-oriented navigation (i.e., reaching a goal that the robot has located), and task-agnostic exploration (i.e., searching for a goal in a novel…

Shadows encode rich information about scene geometry and illumination, yet existing methods either predict a unified shadow mask or overlook attached shadows entirely. We address this gap by proposing a framework for jointly detecting cast…

Training general-purpose robots requires learning from large and diverse data sources. Current approaches rely heavily on teleoperated demonstrations which are difficult to scale. We present a scalable framework for training manipulation…

We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of diverse policies that…

In this article we develop algorithms for data assimilation based upon a computational time dependent stable/unstable splitting. Our particular method is based upon shadowing refinement and synchronization techniques and is motivated by…

Building a single generalist agent with strong zero-shot capability has recently sparked significant advancements. However, extending this capability to multi-agent decision making scenarios presents challenges. Most current works struggle…

We explore possible methods for multi-task transfer learning which seek to exploit the shared physical structure of robotics tasks. Specifically, we train policies for a base set of pre-training tasks, then experiment with adapting to new…

Deep learning has revolutionized many industries by enabling models to automatically learn complex patterns from raw data, reducing dependence on manual feature engineering. However, deep learning algorithms are sensitive to input data, and…

The performance of learned robot visuomotor policies is heavily dependent on the size and quality of the training dataset. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action…

Observing that the key for robotic action planning is to understand the target-object motion when its associated part is manipulated by the end effector, we propose to generate the 3D object-part scene flow and extract its transformations…

Transformers have become prevalent in computer vision due to their performance and flexibility in modelling complex operations. Of particular significance is the 'cross-attention' operation, which allows a vector representation (e.g. of an…

Integrating robots in complex everyday environments requires a multitude of problems to be solved. One crucial feature among those is to equip robots with a mechanism for teaching them a new task in an easy and natural way. When teaching…

The growing demand of industrial, automotive and service robots presents a challenge to the centralized Cloud Robotics model in terms of privacy, security, latency, bandwidth, and reliability. In this paper, we present a `Fog Robotics'…