Related papers: Camera simulation for robot simulation: how import…

We describe a computational model of humans' ability to provide a detailed interpretation of components in a scene. Humans can identify in an image meaningful components almost everywhere, and identifying these components is an essential…

The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore,…

Robotics simulation plays an important role in the design, development, and verification and validation of robotic systems. Recent studies have shown that simulation may be used as a cheaper, safer, and more reliable alternative to manual,…

Classification networks can be used to localize and segment objects in images by means of class activation maps (CAMs). However, without pixel-level annotations, classification networks are known to (1) mainly focus on discriminative…

One of the grand challenges of deep learning is the requirement to obtain large labeled training data sets. While synthesized data sets can be used to overcome this challenge, it is important that these data sets close the reality gap,…

Vision-based perception systems are typically exposed to large orientation changes in different robot applications. In such conditions, their performance might be compromised due to the inherent complexity of processing data captured under…

Robotic technology can support the creation of new tools that improve the creative process of cinematography. It is crucial to consider the specific requirements and perspectives of industry professionals when designing and developing these…

Camera calibration involves estimating camera parameters to infer geometric features from captured sequences, which is crucial for computer vision and robotics. However, conventional calibration is laborious and requires dedicated…

There has been a growing adoption of computer vision tools and technologies in architectural design workflows over the past decade. Notable use cases include point cloud generation, visual content analysis, and spatial awareness for robotic…

Developing meaningful and efficient representations that separate the fundamental structure of the data generation mechanism is crucial in representation learning. However, Disentangled Representation Learning has not fully shown its…

Sphere packings are essential to the development of physical models for powders, composite materials, and the atomic structure of the liquid state. There is a strong scientific need to be able to assess the fit of packing models to data,…

Scene models allow robots to reason about what is in the scene, what else should be in it, and what should not be in it. In this paper, we propose a hybrid Boltzmann Machine (BM) for scene modeling where relations between objects are…

Simulation models are an absolute necessity in the human and social sciences, which can only very exceptionally use experimental science methods to construct their knowledge. Models enable the simulation of social processes by replacing the…

Understanding and modeling human behavior is fundamental to almost any computer vision and robotics applications that involve humans. In this thesis, we take a holistic approach to human behavior modeling and tackle its three essential…

Dashboard cameras capture a tremendous amount of driving scene video each day. These videos are purposefully coupled with vehicle sensing data, such as from the speedometer and inertial sensors, providing an additional sensing modality for…

While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation. Performance metrics are particularly key for meaningful, objective, and transparent…

We propose a method to realistically insert synthetic objects into existing photographs without requiring access to the scene or any additional scene measurements. With a single image and a small amount of annotation, our method creates a…

As the computer vision matures into a systems science and engineering discipline, there is a trend in leveraging latest advances in computer graphics simulations for performance evaluation, learning, and inference. However, there is an open…

We propose FreeSim, a camera simulation method for autonomous driving. FreeSim emphasizes high-quality rendering from viewpoints beyond the recorded ego trajectories. In such viewpoints, previous methods have unacceptable degradation…

Autonomous agents, particularly in the field of robotics, rely on sensory information to perceive and navigate their environment. However, these sensory inputs are often imperfect, leading to distortions in the agent's internal…