Related papers: Meta-Sim2: Unsupervised Learning of Scene Structur…

Many real-world safety-critical systems are governed by explicit rules that define unsafe world configurations and constrain agent interactions. In practice, these rules are complex and context-dependent, making manual specification…

We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. future prediction). We propose a generative…

We propose a model that is able to perform unsupervised physical parameter estimation of systems from video, where the differential equations governing the scene dynamics are known, but labeled states or objects are not available. Existing…

We propose a novel general method that finds action-grounded, discrete object and effect categories and builds probabilistic rules over them for non-trivial action planning. Our robot interacts with objects using an initial action…

Simulating object dynamics from real-world perception shows great promise for digital twins and robotic manipulation but often demands labor-intensive measurements and expertise. We present a fully automated Real2Sim pipeline that generates…

Automating quality inspection with computer vision techniques is often a very data-demanding task. Specifically, supervised deep learning requires a large amount of annotated images for training. In practice, collecting and annotating such…

The research and development cycle of advanced manufacturing processes traditionally requires a large investment of time and resources. Experiments can be expensive and are hence conducted on relatively small scales. This poses problems for…

Estimating the parameters of a model describing a set of observations using a neural network is in general solved in a supervised way. In cases when we do not have access to the model's true parameters this approach can not be applied.…

Scene classification is a fundamental perception task for environmental understanding in today's robotics. In this paper, we have attempted to exploit the use of popular machine learning technique of deep learning to enhance scene…

During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving and augmented reality. However, to train CNNs…

As machine learning models increase in scale and complexity, obtaining sufficient training data has become a critical bottleneck due to acquisition costs, privacy constraints, and data scarcity in specialised domains. While synthetic data…

Generating controllable indoor scenes is fundamental to applications in game development, architectural visualization, and embodied AI. However, existing approaches either support a limited input modalities or rely on implicit generation…

Semantic scene segmentation has primarily been addressed by forming representations of single images both with supervised and unsupervised methods. The problem of semantic segmentation in dynamic scenes has begun to recently receive…

Structural learning, a method to estimate the parameters for discrete energy minimization, has been proven to be effective in solving computer vision problems, especially in 3D scene parsing. As the complexity of the models increases,…

Representing scenes at the granularity of objects is a prerequisite for scene understanding and decision making. We propose PriSMONet, a novel approach based on Prior Shape knowledge for learning Multi-Object 3D scene decomposition and…

We propose a new probabilistic programming language for the design and analysis of perception systems, especially those based on machine learning. Specifically, we consider the problems of training a perception system to handle rare events,…

Scene text erasing seeks to erase text contents from scene images and current state-of-the-art text erasing models are trained on large-scale synthetic data. Although data synthetic engines can provide vast amounts of annotated training…

Text-to-image models are showcasing the impressive ability to create high-quality and diverse generative images. Nevertheless, the transition from freehand sketches to complex scene images remains challenging using diffusion models. In this…

In many real-world applications, modeling both the internal structure of sets and their temporal relationships is essential for capturing complex underlying patterns. Sequential multiple-instance learning aims to address this challenge by…

Recent advances in deep learning, in particular enabled by hardware advances and big data, have provided impressive results across a wide range of computational problems such as computer vision, natural language, or reinforcement learning.…