Related papers: Learning from synthetic data generated with GRADE

The task of generating natural images from 3D scenes has been a long standing goal in computer graphics. On the other hand, recent developments in deep neural networks allow for trainable models that can produce natural-looking images with…

In order to function in unstructured environments, robots need the ability to recognize unseen novel objects. We take a step in this direction by tackling the problem of segmenting unseen object instances in tabletop environments. However,…

Autonomous agents, such as driverless cars, require large amounts of labeled visual data for their training. A viable approach for acquiring such data is training a generative model with collected real data, and then augmenting the…

Annotated datasets are critical for training neural networks for object detection, yet their manual creation is time- and labour-intensive, subjective to human error, and often limited in diversity. This challenge is particularly pronounced…

Visual grouping -- operationalized through tasks such as instance segmentation, visual grounding, and object detection -- enables applications ranging from robotic perception to photo editing. These fundamental problems in computer vision…

Instance-level recognition (ILR) focuses on identifying individual objects rather than broad categories, offering the highest granularity in image classification. However, this fine-grained nature makes creating large-scale annotated…

Synthetic data generation has become essential in last years for feeding data-driven algorithms, which surpassed traditional techniques performance in almost every computer vision problem. Gathering and labelling the amount of data needed…

Novel deep-learning (DL) architectures have reached a level where they can generate digital media, including photorealistic images, that are difficult to distinguish from real data. These technologies have already been used to generate…

Data seems cheap to get, and in many ways it is, but the process of creating a high quality labeled dataset from a mass of data is time-consuming and expensive. With the advent of rich 3D repositories, photo-realistic rendering systems…

Robotic learning in simulation environments provides a faster, more scalable, and safer training methodology than learning directly with physical robots. Also, synthesizing images in a simulation environment for collecting large-scale image…

The usefulness of deep learning models in robotics is largely dependent on the availability of training data. Manual annotation of training data is often infeasible. Synthetic data is a viable alternative, but suffers from domain gap. We…

The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are…

We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects. Similar to other generative approaches, RELATE is trained end-to-end on raw, unlabeled data. RELATE combines an…

Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly:…

Scalable training data generation is a critical problem in deep learning. We propose PennSyn2Real - a photo-realistic synthetic dataset consisting of more than 100,000 4K images of more than 20 types of micro aerial vehicles (MAVs). The…

Nanoparticles occur in various environments as a consequence of man-made processes, which raises concerns about their impact on the environment and human health. To allow for proper risk assessment, a precise and statistically relevant…

Deep neural network based reinforcement learning (RL) can learn appropriate visual representations for complex tasks like vision-based robotic grasping without the need for manually engineering or prior learning a perception system.…

Synthetic image data generation represents a promising avenue for training deep learning models, particularly in the realm of transfer learning, where obtaining real images within a specific domain can be prohibitively expensive due to…

Drone racing is a recreational sport in which the goal is to pass through a sequence of gates in a minimum amount of time while avoiding collisions. In autonomous drone racing, one must accomplish this task by flying fully autonomously in…

Generative models have shown substantial impact across multiple domains, their potential for scene synthesis remains underexplored in robotics. This gap is more evident in drone simulators, where simulation environments still rely heavily…