Related papers: Self-Supervised Real-to-Sim Scene Generation

Deep learning in medical imaging is often limited by scarce and imbalanced annotated data. We present SSGNet, a unified framework that combines class specific generative modeling with iterative semisupervised pseudo labeling to enhance both…

In precision agriculture, the scarcity of labeled data and significant covariate shifts pose unique challenges for training machine learning models. This scarcity is particularly problematic due to the dynamic nature of the environment and…

An important factor in advancing autonomous driving systems is simulation. Yet, there is rather small progress for transferability between the virtual and real world. We revisit this problem for 3D object detection on LiDAR point clouds and…

We present SPSG, a novel approach to generate high-quality, colored 3D models of scenes from RGB-D scan observations by learning to infer unobserved scene geometry and color in a self-supervised fashion. Our self-supervised approach learns…

Realistic synthetic image data rendered from 3D models can be used to augment image sets and train image classification semantic segmentation models. In this work, we explore how high quality physically-based rendering and domain…

Training data is the key ingredient for deep learning approaches, but difficult to obtain for the specialized domains often encountered in robotics. We describe a synthesis pipeline capable of producing training data for cluttered scene…

Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category…

The usage of medical image data for the training of large-scale machine learning approaches is particularly challenging due to its scarce availability and the costly generation of data annotations, typically requiring the engagement of…

Modern vision models excel at general purpose downstream tasks. It is unclear, however, how they may be used for personalized vision tasks, which are both fine-grained and data-scarce. Recent works have successfully applied synthetic data…

Nowadays, various stakeholders involved in the analysis of electric power distribution grids face difficulties in the data acquisition related to the grid topology and parameters of grid assets. To mitigate the problem and possibly…

The goal of scene graph generation is to predict a graph from an input image, where nodes correspond to identified and localized objects and edges to their corresponding interaction predicates. Existing methods are trained in a fully…

This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…

For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-pixel ground truth labels from real images. We address this challenge by introducing Hypersim, a photorealistic synthetic dataset for holistic…

Sketches make an intuitive and powerful visual expression as they are fast executed freehand drawings. We present a method for synthesizing realistic photos from scene sketches. Without the need for sketch and photo pairs, our framework…

Autonomous driving techniques have been flourishing in recent years while thirsting for huge amounts of high-quality data. However, it is difficult for real-world datasets to keep up with the pace of changing requirements due to their…

Image captioning requires numerous annotated image-text pairs, resulting in substantial annotation costs. Recently, large models (e.g. diffusion models and large language models) have excelled in producing high-quality images and text. This…

Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images. Though the results are astonishing to human eyes, how applicable these generated images are for recognition tasks…

Scene Graph Generation (SGG) aims to extract entities, predicates and their semantic structure from images, enabling deep understanding of visual content, with many applications such as visual reasoning and image retrieval. Nevertheless,…

Effectively capturing intricate interactions among road users is of critical importance to achieving safe navigation for autonomous vehicles. While graph learning (GL) has emerged as a promising approach to tackle this challenge, existing…

This paper addresses the challenges of data scarcity and high acquisition costs in training robust object detection models for complex industrial environments, such as offshore oil platforms. Data collection in these hazardous settings…