Related papers: MegaSynth: Scaling Up 3D Scene Reconstruction with…

We explore the task of geometric reconstruction of images captured from a mixture of ground and aerial views. Current state-of-the-art learning-based approaches fail to handle the extreme viewpoint variation between aerial-ground image…

Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. Recently, pose-conditioned diffusion models have led to significant progress by extracting 3D information from 2D foundation models, but these…

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…

Recent progress in computer vision has been dominated by deep neural networks trained over large amounts of labeled data. Collecting such datasets is however a tedious, often impossible task; hence a surge in approaches relying solely on…

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…

Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted…

In the current deep learning paradigm, the amount and quality of training data are as critical as the network architecture and its training details. However, collecting, processing, and annotating real data at scale is difficult, expensive,…

Modern machine learning models for scene understanding, such as depth estimation and object tracking, rely on large, high-quality datasets that mimic real-world deployment scenarios. To address data scarcity, we propose an end-to-end system…

Recent advances in deep learning have significantly increased the performance of face recognition systems. The performance and reliability of these models depend heavily on the amount and quality of the training data. However, the…

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…

Recent advancements in differentiable rendering and 3D reasoning have driven exciting results in novel view synthesis from a single image. Despite realistic results, methods are limited to relatively small view change. In order to…

The default strategy for training single-view Large Reconstruction Models (LRMs) follows the fully supervised route using large-scale datasets of synthetic 3D assets or multi-view captures. Although these resources simplify the training…

Capturing and labeling real-world 3D data is laborious and time-consuming, which makes it costly to train strong 3D models. To address this issue, recent works present a simple method by generating randomized 3D scenes without simulation…

While deep learning has recently achieved great success on multi-view stereo (MVS), limited training data makes the trained model hard to be generalized to unseen scenarios. Compared with other computer vision tasks, it is rather difficult…

Pre-training and transfer learning are an important building block of current computer vision systems. While pre-training is usually performed on large real-world image datasets, in this paper we ask whether this is truly necessary. To this…

Stereo matching is an important problem in computer vision which has drawn tremendous research attention for decades. Recent years, data-driven methods with convolutional neural networks (CNNs) are continuously pushing stereo matching to…

Recent smaller language models such Phi-3.5 and Phi-4 rely on synthetic data generated using larger Language models. Questions remain about leveraging synthetic data for other use cases, such as adapting LLMs to specific domains. A key…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

Large transformer-based models have made significant progress in generalizable novel view synthesis (NVS) from sparse input views, generating novel viewpoints without the need for test-time optimization. However, these models are…

We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of…