Related papers: Primitive-based 3D Building Modeling, Sensor Simul…

In recent years, analysis of remote sensing data has benefited immensely from borrowing techniques from the broader field of computer vision, such as the use of shared models pre-trained on large and diverse datasets. However, satellite…

Recent advances in large-scale pretraining have yielded visual foundation models with strong capabilities. Not only can recent models generalize to arbitrary images for their training task, their intermediate representations are useful for…

3D urban reconstruction of buildings from remotely sensed imagery has drawn significant attention during the past two decades. While aerial imagery and LiDAR provide higher resolution, satellite imagery is cheaper and more efficient to…

In this paper we propose a mask-conditional synthetic image generation model for creating synthetic satellite imagery datasets. Given a dataset of real high-resolution images and accompanying land cover masks, we show that it is possible to…

We present SuperDec, an approach for creating compact 3D scene representations via decomposition into superquadric primitives. While most recent works leverage geometric primitives to obtain photorealistic 3D scene representations, we…

Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose estimation models developed using supervision on large-scale…

High-resolution optical satellite sensors, combined with dense stereo algorithms, have made it possible to reconstruct 3D city models from space. However, these models are, in practice, rather noisy and tend to miss small geometric features…

We introduce an approach to building a custom model from ready-made self-supervised models via their associating instead of training and fine-tuning. We demonstrate it with an example of a humanoid robot looking at the mirror and learning…

Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively handle large multi floor buildings and require scenes to be…

In the manufacturing industry, computer vision systems based on artificial intelligence (AI) are widely used to reduce costs and increase production. Training these AI models requires a large amount of training data that is costly to…

In this project, we build a modular, scalable system that can collect, store, and process millions of satellite images. We test the relative importance of both of the key limitations constraining the prevailing literature by applying this…

In all types of disasters, from earthquakes to armed conflicts, aid workers need accurate and timely data such as damage to buildings and population displacement to mount an effective response. Remote sensing provides this data at an…

Building Information Modeling has been used to analyze as well as increase the energy efficiency of the buildings. It has shown significant promise in existing buildings by deconstruction and retrofitting. Current cities which were built…

High-resolution satellite imagery has proven useful for a broad range of tasks, including measurement of global human population, local economic livelihoods, and biodiversity, among many others. Unfortunately, high-resolution imagery is…

Modern scene reconstruction methods are able to accurately recover 3D surfaces that are visible in one or more images. However, this leads to incomplete reconstructions, missing all occluded surfaces. While much progress has been made on…

Reconstructing 3D object from a single image (RGB or depth) is a fundamental problem in visual scene understanding and yet remains challenging due to its ill-posed nature and complexity in real-world scenes. To address those challenges, we…

Synthetic data is being used lately for training deep neural networks in computer vision applications such as object detection, object segmentation and 6D object pose estimation. Domain randomization hereby plays an important role in…

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…

Given large amount of real photos for training, Convolutional neural network shows excellent performance on object recognition tasks. However, the process of collecting data is so tedious and the background are also limited which makes it…

Directly generating scenes from satellite imagery offers exciting possibilities for integration into applications like games and map services. However, challenges arise from significant view changes and scene scale. Previous efforts mainly…