Related papers: Omnidata: A Scalable Pipeline for Making Multi-Tas…
The identification and removal of systematic errors in object detectors can be a prerequisite for their deployment in safety-critical applications like automated driving and robotics. Such systematic errors can for instance occur under very…
Omnidirectional image quality assessment (OIQA) has been widely investigated in the past few years and achieved much success. However, most of existing studies are dedicated to solve the uniform distortion problem in OIQA, which has a…
Footpath mapping, modeling, and analysis can provide important geospatial insights to many fields of study, including transport, health, environment and urban planning. The availability of robust Geographic Information System (GIS) layers…
We present a cross-domain inference technique that learns from synthetic data to estimate depth and normals for in-the-wild omnidirectional 3D scenes encountered in real-world uncontrolled settings. To this end, we introduce UBotNet, an…
Recent multimodal large language models (MLLMs) have shown strong chain-of-thought (CoT) reasoning ability on vision-language tasks, but their direct deployment in real-world systems is often limited by latency and resource constraints. In…
Recent work has shown the benefits of synthetic data for use in computer vision, with applications ranging from autonomous driving to face landmark detection and reconstruction. There are a number of benefits of using synthetic data from…
Vision-language models for Earth observation (EO) typically rely on the visual spectrum of data as the only model input, thus failing to leverage the rich spectral information available in the multispectral channels recorded by satellites.…
Recently, the self-supervised pre-training paradigm has shown great potential in leveraging large-scale unlabeled data to improve downstream task performance. However, increasing the scale of unlabeled pre-training data in real-world…
Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain scarce and expensive to produce. Prevailing pseudo-labeling…
The Data Science domain has expanded monumentally in both research and industry communities during the past decade, predominantly owing to the Big Data revolution. Artificial Intelligence (AI) and Machine Learning (ML) are bringing more…
Vision-Language Pre-training (VLP) models like CLIP have achieved remarkable success in computer vision and particularly demonstrated superior robustness to distribution shifts of 2D images. However, their robustness under 3D viewpoint…
While Vision-Language Models (VLMs) achieve near-perfect scores on digital document benchmarks like OmniDocBench, their performance in the unpredictable physical world remains largely unknown due to the lack of controlled yet realistic…
Aligning functional schematics with 2D and 3D scene acquisitions is crucial for building digital twins, especially for old industrial facilities that lack native digital models. Current manual alignment using images and LiDAR data does not…
In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world has a great demand for labor and money…
By measuring, modeling and interpreting cosmological datasets, one can place strong constraints on models of the Universe. Central to this effort are summary statistics such as power spectra and bispectra, which condense the…
Instruction-guided image editing methods have demonstrated significant potential by training diffusion models on automatically synthesized or manually annotated image editing pairs. However, these methods remain far from practical,…
DBSCAN is a classical density-based clustering procedure with tremendous practical relevance. However, DBSCAN implicitly needs to compute the empirical density for each sample point, leading to a quadratic worst-case time complexity, which…
Multi-stage screening pipelines are ubiquitous throughout experimental and computational science. Much of the effort in developing screening pipelines focuses on improving generative methods or surrogate models in an attempt to make each…
Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…
Quality control of assembly processes is essential in manufacturing to ensure not only the quality of individual components but also their proper integration into the final product. To assist in this matter, automated assembly control using…