Humans can orient themselves in their 3D environments using simple 2D maps. Differently,
algorithms for visual localization mostly rely on complex 3D point clouds that are expensive …

We present Scan2CAD, a novel data-driven method that learns to align clean 3D CAD models
from a shape database to the noisy and incomplete geometry of a commodity RGB-D scan…

In this work, we introduce the task of 3D object instance re-localization (RIO): given one or
multiple objects in an RGB-D scan, we want to estimate their corresponding 6DoF poses in …

We present a novel, end-to-end approach to align CAD models to an 3D scan of a scene,
enabling transformation of a noisy, incomplete 3D scan to a compact, CAD reconstruction with …

We present a novel approach to reconstructing lightweight, CAD-based representations of
scanned 3D environments from commodity RGB-D sensors. Our key idea is to jointly optimize …

Lung resections have been always the shortest way of removal of the affected zone of the lung
with the hope of future recovery of tuberculosis (TB) patients. Nevertheless the successes …

The aim of this pilot study was to examine the effectiveness of a CrossFit-based training
program to enhance the general and sport-specific physical fitness of 10–12-year-old judokas. …

Surgery of pulmonary tuberculosis associated with open thoracotomy due to dense pleural
and vascular adhesions. These reasons limited the use of video-assisted thoracoscopic …

We introduce ReplaceAnything3D model (RAM3D), a novel text-guided 3D scene editing
method that enables the replacement of specific objects within a scene. Given multi-view …

We introduce SceneScript, a method that directly produces full scene models as a sequence
of structured language commands using an autoregressive, token-based approach. Our …