Object rearrangement is pivotal in robotic-environment interactions,
rep...
Unlike in natural images, in endoscopy there is no clear notion of an
up...
Dynamic reconstruction with neural radiance fields (NeRF) requires accur...
Thyroid disorders are most commonly diagnosed using high-resolution
Ultr...
Since real-world training datasets cannot properly sample the long tail ...
6D pose estimation pipelines that rely on RGB-only or RGB-D data show
li...
This paper addresses the limitations of current datasets for 3D vision t...
In this paper, we present a novel shape reconstruction method leveraging...
Purpose: Recent advances in Surgical Data Science (SDS) have contributed...
Controllable scene synthesis aims to create interactive environments for...
Statistical shape models (SSMs) are an established way to geometrically
...
Learning-based methods to solve dense 3D vision problems typically train...
Scene Graph Generation (SGG) is a challenging visual understanding task....
The intrinsic rotation invariance lies at the core of matching point clo...
Reliable multi-agent trajectory prediction is crucial for the safe plann...
Purpose: Mutual acceptance is required for any human-to-human interactio...
We present a physics-enhanced implicit neural representation (INR) for
u...
In the last decade, various robotic platforms have been introduced that ...
In this paper, we introduce neural texture learning for 6D object pose
e...
Estimating the 6D pose of objects is one of the major fields in 3D compu...
Despite monocular 3D object detection having recently made a significant...
Successful point cloud registration relies on accurate correspondences
e...
6-DoF robotic grasping is a long-lasting but unsolved problem. Recent me...
As panoptic segmentation provides a prediction for every pixel in input,...
For visual manipulation tasks, we aim to represent image content with
se...
Processing 3D data efficiently has always been a challenge. Spatial
oper...
In this paper, we introduce DA^2, the first large-scale dual-arm
dexteri...
Despite its broad availability, volumetric information acquisition from
...
Object pose estimation is crucial for robotic applications and augmented...
Depth estimation is a core task in 3D computer vision. Recent methods
in...
We present a novel one-shot method for object detection and 6 DoF pose
e...
Learning-based depth estimation has witnessed recent progress in multipl...
Establishing correspondences from image to 3D has been a key task of 6Do...
The surgical operating room (OR) presents many opportunities for automat...
Pose estimation of 3D objects in monocular images is a fundamental and
l...
Shape matching has been a long-studied problem for the computer graphics...
In nuclear medicine, radioiodine therapy is prescribed to treat diseases...
As 3D object detection on point clouds relies on the geometrical
relatio...
Light has many properties that can be passively measured by vision senso...
Indirect Time-of-Flight (I-ToF) imaging is a widespread way of depth
est...
The ability to successfully grasp objects is crucial in robotics, as it
...
Retinal surgery is a complex medical procedure that requires exceptional...
We study the problem of extracting correspondences between a pair of poi...
Inferring geometrically consistent dense 3D scenes across a tuple of
tem...
Estimating the uncertainty of a neural network plays a fundamental role ...
While self-supervised monocular depth estimation in driving scenarios ha...
In this paper we introduce OperA, a transformer-based model that accurat...
3D Point clouds are a rich source of information that enjoy growing
popu...
Object pose estimation is an integral part of robot vision and augmented...
Depth completion aims to predict a dense depth map from a sparse depth i...