Omniglue: Generalizable feature matching with foundation model guidance

H Jiang, A Karpur, B Cao, Q Huang… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
The image matching field has been witnessing a continuous emergence of novel learnable
feature matching techniques with ever-improving performance on conventional benchmarks …

NodeSLAM: Neural object descriptors for multi-view shape reconstruction

E Sucar, K Wada, A Davison - 2020 International Conference …, 2020‏ - ieeexplore.ieee.org
The choice of scene representation is crucial in both the shape inference algorithms it
requires and the smart applications it enables. We present efficient and optimisable multi …

Rfd-net: Point scene understanding by semantic instance reconstruction

Y Nie, J Hou, X Han, M Nießner - Proceedings of the IEEE …, 2021‏ - openaccess.thecvf.com
Semantic scene understanding from point clouds is particularly challenging as the points
reflect only a sparse set of the underlying 3D geometry. Previous works often convert point …

Mask2cad: 3d shape prediction by learning to segment and retrieve

W Kuo, A Angelova, TY Lin, A Dai - … , Glasgow, UK, August 23–28, 2020 …, 2020‏ - Springer
Object recognition has seen significant progress in the image domain, with focus primarily
on 2D perception. We propose to leverage existing large-scale datasets of 3D models to …

Pixel-aligned recurrent queries for multi-view 3d object detection

Y **e, H Jiang, G Gkioxari… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
We present PARQ-a multi-view 3D object detector with transformer and pixel-aligned
recurrent queries. Unlike previous works that use learnable features or only encode 3D point …

Snap2cad: 3D indoor environment reconstruction for AR/VR applications using a smartphone device

A Manni, D Oriti, A Sanna, F De Pace, F Manuri - Computers & Graphics, 2021‏ - Elsevier
Indoor environment reconstruction is a challenging task in Computer Vision and Computer
Graphics, especially when Extended Reality (XR) technologies are considered. Current …

Pins: progressive implicit networks for multi-scale neural representations

Z Landgraf, AS Hornung, RS Cabral - arxiv preprint arxiv:2202.04713, 2022‏ - arxiv.org
Multi-layer perceptrons (MLP) have proven to be effective scene encoders when combined
with higher-dimensional projections of the input, commonly referred to as\textit {positional …

Rangeudf: Semantic surface reconstruction from 3d point clouds

B Wang, Z Yu, B Yang, J Qin, T Breckon, L Shao… - arxiv preprint arxiv …, 2022‏ - arxiv.org
We present RangeUDF, a new implicit representation based framework to recover the
geometry and semantics of continuous 3D scene surfaces from point clouds. Unlike …

Dynamic convolution for 3D point cloud instance segmentation

T He, C Shen, A Van Den Hengel - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
In this paper, we come up with a simple yet effective approach for instance segmentation on
3D point cloud with strong robustness. Previous top-performing methods for this task adopt a …

Sdfest: Categorical pose and shape estimation of objects from rgb-d using signed distance fields

L Bruns, P Jensfelt - IEEE Robotics and Automation Letters, 2022‏ - ieeexplore.ieee.org
Rich geometric understanding of the world is an important component of many robotic
applications such as planning and manipulation. In this paper, we present a modular …