Camera pose estimation for two-view geometry traditionally relies on RAN...
Learning-based visual relocalizers exhibit leading pose accuracy, but re...
We propose SimSC, a remarkably simple framework, to address the problem ...
Absolute Pose Regression (APR) methods use deep neural networks to direc...
High-quality 3D ground-truth shapes are critical for 3D object reconstru...
Training a Neural Radiance Field (NeRF) without pre-computed camera pose...
We present ApproxConv, a novel method for compressing the layers of a
co...
Can we relocalize in a scene represented by a single reference image?
St...
The prowess that makes few-shot learning desirable in medical image anal...
Dense 3D reconstruction from a stream of depth images is the key to many...
We introduce a camera relocalization pipeline that combines absolute pos...
The ability to adapt medical image segmentation networks for a novel cla...
Despite the success of deep learning methods for semantic segmentation,
...
We propose Ray-ONet to reconstruct detailed 3D models from monocular ima...
We present LaLaLoc to localise in environments without the need for prio...
This paper tackles the problem of novel view synthesis (NVS) from 2D ima...
Neural implicit representations have shown substantial improvements in
e...
We introduce a novel self-attention-based normal estimation network that...
We propose a novel method for neural network quantization that casts the...
We tackle the problem of establishing dense pixel-wise correspondences
b...
We present FlowNet3D++, a deep scene flow estimation network. Inspired b...
We introduce a variation of the convolutional layer called DSConv
(Distr...
Volumetric models have become a popular representation for 3D scenes in
...
We introduce a parallel GPU implementation of the Simple Linear Iterativ...
Volumetric models have become a popular representation for 3D scenes in
...