research
∙
06/02/2023
Two-View Geometry Scoring Without Correspondences
Camera pose estimation for two-view geometry traditionally relies on RAN...
share
research
∙
05/23/2023
Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses
Learning-based visual relocalizers exhibit leading pose accuracy, but re...
research
∙
05/03/2023
SimSC: A Simple Framework for Semantic Correspondence with Temperature Learning
We propose SimSC, a remarkably simple framework, to address the problem ...
research
∙
03/17/2023
Refinement for Absolute Pose Regression with Neural Feature Synthesis
Absolute Pose Regression (APR) methods use deep neural networks to direc...
research
∙
03/03/2023
MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices
High-quality 3D ground-truth shapes are critical for 3D object reconstru...
research
∙
12/14/2022
NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior
Training a Neural Radiance Field (NeRF) without pre-computed camera pose...
research
∙
10/17/2022
Approximating Continuous Convolutions for Deep Network Compression
We present ApproxConv, a novel method for compressing the layers of a co...
research
∙
10/11/2022
Map-free Visual Relocalization: Metric Pose Relative to a Single Image
Can we relocalize in a scene represented by a single reference image? St...
research
∙
09/12/2022
Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration
The prowess that makes few-shot learning desirable in medical image anal...
research
∙
04/03/2022
BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion
Dense 3D reconstruction from a stream of depth images is the key to many...
research
∙
04/01/2022
DFNet: Enhance Absolute Pose Regression with Direct Feature Matching
We introduce a camera relocalization pipeline that combines absolute pos...
research
∙
01/17/2022
Few-shot image segmentation for cross-institution male pelvic organs using registration-assisted prototypical learning
The ability to adapt medical image segmentation networks for a novel cla...
research
∙
10/22/2021
Few-shot Semantic Segmentation with Self-supervision from Pseudo-classes
Despite the success of deep learning methods for semantic segmentation, ...
research
∙
07/05/2021
Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image
We propose Ray-ONet to reconstruct detailed 3D models from monocular ima...
research
∙
04/19/2021
LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments
We present LaLaLoc to localise in environments without the need for prio...
research
∙
02/14/2021
NeRF–: Neural Radiance Fields Without Known Camera Parameters
This paper tackles the problem of novel view synthesis (NVS) from 2D ima...
research
∙
01/29/2021
Towards Generalising Neural Implicit Representations
Neural implicit representations have shown substantial improvements in e...
research
∙
08/23/2020
Neighbourhood-Insensitive Point Cloud Normal Estimation Network
We introduce a novel self-attention-based normal estimation network that...
research
∙
07/15/2020
Finding Non-Uniform Quantization Schemes usingMulti-Task Gaussian Processes
We propose a novel method for neural network quantization that casts the...
research
∙
06/16/2020
Dual-Resolution Correspondence Networks
We tackle the problem of establishing dense pixel-wise correspondences b...
research
∙
12/03/2019
FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation
We present FlowNet3D++, a deep scene flow estimation network. Inspired b...
research
∙
01/07/2019
DSConv: Efficient Convolution Operator
We introduce a variation of the convolutional layer called DSConv (Distr...
research
∙
08/02/2017
InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop Closure
Volumetric models have become a popular representation for 3D scenes in ...
research
∙
09/14/2015
gSLICr: SLIC superpixels at over 250Hz
We introduce a parallel GPU implementation of the Simple Linear Iterativ...
research
∙
10/03/2014