Search Results for author: Victor Adrian Prisacariu

Found 23 papers, 14 papers with code

Approximating Continuous Convolutions for Deep Network Compression

no code implementations17 Oct 2022 Theo W. Costain, Victor Adrian Prisacariu

We present ApproxConv, a novel method for compressing the layers of a convolutional neural network.

Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration

1 code implementation12 Sep 2022 Yiwen Li, Yunguan Fu, Iani Gayo, Qianye Yang, Zhe Min, Shaheer Saeed, Wen Yan, Yipei Wang, J. Alison Noble, Mark Emberton, Matthew J. Clarkson, Henkjan Huisman, Dean Barratt, Victor Adrian Prisacariu, Yipeng Hu

The prowess that makes few-shot learning desirable in medical image analysis is the efficient use of the support image data, which are labelled to classify or segment new classes, a task that otherwise requires substantially more training images and expert annotations.

Few-Shot Learning

DFNet: Enhance Absolute Pose Regression with Direct Feature Matching

1 code implementation1 Apr 2022 Shuai Chen, Xinghui Li, ZiRui Wang, Victor Adrian Prisacariu

We introduce a camera relocalization pipeline that combines absolute pose regression (APR) and direct feature matching.

Camera Relocalization Novel View Synthesis +3

Few-shot image segmentation for cross-institution male pelvic organs using registration-assisted prototypical learning

no code implementations17 Jan 2022 Yiwen Li, Yunguan Fu, Qianye Yang, Zhe Min, Wen Yan, Henkjan Huisman, Dean Barratt, Victor Adrian Prisacariu, Yipeng Hu

The ability to adapt medical image segmentation networks for a novel class such as an unseen anatomical or pathological structure, when only a few labelled examples of this class are available from local healthcare providers, is sought-after.

Anatomy Image Segmentation +2

Few-shot Semantic Segmentation with Self-supervision from Pseudo-classes

1 code implementation22 Oct 2021 Yiwen Li, Gratianus Wesley Putra Data, Yunguan Fu, Yipeng Hu, Victor Adrian Prisacariu

Despite the success of deep learning methods for semantic segmentation, few-shot semantic segmentation remains a challenging task due to the limited training data and the generalisation requirement for unseen classes.

Few-Shot Semantic Segmentation Semantic Segmentation

Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image

1 code implementation5 Jul 2021 Wenjing Bian, ZiRui Wang, Kejie Li, Victor Adrian Prisacariu

We propose Ray-ONet to reconstruct detailed 3D models from monocular images efficiently.

3D Reconstruction

LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments

no code implementations ICCV 2021 Henry Howard-Jenkins, Jose-Raul Ruiz-Sarmiento, Victor Adrian Prisacariu

We present LaLaLoc to localise in environments without the need for prior visitation, and in a manner that is robust to large changes in scene appearance, such as a full rearrangement of furniture.

Pose Estimation

NeRF--: Neural Radiance Fields Without Known Camera Parameters

4 code implementations14 Feb 2021 ZiRui Wang, Shangzhe Wu, Weidi Xie, Min Chen, Victor Adrian Prisacariu

Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by removing the requirement of known or pre-computed camera parameters, including both intrinsics and 6DoF poses.

Novel View Synthesis

Towards Generalising Neural Implicit Representations

no code implementations29 Jan 2021 Theo W. Costain, Victor Adrian Prisacariu

Neural implicit representations have shown substantial improvements in efficiently storing 3D data, when compared to conventional formats.

Semantic Segmentation

Neighbourhood-Insensitive Point Cloud Normal Estimation Network

1 code implementation23 Aug 2020 Zirui Wang, Victor Adrian Prisacariu

We introduce a novel self-attention-based normal estimation network that is able to focus softly on relevant points and adjust the softness by learning a temperature parameter, making it able to work naturally and effectively within a large neighbourhood range.

Finding Non-Uniform Quantization Schemes using Multi-Task Gaussian Processes

1 code implementation ECCV 2020 Marcelo Gennari do Nascimento, Theo W. Costain, Victor Adrian Prisacariu

We propose a novel method for neural network quantization that casts the neural architecture search problem as one of hyperparameter search to find non-uniform bit distributions throughout the layers of a CNN.

Gaussian Processes Neural Architecture Search +1

Dual-Resolution Correspondence Networks

1 code implementation NeurIPS 2020 Xinghui Li, Kai Han, Shuda Li, Victor Adrian Prisacariu

The fine-resolution feature maps are used to obtain the final dense correspondences guided by the refined coarse 4D correlation tensor.

GroSS Decomposition: Group-Size Series Decomposition for Whole Search-Space Training

no code implementations25 Sep 2019 Henry Howard-Jenkins, Yiwen Li, Victor Adrian Prisacariu

We present Group-size Series (GroSS) decomposition, a mathematical formulation of tensor factorisation into a series of approximations of increasing rank terms.

DSConv: Efficient Convolution Operator

1 code implementation7 Jan 2019 Marcelo Gennari, Roger Fawcett, Victor Adrian Prisacariu

Quantization is a popular way of increasing the speed and lowering the memory usage of Convolution Neural Networks (CNNs).


InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop Closure

1 code implementation2 Aug 2017 Victor Adrian Prisacariu, Olaf Kähler, Stuart Golodetz, Michael Sapienza, Tommaso Cavallari, Philip H. S. Torr, David W. Murray

Representing the reconstruction volumetrically as a TSDF leads to most of the simplicity and efficiency that can be achieved with GPU implementations of these systems.

3D Reconstruction Simultaneous Localization and Mapping

gSLICr: SLIC superpixels at over 250Hz

1 code implementation14 Sep 2015 Carl Yuheng Ren, Victor Adrian Prisacariu, Ian D. Reid

We introduce a parallel GPU implementation of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation.


A Framework for the Volumetric Integration of Depth Images

no code implementations3 Oct 2014 Victor Adrian Prisacariu, Olaf Kähler, Ming Ming Cheng, Carl Yuheng Ren, Julien Valentin, Philip H. S. Torr, Ian D. Reid, David W. Murray

Along with the framework we also provide a set of components for scalable reconstruction: two implementations of camera trackers, based on RGB data and on depth data, two representations of the 3D volumetric data, a dense volume and one based on hashes of subblocks, and an optional module for swapping subblocks in and out of the typically limited GPU memory.

3D Reconstruction

Cannot find the paper you are looking for? You can Submit a new open access paper.