V
Victor Adrian Prisacariu
Researcher at University of Oxford
Publications - 95
Citations - 4116
Victor Adrian Prisacariu is an academic researcher from University of Oxford. The author has contributed to research in topics: Computer science & 3D reconstruction. The author has an hindex of 28, co-authored 77 publications receiving 2955 citations.
Papers
More filters
Proceedings ArticleDOI
GA-Net: Guided Aggregation Net for End-To-End Stereo Matching
TL;DR: In this article, a semi-global aggregation layer and a local guided aggregation layer are proposed to capture local and the whole-image cost dependencies respectively, which can be used to replace the widely used 3D convolutional layer which is computationally costly and memory-consuming.
Journal ArticleDOI
Very High Frame Rate Volumetric Integration of Depth Images on Mobile Devices
Olaf Kähler,Victor Adrian Prisacariu,Carl Yuheng Ren,Xin Sun,Philip H. S. Torr,David W. Murray +5 more
TL;DR: A range of modifications to existing volumetric integration methods based on voxel block hashing are presented, considerably improving their performance and making them applicable to tablet computer applications.
Proceedings ArticleDOI
Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction
Vibhav Vineet,Ondrej Miksik,Morten Lidegaard,Matthias NieBner,Stuart Golodetz,Victor Adrian Prisacariu,Olaf Kähler,David W. Murray,Shahram Izadi,Patrick Peerez,Philip H. S. Torr +10 more
TL;DR: This paper presents what to their knowledge is the first system that can perform dense, large-scale, outdoor semantic reconstruction of a scene in (near) real time and presents a `semantic fusion' approach that allows us to handle dynamic objects more effectively than previous approaches.
fastHOG – a real-time GPU implementation of HOG
TL;DR: A parallel implementation of the histogram of oriented gradients algorithm for object detection, using the GPU and the NVIDIA CUDA framework, which allows for real-time performance of the full HOG algorithm for the first time in the literature.
Book ChapterDOI
RelocNet: Continuous Metric Learning Relocalisation Using Neural Nets
TL;DR: A method of learning suitable convolutional representations for camera pose retrieval based on nearest neighbour matching and continuous metric learning-based feature descriptors, which is able to generalise in a meaningful way, and outperforms related methods across several experiments.