no code implementations • 16 May 2024 • Xianzheng Ma, Yash Bhalgat, Brandon Smart, Shuai Chen, Xinghui Li, Jian Ding, Jindong Gu, Dave Zhenyu Chen, Songyou Peng, Jia-Wang Bian, Philip H Torr, Marc Pollefeys, Matthias Nießner, Ian D Reid, Angel X. Chang, Iro Laina, Victor Adrian Prisacariu
Hence, with this paper, we aim to chart a course for future research that explores and expands the capabilities of 3D-LLMs in understanding and interacting with the complex 3D world.
no code implementations • 22 Apr 2024 • Eric Brachmann, Jamie Wynn, Shuai Chen, Tommaso Cavallari, Áron Monszpart, Daniyar Turmukhambetov, Victor Adrian Prisacariu
We address the task of estimating camera parameters from a set of images depicting a scene.
no code implementations • 22 Apr 2024 • ZiRui Wang, Wenjing Bian, Omkar Parkhi, Yuheng Ren, Victor Adrian Prisacariu
We introduce a novel cross-reference image quality assessment method that effectively fills the gap in the image assessment landscape, complementing the array of established evaluation schemes -- ranging from full-reference metrics like SSIM, no-reference metrics such as NIQE, to general-reference metrics including FID, and Multi-modal-reference metrics, e. g., CLIPScore.
1 code implementation • 15 Apr 2024 • Shuai Chen, Tommaso Cavallari, Victor Adrian Prisacariu, Eric Brachmann
We present a new approach to pose regression, map-relative pose regression (marepo), that satisfies the data hunger of the pose regression network in a scene-agnostic fashion.
1 code implementation • 9 Apr 2024 • Axel Barroso-Laguna, Sowmya Munukutla, Victor Adrian Prisacariu, Eric Brachmann
Usually, correspondences are 2D-to-2D and the pose we estimate is defined only up to scale.
no code implementations • 13 Mar 2024 • Jing Wu, Jia-Wang Bian, Xinghui Li, Guangrun Wang, Ian Reid, Philip Torr, Victor Adrian Prisacariu
We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS).
1 code implementation • 11 Oct 2023 • Jia-Wang Bian, Wenjing Bian, Victor Adrian Prisacariu, Philip Torr
On the MobileBrick dataset that contains casually captured unbounded 360-degree videos, our method refines ARKit poses and improves the reconstruction F1 score from 69. 18 to 75. 67, outperforming that with the dataset provided ground-truth pose (75. 14).
1 code implementation • CVPR 2023 • Axel Barroso-Laguna, Eric Brachmann, Victor Adrian Prisacariu, Gabriel J. Brostow, Daniyar Turmukhambetov
As a remedy, we propose the Fundamental Scoring Network (FSNet), which infers a score for a pair of overlapping images and any proposed fundamental matrix.
no code implementations • CVPR 2023 • Eric Brachmann, Tommaso Cavallari, Victor Adrian Prisacariu
We start from the obvious: a relocalization network can be split in a scene-agnostic feature backbone, and a scene-specific prediction head.
no code implementations • 3 May 2023 • Xinghui Li, Kai Han, Xingchen Wan, Victor Adrian Prisacariu
This module is trained together with the backbone and the temperature is updated online.
1 code implementation • 17 Mar 2023 • Shuai Chen, Yash Bhalgat, Xinghui Li, Jiawang Bian, Kejie Li, ZiRui Wang, Victor Adrian Prisacariu
To enhance the robustness of our model, we introduce a feature fusion module and a progressive training strategy.
1 code implementation • CVPR 2023 • Kejie Li, Jia-Wang Bian, Robert Castle, Philip H. S. Torr, Victor Adrian Prisacariu
The distinct data modality offered by high-resolution RGB images and low-resolution depth maps captured on a mobile device, when combined with precise 3D geometry annotations, presents a unique opportunity for future research on high-fidelity 3D reconstruction.
1 code implementation • CVPR 2023 • Wenjing Bian, ZiRui Wang, Kejie Li, Jia-Wang Bian, Victor Adrian Prisacariu
Recent advances in this direction demonstrate the possibility of jointly optimising a NeRF and camera poses in forward-facing scenes.
no code implementations • 17 Oct 2022 • Theo W. Costain, Victor Adrian Prisacariu
We present ApproxConv, a novel method for compressing the layers of a convolutional neural network.
1 code implementation • 11 Oct 2022 • Eduardo Arnold, Jamie Wynn, Sara Vicente, Guillermo Garcia-Hernando, Áron Monszpart, Victor Adrian Prisacariu, Daniyar Turmukhambetov, Eric Brachmann
Can we relocalize in a scene represented by a single reference image?
1 code implementation • 12 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.
1 code implementation • CVPR 2022 • Kejie Li, Yansong Tang, Victor Adrian Prisacariu, Philip H. S. Torr
Dense 3D reconstruction from a stream of depth images is the key to many mixed reality and robotic applications.
1 code implementation • 1 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.
no code implementations • 17 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.
1 code implementation • 22 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.
1 code implementation • 5 Jul 2021 • Wenjing Bian, ZiRui Wang, Kejie Li, Victor Adrian Prisacariu
We propose Ray-ONet to reconstruct detailed 3D models from monocular images efficiently.
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.
5 code implementations • 14 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.
no code implementations • 29 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.
1 code implementation • ICCV 2021 • Feihu Zhang, Oliver J. Woodford, Victor Adrian Prisacariu, Philip H.S. Torr
Full-motion cost volumes play a central role in current state-of-the-art optical flow methods.
Ranked #5 on Optical Flow Estimation on KITTI 2015 (train)
no code implementations • ICCV 2021 • Shuyang Sun, Xiaoyu Yue, Xiaojuan Qi, Wanli Ouyang, Victor Adrian Prisacariu, Philip H.S. Torr
Aggregating features from different depths of a network is widely adopted to improve the network capability.
1 code implementation • 23 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.
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.
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.
no code implementations • 3 Dec 2019 • Zirui Wang, Shuda Li, Henry Howard-Jenkins, Victor Adrian Prisacariu, Min Chen
We present FlowNet3D++, a deep scene flow estimation network.
no code implementations • 25 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.
1 code implementation • 7 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).
no code implementations • ECCV 2018 • Gratianus Wesley Putra Data, Kirjon Ngu, David William Murray, Victor Adrian Prisacariu
Perceiving a visual concept as a mixture of learned ones is natural for humans, aiding them to grasp new concepts and strengthening old ones.
1 code implementation • 2 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.
1 code implementation • 14 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.
no code implementations • 3 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.