Search Results for author:
Found 35 papers, 21 papers with code
Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer
We address the task of estimating camera parameters from a set of images depicting a scene.
CrossScore: Towards Multi-View Image Evaluation and Scoring
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.
Map-Relative Pose Regression for Visual Re-Localization
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.
Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences
Usually, correspondences are 2D-to-2D and the pose we estimate is defined only up to scale.
GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS).
PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction
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).
Two-View Geometry Scoring Without Correspondences
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.
Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses
We start from the obvious: a relocalization network can be split in a scene-agnostic feature backbone, and a scene-specific prediction head.
SimSC: A Simple Framework for Semantic Correspondence with Temperature Learning
This module is trained together with the backbone and the temperature is updated online.
Neural Refinement for Absolute Pose Regression with Feature Synthesis
To enhance the robustness of our model, we introduce a feature fusion module and a progressive training strategy.
MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices
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.
NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior
Recent advances in this direction demonstrate the possibility of jointly optimising a NeRF and camera poses in forward-facing scenes.
Approximating Continuous Convolutions for Deep Network Compression
We present ApproxConv, a novel method for compressing the layers of a convolutional neural network.
Map-free Visual Relocalization: Metric Pose Relative to a Single Image
Can we relocalize in a scene represented by a single reference image?
Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration
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.
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 mixed reality and robotic applications.
DFNet: Enhance Absolute Pose Regression with Direct Feature Matching
We introduce a camera relocalization pipeline that combines absolute pose regression (APR) and direct feature matching.
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 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.
Few-shot Semantic Segmentation with Self-supervision from Pseudo-classes
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.
Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image
We propose Ray-ONet to reconstruct detailed 3D models from monocular images efficiently.
LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments
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.
NeRF--: Neural Radiance Fields Without Known Camera Parameters
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.
Towards Generalising Neural Implicit Representations
Neural implicit representations have shown substantial improvements in efficiently storing 3D data, when compared to conventional formats.
Aggregation With Feature Detection
Aggregating features from different depths of a network is widely adopted to improve the network capability.
Separable Flow: Learning Motion Cost Volumes for Optical Flow Estimation
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)
Neighbourhood-Insensitive Point Cloud Normal Estimation Network
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
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.
Dual-Resolution Correspondence Networks
The fine-resolution feature maps are used to obtain the final dense correspondences guided by the refined coarse 4D correlation tensor.
FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation
We present FlowNet3D++, a deep scene flow estimation network.
GroSS Decomposition: Group-Size Series Decomposition for Whole Search-Space Training
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
Quantization is a popular way of increasing the speed and lowering the memory usage of Convolution Neural Networks (CNNs).
Interpolating Convolutional Neural Networks Using Batch Normalization
Perceiving a visual concept as a mixture of learned ones is natural for humans, aiding them to grasp new concepts and strengthening old ones.
InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop Closure
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.
gSLICr: SLIC superpixels at over 250Hz
We introduce a parallel GPU implementation of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation.
A Framework for the Volumetric Integration of Depth Images
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.
