Guillaume Bourmaud
YOU?
Author Swipe
View article: Handling Multiple Hypotheses in Coarse-to-Fine Dense Image Matching
Handling Multiple Hypotheses in Coarse-to-Fine Dense Image Matching Open
Dense image matching aims to find a correspondent for every pixel of a source image in a partially overlapping target image. State-of-the-art methods typically rely on a coarse-to-fine mechanism where a single correspondent hypothesis is p…
View article: Evaluating the Posterior Sampling Ability of Plug&Play Diffusion Methods in Sparse-View CT
Evaluating the Posterior Sampling Ability of Plug&Play Diffusion Methods in Sparse-View CT Open
International audience
View article: Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression
Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression Open
Pre-training techniques have greatly advanced computer vision, with CroCo's cross-view completion approach yielding impressive results in tasks like 3D reconstruction and pose regression. However, cross-view completion is ill-posed in non-…
View article: RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges
RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges Open
Camera pose estimation is crucial for many computer vision applications, yet existing benchmarks offer limited insight into method limitations across different geometric challenges. We introduce RUBIK, a novel benchmark that systematically…
View article: Evaluating the Posterior Sampling Ability of Plug&Play Diffusion Methods in Sparse-View CT
Evaluating the Posterior Sampling Ability of Plug&Play Diffusion Methods in Sparse-View CT Open
Plug&Play (PnP) diffusion models are state-of-the-art methods in computed tomography (CT) reconstruction. Such methods usually consider applications where the sinogram contains a sufficient amount of information for the posterior distribut…
View article: Are Semi-Dense Detector-Free Methods Good at Matching Local Features?
Are Semi-Dense Detector-Free Methods Good at Matching Local Features? Open
Semi-dense detector-free approaches (SDF), such as LoFTR, are currently among the most popular image matching methods. While SDF methods are trained to establish correspondences between two images, their performances are almost exclusively…
View article: A kriging-based analysis of cloud liquid water content using CloudSat data
A kriging-based analysis of cloud liquid water content using CloudSat data Open
Spatiotemporal statistical learning has received increased attention in the past decade, due to spatially and temporally indexed data proliferation, especially data collected from satellite remote sensing. In the meantime, observational st…
View article: Comment on amt-2021-348
Comment on amt-2021-348 Open
Abstract. Spatiotemporal statistical learning has received increased attention in the past decade, due to spatially and temporally indexed data proliferation, especially data collected from satellite remote sensing. In the meantime, observ…
View article: A kriging-based analysis of cloud Liquid Water Content using CloudSat data
A kriging-based analysis of cloud Liquid Water Content using CloudSat data Open
Spatiotemporal statistical learning has received increased attention in the past decade, due to spatially and temporally indexed data proliferation, especially collected from satellite remote sensing. In the mean time, observational studie…
View article: Visual Correspondence Hallucination: Towards Geometric Reasoning
Visual Correspondence Hallucination: Towards Geometric Reasoning Open
Given a pair of partially overlapping source and target images and a keypoint in the source image, the keypoint's correspondent in the target image can be either visible, occluded or outside the field of view. Local feature matching method…
View article: Visual Correspondence Hallucination
Visual Correspondence Hallucination Open
Given a pair of partially overlapping source and target images and a keypoint in the source image, the keypoint's correspondent in the target image can be either visible, occluded or outside the field of view. Local feature matching method…
View article: Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation
Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation Open
Absolute camera pose estimation is usually addressed by sequentially solving two distinct subproblems: First a feature matching problem that seeks to establish putative 2D-3D correspondences, and then a Perspective-n-Point problem that min…
View article: S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching
S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching Open
Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under chal…
View article: Pareto Meets Huber: Efficiently Avoiding Poor Minima in Robust Estimation
Pareto Meets Huber: Efficiently Avoiding Poor Minima in Robust Estimation Open
International audience
View article: Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization
Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization Open
We propose a novel approach to feature point matching, suitable for robust and accurate outdoor visual localization in long-term scenarios. Given a query image, we first match it against a database of registered reference images, using rec…
View article: Efficient Condition-based Representations for Long-Term Visual Localization.
Efficient Condition-based Representations for Long-Term Visual Localization. Open
We propose an approach to localization from images that is designed to explicitly handle the strong variations in appearance happening when capturing conditions change throughout the day or across seasons. As revealed by recent long-term l…
View article: Improving Nighttime Retrieval-Based Localization
Improving Nighttime Retrieval-Based Localization Open
Outdoor visual localization is a crucial component to many computer vision systems. We propose an approach to localization from images that is designed to explicitly handle the strong variations in appearance happening between daytime and …
View article: Multiplicative vs. Additive Half-Quadratic Minimization for Robust Cost Optimization
Multiplicative vs. Additive Half-Quadratic Minimization for Robust Cost Optimization Open
International audience
View article: Descending, lifting or smoothing: Secrets of robust cost optimization
Descending, lifting or smoothing: Secrets of robust cost optimization Open
International audience
View article: Iterated Lifting for Robust Cost Optimization
Iterated Lifting for Robust Cost Optimization Open
Optimization of latent model parameters using robust formulations usually creates a large number of local minima due to the quasi-convex shape of the underlying robust kernel. Lifting the robust kernel, i.e. embedding the problem into a hi…
View article: Iterated Lifting for Robust Cost Optimization
Iterated Lifting for Robust Cost Optimization Open
International audience
View article: Online Variational Bayesian Motion Averaging
Online Variational Bayesian Motion Averaging Open
International audience