1 code implementation • 21 Dec 2023 • Shuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii, Jerome Revaud
Our formulation directly provides a 3D model of the scene as well as depth information, but interestingly, we can seamlessly recover from it, pixel matches, relative and absolute camera.
no code implementations • 3 Oct 2023 • Jongmin Lee, Yohann Cabon, Romain Brégier, Sungjoo Yoo, Jerome Revaud
Existing learning-based methods for object pose estimation in RGB images are mostly model-specific or category based.
no code implementations • 1 Oct 2023 • Vincent Leroy, Jerome Revaud, Thomas Lucas, Philippe Weinzaepfel
It is 4 times faster to train than a full-resolution network, and it is straightforward to use at test time compared to existing approaches.
no code implementations • 21 Jul 2023 • Jerome Revaud, Yohann Cabon, Romain Brégier, Jongmin Lee, Philippe Weinzaepfel
Instead of encoding the scene coordinates into the network weights, our model takes as input a database image with some sparse 2D pixel to 3D coordinate annotations, extracted from e. g. off-the-shelf Structure-from-Motion or RGB-D data, and a query image for which are predicted a dense 3D coordinate map and its confidence, based on cross-attention.
no code implementations • ICCV 2021 • Jerome Revaud, Martin Humenberger
Experimental results conducted on three diverse benchmarks demonstrate excellent speed estimation accuracy that could enable the wide use of CCTV cameras for traffic analysis, even in challenging conditions where state-of-the-art methods completely fail.
2 code implementations • NeurIPS 2020 • Thibault Castells, Philippe Weinzaepfel, Jerome Revaud
The key idea is to somehow estimate the importance (or weight) of each sample directly during training based on the observation that easy and hard samples behave differently and can therefore be separated.
2 code implementations • NeurIPS 2019 • Jerome Revaud, Cesar De Souza, Martin Humenberger, Philippe Weinzaepfel
We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness.
Ranked #2 on Camera Localization on Aachen Day-Night benchmark
2 code implementations • ICCV 2019 • Jerome Revaud, Jon Almazan, Rafael Sampaio de Rezende, Cesar Roberto de Souza
Recent deep models for image retrieval have outperformed traditional methods by leveraging ranking-tailored loss functions, but important theoretical and practical problems remain.
1 code implementation • 14 Jun 2019 • Jerome Revaud, Philippe Weinzaepfel, César De Souza, Noe Pion, Gabriela Csurka, Yohann Cabon, Martin Humenberger
In this work, we argue that salient regions are not necessarily discriminative, and therefore can harm the performance of the description.
no code implementations • CVPR 2019 • Jerome Revaud, Minhyeok Heo, Rafael S. Rezende, Chanmi You, Seong-Gyun Jeong
Maps are an increasingly important tool in our daily lives, yet their rich semantic content still largely depends on manual input.
4 code implementations • 25 Oct 2016 • Albert Gordo, Jon Almazan, Jerome Revaud, Diane Larlus
Second, we build on the recent R-MAC descriptor, show that it can be interpreted as a deep and differentiable architecture, and present improvements to enhance it.
Ranked #13 on Image Retrieval on ROxford (Medium)
3 code implementations • 5 Apr 2016 • Albert Gordo, Jon Almazan, Jerome Revaud, Diane Larlus
We propose a novel approach for instance-level image retrieval.
Ranked #3 on Image Retrieval on Oxf105k
no code implementations • 15 Aug 2015 • Danila Potapov, Matthijs Douze, Jerome Revaud, Zaid Harchaoui, Cordelia Schmid
While important advances were recently made towards temporally localizing and recognizing specific human actions or activities in videos, efficient detection and classification of long video chunks belonging to semantically defined categories such as "pursuit" or "romance" remains challenging. We introduce a new dataset, Action Movie Franchises, consisting of a collection of Hollywood action movie franchises.
1 code implementation • 25 Jun 2015 • Jerome Revaud, Philippe Weinzaepfel, Zaid Harchaoui, Cordelia Schmid
We introduce a novel matching algorithm, called DeepMatching, to compute dense correspondences between images.
Ranked #4 on Dense Pixel Correspondence Estimation on HPatches
Dense Pixel Correspondence Estimation Optical Flow Estimation
no code implementations • CVPR 2015 • Philippe Weinzaepfel, Jerome Revaud, Zaid Harchaoui, Cordelia Schmid
We compare the results obtained with several state-of-the-art optical flow approaches and study the impact of the different cues used in the random forest. Furthermore, we introduce a new dataset, the YouTube Motion Boundaries dataset (YMB), that comprises 60 sequences taken from real-world videos with manually annotated motion boundaries.
no code implementations • CVPR 2015 • Jerome Revaud, Philippe Weinzaepfel, Zaid Harchaoui, Cordelia Schmid
We propose a novel approach for optical flow estimation , targeted at large displacements with significant oc-clusions.
no code implementations • CVPR 2014 • Mattis Paulin, Jerome Revaud, Zaid Harchaoui, Florent Perronnin, Cordelia Schmid
We propose a principled algorithm Image Transformation Pursuit (ITP) for the automatic selection of a compact set of transformations.
no code implementations • CVPR 2013 • Jerome Revaud, Matthijs Douze, Cordelia Schmid, Herve Jegou
Furthermore, we extend product quantization to complex vectors in order to compress our descriptors, and to compare them in the compressed domain.