State-of-the-art visual localization approaches generally rely on a first image retrieval step whose role is crucial. Yet, retrieval often struggles when facing varying conditions, due to e.g. weather or time of day, with dramatic consequences on the visual localization accuracy. In this paper, we improve this retrieval step and tailor it to the final localization task. Among the several changes we advocate for, we propose to synthesize variants of the training set images, obtained from generative text-to-image models, in order to automatically expand the training set towards a number of nameable variations that particularly hurt visual localization. These changes result in Ret4Loc, a training approach that learns from such synthetic variants together with real images and that leverages geometric consistency for filtering and sampling. Experiments show that it leads to large improvements on multiple challenging visual localization and place recognition benchmarks.
Weatherproofing retrieval for localization with generative AI and geometric consistency
| Yannis Kalantidis, Mert Bulent Sariyildiz, Rafael Sampaio De Rezende, Philippe Weinzaepfel, Diane Larlus, Gabriela Csurka |
| The International Conference on Learning Representations (ICLR), Vienna, Austria, 7-11 May, 2024 |
Relative gains in localization accuracy
Compared to the state of the art (black dot), using our Ret4Loc models trained with real (Ret4Loc) or real+synthetic images (Ret4Loc+Synth).
Synthetic variants
For the training set images shown on the left.
Geometric correspondences
Ret4Loc in three figures: (left) overview of our experimental validation, (middle) synthetic variants used to extend the training set, and (right) geometric consistency used to select those variants. More precisely: (Left) Relative gains in localization accuracy compared to the state of the art (black dot) for 7 outdoor and 1 indoor datasets, achieved by our best retrieval models trained with our method using only real images (Ret4Loc) or real and synthetic images (Ret4Loc + Synth). Axes in log-scale. (Middle) Original images and several of their synthetic variants obtained for different prompts. (Right) Estimated local correspondences between two matching images before and after alteration. This is used to discard from the training set synthetic variants that fail that verification process.
Visual Localization Results
Figure-2: Localization accuracy as a function of the top-k retrieved images for Ret4Loc models and the state of the art. Results shown for two protocols: A Pose approximation protocol (EWB) and a Structure-from-Motion (SfM) based protocol. Ret4Loc-HOW-Synth variations using geometric consistency are denoted with a ”+”.
Place Recognition Results
Figure-3: Visual place recognition results. We report the usual metrics (top-k recall), i.e. if one correct image is retrieved in the top k. ∗ denotes results from GCL (Leyva-Vallina et al., 2023);
Pretrained Models
Here you can find links to Ret4Loc pretrained models. We built our codebase on top of the HOW codebase. You can use code from HOW to load and evaluate the Ret4Loc models.
We provide two model weights (33MB each):
ret4loc_how.pth– the baseline Ret4Loc-HOW modelret4loc_how_synth-pp.pth– our best Ret4Loc model trained with synthetic data and geometric verification.
You can load our models exactly like a HOW model.
@inproceedings{DBLP:conf/iclr/KalantidisSRWLC24, author = {Yannis Kalantidis and Mert B{\”{u}}lent Sariyildiz and Rafael S. Rezende and Philippe Weinzaepfel and Diane Larlus and Gabriela Csurka}, title = {Weatherproofing Retrieval for Localization with Generative {AI} and Geometric Consistency}, booktitle = {The Twelfth International Conference on Learning Representations, {ICLR} 2024, Vienna, Austria, May 7-11, 2024}, publisher = {OpenReview.net}, year = {2024}, url = {https://openreview.net/forum?id=5EniAcsO7f}, timestamp = {Wed, 07 Aug 2024 17:11:53 +0200}, biburl = {https://dblp.org/rec/conf/iclr/KalantidisSRWLC24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.