RANa: Retrieval-Augmented Navigation

Methods for navigation based on large-scale learning typically treat each episode as a new problem, where the agent is spawned with a clean memory in an unknown environment. While these generalization capabilities to an unknown environment are extremely important, we claim that, in a realistic setting, an agent should have the capacity of exploiting information collected during earlier robot operations. We address this by introducing a new retrieval-augmented agent, trained with RL, capable of querying a database collected from previous episodes in the same environment and learning how to integrate this additional context information. We introduce a unique agent architecture for the general navigation task, evaluated on ObjectNav, ImageNav and Instance-ImageNav. Our retrieval and context encoding methods are data-driven and heavily employ vision foundation models (FM) for both semantic and geometric understanding. We propose new benchmarks for these settings and we show that retrieval allows zero-shot transfer across tasks and environments while significantly improving performance.

MUSt3R: Multi-view Network for Stereo 3D Reconstruction

DUSt3R introduced a novel paradigm in geometric computer vision by proposing a model that can provide dense and unconstrained Stereo 3D Reconstruction of arbitrary image collections with no prior information about camera calibration nor viewpoint poses. Under the hood, however, DUSt3R processes image pairs, regressing local 3D reconstructions that need to be aligned in a global coordinate system. The number of pairs, growing quadratically, is an inherent limitation that becomes especially concerning for robust and fast optimization in the case of large image collections. In this paper, we propose an extension of DUSt3R from pairs to multiple views, that addresses all aforementioned concerns. Indeed, we propose a Multi-view Network for Stereo 3D Reconstruction, or MUSt3R, that modifies the DUSt3R architecture by making it symmetric and extending it to directly predict 3D structure for all views in a common coordinate frame. Second, we entail the model with a multi-layer memory mechanism which allows to reduce the computational complexity and to scale the reconstruction to large collections, inferring thousands of 3D pointmaps at high frame-rates with limited added complexity. The framework is designed to perform 3D reconstruction both offline and online, and hence can be seamlessly applied to SfM and visual SLAM scenarios showing state-of-the-art performance on various 3D downstream tasks, including uncalibrated Visual Odometry, relative camera pose, scale and focal estimation, 3D reconstruction and multi-view depth estimation.

What could go wrong? Discovering and describing failure modes in computer vision

Deep learning models are effective, yet brittle. Even carefully trained, their behavior tends to be hard to predict when confronted with out-of-distribution samples. In this work, our goal is to propose a simple yet effective solution to predict and describe via natural language potential failure modes of computer vision models. Given a pretrained model and a set of samples, our aim is to find sentences that accurately describe the visual conditions in which the model underperforms. In order to study this important topic and foster future research on it, we formalize the problem of Language-Based Error Explainability (LBEE) and propose a set of metrics to evaluate and compare different methods for this task. We propose solutions that operate in a joint vision-and-language embedding space, and can characterize through language descriptions model failures caused, e.g., by objects unseen during training or adverse visual conditions. We experiment with different tasks, such as classification under the presence of dataset bias and semantic segmentation in unseen environments, and show that the proposed methodology isolates nontrivial sentences associated with specific error causes. We hope our work will help practitioners better understand the behavior of models, increasing their overall safety and interpretability.

Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement

Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former requires sparse feature extractors and matchers to build the scene representation. The latter might lack geometric grounding not capturing the 3D structure of the scene well enough. This paper proposes to jointly learn the scene representation along with a 3D dense feature field and a 2D feature extractor whose outputs are embedded in the same metric space. Through a contrastive framework we align this volumetric field with the image-based extractor and regularize the latter with a ranking loss from learned surface information. We learn the underlying geometry of the scene with an implicit field through volumetric rendering and design our feature field to leverage intermediate geometric information encoded in the implicit field. The resulting features are discriminative and robust to viewpoint change while maintaining rich encoded information. Visual localization is then achieved by aligning the image-based features and the rendered volumetric features. We show the effectiveness of our approach on real-world scenes, demonstrating that our approach outperforms prior and concurrent work on leveraging implicit scene representations for localization.

SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection

Open-vocabulary object detection (OvOD) has transformed detection into a language-guided task, empowering users to freely define their class vocabularies of interest during inference. However, our initial investigation indicates that existing OvOD detectors exhibit significant variability when dealing with vocabularies across various semantic granularities, posing a concern for real-world deployment. To this end, we introduce Semantic Hierarchy Nexus (SHiNe), a novel classifier that uses semantic knowledge from class hierarchies. It runs offline in three steps: i) it retrieves relevant super-/sub-categories from a hierarchy for each target class; ii) it integrates these categories into hierarchy-aware sentences; iii) it fuses these sentence embeddings to generate the nexus classifier vector. Our evaluation on various detection benchmarks demonstrates that SHiNe enhances robustness across diverse vocabulary granularities, achieving up to +31.9% mAP50 with ground truth hierarchies, while retaining improvements using hierarchies generated by large language models. Moreover, when applied to open-vocabulary classification on ImageNet-1k, SHiNe improves the CLIP zero-shot baseline by +2.8% accuracy. SHiNe is training-free and can be seamlessly integrated with any off-the-shelf OvOD detector, without incurring additional computational overhead during inference. The code is open source.

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency

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. After expanding the training set, we propose a training approach that leverages the specificities and the underlying geometry of this mix of real and synthetic images. We experimentally show that those changes translate into large improvements for the most challenging visual localization datasets. Project page: https://europe.naverlabs.com/ret4loc

RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation

Class-incremental semantic image segmentation assumes multiple model updates, each enriching the model to segment new categories. This is typically carried out by providing expensive pixel-level annotations to the training algorithm for all new objects, limiting the adoption of such methods in practical applications. Approaches that solely require image-level labels offer an attractive alternative, yet, such coarse annotations lack precise information about the location and boundary of the new objects. In this paper we argue that, since classes represent not just indices but semantic entities, the conceptual relationships between them can provide valuable information that should be leveraged. We propose a weakly supervised approach that exploits such semantic relations to transfer objectness prior from the previously learned classes into the new ones, complementing the supervisory signal from image-level labels. We validate our approach on a number of continual learning tasks, and show how even a simple pairwise interaction between classes can significantly improve the segmentation mask quality of both old and new classes. We show these conclusions still hold for longer and, hence, more realistic sequences of tasks and for a challenging few-shot scenario.

Semantic Image Segmentation: Two Decades of Research

Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. This survey is an effort to summarize two decades of research in the field of SiS, where we propose a literature review of solutions starting from early historical methods followed by an overview of more recent deep learning methods including the latest trend of using transformers. We complement the review by discussing particular cases of the weak supervision and side machine learning techniques that can be used to improve the semantic segmentation such as curriculum, incremental or self-supervised learning. State-of-the-art SiS models rely on a large amount of annotated samples, which are more expensive to obtain than labels for tasks such as image classification. Since unlabeled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation (UDA) reached a broad success within the semantic segmentation community. Therefore, a second core contribution of this book is to summarize five years of a rapidly growing field, Domain Adaptation for Semantic Image Segmentation (DASiS) which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments. In addition to providing a comprehensive survey on DASiS techniques, we unveil also newer trends such as multi-domain learning, domain generalization, domain incremental learning, test-time adaptation and source-free domain adaptation. Finally, we conclude this survey by describing datasets and benchmarks most widely used in SiS and DASiS and briefly discuss related tasks such as instance and panoptic image segmentation, as well as applications such as medical image segmentation.

Improved Cross-view Completion Pre-training for Stereo Matching

Despite impressive performance for high-level downstream tasks, self-supervised pre-training methods have not yet fully delivered on dense geometric vision tasks such as stereo matching. The application of self-supervised learning concepts, such as instance discrimination or masked image modeling, to geometric tasks is an active area of research. In this work we build on the recent cross-view completion framework: this variation of masked image modeling leverages a second view from the same scene, which is well suited for binocular downstream tasks. However, the applicability of this concept has so far been limited in at least two ways: (a) by the difficulty of collecting real-world image pairs - in practice only synthetic data had been used - and (b) by the lack of generalization of vanilla transformers to dense downstream tasks for which relative position is more meaningful than absolute position. We explore three avenues of improvement: first, we introduce a method to collect suitable real-world image pairs at large scale. Second, we experiment with relative positional embeddings and demonstrate that they enable vision transformers to perform substantially better. Third, we scale up vision transformer based cross-completion architectures, which is made possible by the use of large amounts of data. With these improvements, we show for the first time that state-of-the-art results on deep stereo matching can be reached without using any standard task-specific techniques like correlation volume, iterative estimation or multi-scale reasoning.

CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion

Masked Image Modeling (MIM) has recently been established as a potent pre-training paradigm. A pretext task is constructed by masking patches in an input image, and this masked content is then predicted by a neural network using visible patches as sole input. This pre-training leads to state-of-the-art performance when finetuned for high-level semantic tasks, e.g. image classification and object detection. In this paper we instead seek to learn representations that transfer well to a wide variety of 3D vision and lower-level geometric downstream tasks, such as depth prediction or optical flow estimation. Inspired by MIM, we propose an unsupervised representation learning task trained from pairs of images showing the same scene from different viewpoints. More precisely, we propose the pretext task of cross-view completion where the first input image is partially masked, and this masked content has to be reconstructed from the visible content and the second image. In single-view MIM, the masked content often cannot be inferred precisely from the visible portion only, so the model learns to act as a prior influenced by high-level semantics. In contrast, this ambiguity can be resolved with cross-view completion from the second unmasked image, on the condition that the model is able to understand the spatial relationship between the two images. Our experiments show that our pretext task leads to significantly improved performance for monocular 3D vision downstream tasks such as depth estimation. In addition, our model can be directly applied to binocular downstream tasks like optical flow or relative camera pose estimation, for which we obtain competitive results without bells and whistles, i.e., using a generic architecture without any task-specific design.