Determining the precise geographic location of an image at a global scale remains an unsolved challenge. Standard image retrieval techniques are inefficient due to the sheer volume of images (>100M) and fail when coverage is insufficient. Scalable solutions, however, involve a trade-off: global classification typically yields coarse results (10+ kilometers), while cross-view retrieval between ground and aerial imagery suffers from a domain gap and has been primarily studied on smaller regions. This paper introduces a hybrid approach that achieves fine-grained geo-localization across a large geographic expanse the size of a continent. We leverage a proxy classification task during training to learn rich feature representations that implicitly encode precise location information. We combine these learned prototypes with embeddings of aerial imagery to increase robustness to the sparsity of ground-level data. This enables direct, fine-grained retrieval over areas spanning multiple countries. Our extensive evaluation demonstrates that our approach can localize within 200m more than 68\% of queries of a dataset covering a large part of Europe. The code is publicly available at [scaling-geoloc.github.io](https://scaling-geoloc.github.io).

Diffusion models generating images conditionally on text, such as Dall-E 2 [51] and Stable Diffusion [53], have recently made a splash far beyond the computer vision community. Here, we tackle the related problem of generating point clouds, both unconditionally, and conditionally with images. For the latter, we introduce a novel geometrically-motivated conditioning scheme based on projecting sparse image features into the point cloud and attaching them to each individual point, at every step in the denoising process. This approach improves geometric consistency and yields greater fidelity than current methods relying on unstructured, global latent codes. Additionally, we show how to apply recent continuous-time diffusion schemes [59], [21]. Our method performs on par or above the state of art on conditional and unconditional experiments on synthetic data, while being faster, lighter, and delivering tractable likelihoods. We show it can also scale to diverse indoors scenes.

Semantic 2D maps are commonly used by humans and machines for navigation purposes, whether it's walking or driving. However, these maps have limitations: they lack detail, often contain inaccuracies, and are difficult to create and maintain, especially in an automated fashion. Can we use _raw imagery_ to automatically create _better maps_ that can be easily interpreted by both humans and machines? We introduce SNAP, a deep network that learns rich 2D _neural_ maps from ground-level and overhead images. We train our model to align neural maps estimated from different inputs, supervised only with camera poses over tens of millions of StreetView images. SNAP can resolve the location of challenging image queries beyond the reach of traditional methods, outperforming the state of the art in localization by a large margin. Moreover, our neural maps encode not only geometry and appearance but also high-level semantics, discovered without explicit supervision. This enables effective pre-training for data-efficient semantic scene understanding, with the potential to unlock cost-efficient creation of more detailed maps.

Existing unsupervised methods for keypoint learning rely heavily on the assumption that a specific keypoint type (e.g. elbow, digit, abstract geometric shape) appears only once in an image. This greatly limits their applicability, as each instance must be isolated before applying the method—an issue that is never discussed or evaluated. We thus propose a novel method to learn Task-agnostic, UnSupervised Keypoints (TUSK) which can deal with multiple instances. To achieve this, instead of the commonly-used strategy of detecting multiple heatmaps, each dedicated to a specific keypoint type, we use a single heatmap for detection, and enable unsupervised learning of keypoint types through clustering. Specifically, we encode semantics into the keypoints by teaching them to reconstruct images from a sparse set of keypoints and their descriptors, where the descriptors are forced to form distinct clusters in feature space around learned prototypes. This makes our approach amenable to a wider range of tasks than any previous unsupervised keypoint method: we show experiments on multiple-instance detection and classification, object discovery, and landmark detection—all unsupervised—with performance on par with the state of the art, while also being able to deal with multiple instances.

We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other. By doing so, one has the option to query only the points of interest and retrieve sparse correspondences, or to query all points in an image and obtain dense mappings. Importantly, in order to capture both local and global priors, and to let our model relate between image regions using the most relevant among said priors, we realize our network using a transformer. At inference time, we apply our correspondence network by recursively zooming in around the estimates, yielding a multiscale pipeline able to provide highly-accurate correspondences. Our method significantly outperforms the state of the art on both sparse and dense correspondence problems on multiple datasets and tasks, ranging from wide-baseline stereo to optical flow, without any retraining for a specific dataset. We commit to releasing data, code, and all the tools necessary to train from scratch and ensure reproducibility.

Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds. Permutation-equivariant networks have become a popular solution - they operate on individual data points with simple perceptrons and extract contextual information with global pooling. This can be achieved with a simple normalization of the feature maps, a global operation that is unaffected by the order. In this paper, we propose Attentive Context Normalization (ACN), a simple yet effective technique to build permutation-equivariant networks robust to outliers. Specifically, we show how to normalize the feature maps with weights that are estimated within the network, excluding outliers from this normalization. We use this mechanism to leverage two types of attention: local and global - by combining them, our method is able to find the essential data points in high-dimensional space in order to solve a given task. We demonstrate through extensive experiments that our approach, which we call Attentive Context Networks (ACNe), provides a significant leap in performance compared to the state-of-the-art on camera pose estimation, robust fitting, and point cloud classification under noise and outliers. Source code: https://github.com/vcg-uvic/acne.

Local feature frameworks are difficult to learn in an end-to-end fashion due to the discreteness inherent to the selection and matching of sparse keypoints. We introduce DISK (DIScrete Keypoints), a novel method that overcomes these obstacles by leveraging principles from Reinforcement Learning (RL), optimizing end-to-end for a high number of correct feature matches. Our simple yet expressive probabilistic model lets us keep the training and inference regimes close, while maintaining good enough convergence properties to reliably train from scratch. Our features can be extracted very densely while remaining discriminative, challenging commonly held assumptions about what constitutes a good keypoint, as showcased in Fig. 1, and deliver state-of-the-art results on three public benchmarks.

The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if two patches are not in correspondence, their descriptors will not match. A strategy often used to alleviate this problem is to “pool” the pixel-wise features over log-polar regions, rather than regularly spaced ones. By contrast, we propose to extract the “support region” directly with a log-polar sampling scheme. We show that this provides us with a better representation by simultaneously oversampling the immediate neighbourhood of the point and undersampling regions far away from it. We demonstrate that this representation is particularly amenable to learning descriptors with deep networks. Our models can match descriptors across a much wider range of scales than was possible before, and also leverage much larger support regions without suffering from occlusions. We report state-of-the-art results on three different datasets.

We propose a novel image sampling method for differentiable image transformation in deep neural networks. The sampling schemes currently used in deep learning, such as Spatial Transformer Networks, rely on bilinear interpolation, which performs poorly under severe scale changes, and more importantly, results in poor gradient propagation. This is due to their strict reliance on direct neighbors. Instead, we propose to generate random auxiliary samples in the vicinity of each pixel in the sampled image, and create a linear approximation with their intensity values. We then use this approximation as a differentiable formula for the transformed image. We demonstrate that our approach produces more representative gradients with a wider basin of convergence for image alignment, which leads to considerable performance improvements when training networks for registration and classification tasks. This is not only true under large downsampling, but also when there are no scale changes. We compare our approach with multi-scale sampling and show that we outperform it. We then demonstrate that our improvements to the sampler are compatible with other tangential improvements to Spatial Transformer Networks and that it further improves their performance.

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outliers, while simultaneously using them to recover the relative pose, as encoded by the essential matrix. Our architecture is based on a multi-layer perceptron operating on pixel coordinates rather than directly on the image, and is thus simple and small. We introduce a novel normalization technique, called Context Normalization, which allows us to process each data point separately while embedding global information in it, and also makes the network invariant to the order of the correspondences. Our experiments on multiple challenging datasets demonstrate that our method is able to drastically improve the state of the art with little training data.

We present a novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision. To do so we exploit depth and relative camera pose cues to create a virtual target that the network should achieve on one image, provided the outputs of the network for the other image. While this process is inherently non-differentiable, we show that we can optimize the network in a two-branch setup by confining it to one branch, while preserving differentiability in the other. We train our method on both indoor and outdoor datasets, with depth data from 3D sensors for the former, and depth estimates from an off-the-shelf Structure-from-Motion solution for the latter. Our models outperform the state of the art on sparse feature matching on both datasets, while running at 60+ fps for QVGA images.

Image matching is a fundamental problem in Computer Vision. In the context of feature-based matching, SIFT and its variants have long excelled in a wide array of applications. However, for ultra-wide baselines, as in the case of aerial images captured under large camera rotations, the appearance variation goes beyond the reach of SIFT and RANSAC. In this paper we propose a data-driven, deep learning-based approach that sidesteps local correspondence by framing the problem as a classification task. Furthermore, we demonstrate that local correspondences can still be useful. To do so we incorporate an attention mechanism to produce a set of probable matches, which allows us to further increase performance. We train our models on a dataset of urban aerial imagery consisting of 'same' and 'different' pairs, collected for this purpose, and characterize the problem via a human study with annotations from Amazon Mechanical Turk. We demonstrate that our models outperform the state-of-the-art on ultra-wide baseline matching and approach human accuracy.

Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e.g. SIFT. In this paper we use Convolutional Neural Networks (CNNs) to learn discriminant patch representations and in particular train a Siamese network with pairs of (non-)corresponding patches. We deal with the large number of potential pairs with the combination of a stochastic sampling of the training set and an aggressive mining strategy biased towards patches that are hard to classify. By using the L2 distance during both training and testing we develop 128-D descriptors whose euclidean distances reflect patch similarity, and which can be used as a drop-in replacement for any task involving SIFT. We demonstrate consistent performance gains over the state of the art, and generalize well against scaling and rotation, perspective transformation, non-rigid deformation, and illumination changes. Our descriptors are efficient to compute and amenable to modern GPUs, and are publicly available.

In this work we propose a technique to combine bottom-up segmentation, coming in the form of SLIC superpixels, with sliding window detectors, such as Deformable Part Models (DPMs). The merit of our approach lies in "cleaning up" the low-level HOG features by exploiting the spatial support of SLIC superpixels, this can be understood as using segmentation to split the feature variation into object-specific and background changes. Rather than committing to a single segmentation we use a large pool of SLIC superpixels and combine them in a scale-, position- and object-dependent manner to build soft segmentation masks. The segmentation masks can be computed fast enough to repeat this process over every candidate window, during training and detection, for both the root and part filters of DPMs. We use these masks to construct enhanced, background-invariant features to train DPMs. We test our approach on the PASCAL VOC 2007, outperforming the standard DPM in 17 out of 20 classes, yielding an average increase of 1.7% AP. Additionally, we demonstrate the robustness of this approach, extending it to dense SIFT descriptors for large displacement optical flow.

In this work we exploit segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes. For this, we downplay measurements coming from areas that are unlikely to belong to the same region as the descriptor's center, as suggested by soft segmentation masks. Our treatment is applicable to any image point, i.e. dense, and its computational overhead is in the order of a few seconds. We integrate this idea with Dense SIFT, and also with Dense Scale and Rotation Invariant Descriptors (SID), delivering descriptors that are densely computable, invariant to scaling and rotation, and robust to background changes. We apply our approach to standard benchmarks on large displacement motion estimation using SIFT-flow and wide-baseline stereo, systematically demonstrating that the introduction of segmentation yields clear improvements.

We present to the robotic community a fully autonomous navigation solution for mobile robots operating in urban pedestrian areas. We introduce our robots and the experimental zone, overview the architecture of the navigation framework, and present the results after 3.5km of autonomous navigation. We expose the main lessons learnt by the scientific team and identify the issues to improve future works.

We present an approach to the problem of 3D map building in urban settings for service robots, using three-dimensional laser range scans as the main data input. Our system is based on the probabilistic alignment of 3D point clouds employing a delayed-state information-form SLAM algorithm, for which we can add observations of relative robot displacements efficiently. These observations come from the alignment of dense range data point clouds computed with a variant of the iterative closest point algorithm. The datasets were acquired with our custom built 3D range scanner integrated into a mobile robot platform. Our mapping results are compared to a GIS-based CAD model of the experimental site. The results show that our approach to 3D mapping performs with sufficient accuracy to derive traversability maps that allow our service robots navigate and accomplish their assigned tasks on a urban pedestrian area.