Torsten Sattler

Gabriele Berton, Riccardo Mereu, Gabriele Trivigno et al.

In this paper, we propose a new open-source benchmarking framework for Visual Geo-localization (VG) that allows to build, train, and test a wide range of commonly used architectures, with the flexibility to change individual components of a geo-localization pipeline. The purpose of this framework is twofold: i) gaining insights into how different components and design choices in a VG pipeline impact the final results, both in terms of performance (recall@N metric) and system requirements (such as execution time and memory consumption); ii) establish a systematic evaluation protocol for comparing different methods. Using the proposed framework, we perform a large suite of experiments which provide criteria for choosing backbone, aggregation and negative mining depending on the use-case and requirements. We also assess the impact of engineering techniques like pre/post-processing, data augmentation and image resizing, showing that better performance can be obtained through somewhat simple procedures: for example, downscaling the images' resolution to 80% can lead to similar results with a 36% savings in extraction time and dataset storage requirement. Code and trained models are available at https://deep-vg-bench.herokuapp.com/.

Martin Humenberger, Yohann Cabon, Noé Pion et al.

Visual localization, i.e., camera pose estimation in a known scene, is a core component of technologies such as autonomous driving and augmented reality. State-of-the-art localization approaches often rely on image retrieval techniques for one of two purposes: (1) provide an approximate pose estimate or (2) determine which parts of the scene are potentially visible in a given query image. It is common practice to use state-of-the-art image retrieval algorithms for both of them. These algorithms are often trained for the goal of retrieving the same landmark under a large range of viewpoint changes which often differs from the requirements of visual localization. In order to investigate the consequences for visual localization, this paper focuses on understanding the role of image retrieval for multiple visual localization paradigms. First, we introduce a novel benchmark setup and compare state-of-the-art retrieval representations on multiple datasets using localization performance as metric. Second, we investigate several definitions of "ground truth" for image retrieval. Using these definitions as upper bounds for the visual localization paradigms, we show that there is still sgnificant room for improvement. Third, using these tools and in-depth analysis, we show that retrieval performance on classical landmark retrieval or place recognition tasks correlates only for some but not all paradigms to localization performance. Finally, we analyze the effects of blur and dynamic scenes in the images. We conclude that there is a need for retrieval approaches specifically designed for localization paradigms. Our benchmark and evaluation protocols are available at https://github.com/naver/kapture-localization.

Zehao Yu, Anpei Chen, Binbin Huang et al.

Recently, 3D Gaussian Splatting has demonstrated impressive novel view synthesis results, reaching high fidelity and efficiency. However, strong artifacts can be observed when changing the sampling rate, \eg, by changing focal length or camera distance. We find that the source for this phenomenon can be attributed to the lack of 3D frequency constraints and the usage of a 2D dilation filter. To address this problem, we introduce a 3D smoothing filter which constrains the size of the 3D Gaussian primitives based on the maximal sampling frequency induced by the input views, eliminating high-frequency artifacts when zooming in. Moreover, replacing 2D dilation with a 2D Mip filter, which simulates a 2D box filter, effectively mitigates aliasing and dilation issues. Our evaluation, including scenarios such a training on single-scale images and testing on multiple scales, validates the effectiveness of our approach.

Zehao Yu, Songyou Peng, Michael Niemeyer et al.

In recent years, neural implicit surface reconstruction methods have become popular for multi-view 3D reconstruction. In contrast to traditional multi-view stereo methods, these approaches tend to produce smoother and more complete reconstructions due to the inductive smoothness bias of neural networks. State-of-the-art neural implicit methods allow for high-quality reconstructions of simple scenes from many input views. Yet, their performance drops significantly for larger and more complex scenes and scenes captured from sparse viewpoints. This is caused primarily by the inherent ambiguity in the RGB reconstruction loss that does not provide enough constraints, in particular in less-observed and textureless areas. Motivated by recent advances in the area of monocular geometry prediction, we systematically explore the utility these cues provide for improving neural implicit surface reconstruction. We demonstrate that depth and normal cues, predicted by general-purpose monocular estimators, significantly improve reconstruction quality and optimization time. Further, we analyse and investigate multiple design choices for representing neural implicit surfaces, ranging from monolithic MLP models over single-grid to multi-resolution grid representations. We observe that geometric monocular priors improve performance both for small-scale single-object as well as large-scale multi-object scenes, independent of the choice of representation.

Aikaterini Adam, Torsten Sattler, Konstantinos Karantzalos et al.

AR/VR applications and robots need to know when the scene has changed. An example is when objects are moved, added, or removed from the scene. We propose a 3D object discovery method that is based only on scene changes. Our method does not need to encode any assumptions about what is an object, but rather discovers objects by exploiting their coherent move. Changes are initially detected as differences in the depth maps and segmented as objects if they undergo rigid motions. A graph cut optimization propagates the changing labels to geometrically consistent regions. Experiments show that our method achieves state-of-the-art performance on the 3RScan dataset against competitive baselines. The source code of our method can be found at https://github.com/katadam/ObjectsCanMove.

Jonáš Kulhánek, Erik Derner, Torsten Sattler et al.

Novel view synthesis is a long-standing problem. In this work, we consider a variant of the problem where we are given only a few context views sparsely covering a scene or an object. The goal is to predict novel viewpoints in the scene, which requires learning priors. The current state of the art is based on Neural Radiance Field (NeRF), and while achieving impressive results, the methods suffer from long training times as they require evaluating millions of 3D point samples via a neural network for each image. We propose a 2D-only method that maps multiple context views and a query pose to a new image in a single pass of a neural network. Our model uses a two-stage architecture consisting of a codebook and a transformer model. The codebook is used to embed individual images into a smaller latent space, and the transformer solves the view synthesis task in this more compact space. To train our model efficiently, we introduce a novel branching attention mechanism that allows us to use the same model not only for neural rendering but also for camera pose estimation. Experimental results on real-world scenes show that our approach is competitive compared to NeRF-based methods while not reasoning explicitly in 3D, and it is faster to train.

Kunal Chelani, Assia Benbihi, Fredrik Kahl et al.

Rapid growth in the popularity of AR/VR/MR applications and cloud-based visual localization systems has given rise to an increased focus on the privacy of user content in the localization process. This privacy concern has been further escalated by the ability of deep neural networks to recover detailed images of a scene from a sparse set of 3D or 2D points and their descriptors - the so-called inversion attacks. Research on privacy-preserving localization has therefore focused on preventing these inversion attacks on both the query image keypoints and the 3D points of the scene map. To this end, several geometry obfuscation techniques that lift points to higher-dimensional spaces, i.e., lines or planes, or that swap coordinates between points % have been proposed. In this paper, we point to a common weakness of these obfuscations that allows to recover approximations of the original point positions under the assumption of known neighborhoods. We further show that these neighborhoods can be computed by learning to identify descriptors that co-occur in neighborhoods. Extensive experiments show that our approach for point recovery is practically applicable to all existing geometric obfuscation schemes. Our results show that these schemes should not be considered privacy-preserving, even though they are claimed to be privacy-preserving. Code will be available at https://github.com/kunalchelani/RecoverPointsNeighborhood.

Vojtech Panek, Zuzana Kukelova, Torsten Sattler

Visual localization, i.e., the problem of camera pose estimation, is a central component of applications such as autonomous robots and augmented reality systems. A dominant approach in the literature, shown to scale to large scenes and to handle complex illumination and seasonal changes, is based on local features extracted from images. The scene representation is a sparse Structure-from-Motion point cloud that is tied to a specific local feature. Switching to another feature type requires an expensive feature matching step between the database images used to construct the point cloud. In this work, we thus explore a more flexible alternative based on dense 3D meshes that does not require features matching between database images to build the scene representation. We show that this approach can achieve state-of-the-art results. We further show that surprisingly competitive results can be obtained when extracting features on renderings of these meshes, without any neural rendering stage, and even when rendering raw scene geometry without color or texture. Our results show that dense 3D model-based representations are a promising alternative to existing representations and point to interesting and challenging directions for future research.

Jonas Kulhanek, Torsten Sattler

Neural Radiance Fields (NeRFs) are a very recent and very popular approach for the problems of novel view synthesis and 3D reconstruction. A popular scene representation used by NeRFs is to combine a uniform, voxel-based subdivision of the scene with an MLP. Based on the observation that a (sparse) point cloud of the scene is often available, this paper proposes to use an adaptive representation based on tetrahedra obtained by Delaunay triangulation instead of uniform subdivision or point-based representations. We show that such a representation enables efficient training and leads to state-of-the-art results. Our approach elegantly combines concepts from 3D geometry processing, triangle-based rendering, and modern neural radiance fields. Compared to voxel-based representations, ours provides more detail around parts of the scene likely to be close to the surface. Compared to point-based representations, our approach achieves better performance. The source code is publicly available at: https://jkulhanek.com/tetra-nerf.

Vladimir Guzov, Julian Chibane, Riccardo Marin et al.

Our world is not static and humans naturally cause changes in their environments through interactions, e.g., opening doors or moving furniture. Modeling changes caused by humans is essential for building digital twins, e.g., in the context of shared physical-virtual spaces (metaverses) and robotics. In order for widespread adoption of such emerging applications, the sensor setup used to capture the interactions needs to be inexpensive and easy-to-use for non-expert users. I.e., interactions should be captured and modeled by simple ego-centric sensors such as a combination of cameras and IMU sensors, not relying on any external cameras or object trackers. Yet, to the best of our knowledge, no work tackling the challenging problem of modeling human-scene interactions via such an ego-centric sensor setup exists. This paper closes this gap in the literature by developing a novel approach that combines visual localization of humans in the scene with contact-based reasoning about human-scene interactions from IMU data. Interestingly, we can show that even without visual observations of the interactions, human-scene contacts and interactions can be realistically predicted from human pose sequences. Our method, iReplica (Interaction Replica), is an essential first step towards the egocentric capture of human interactions and modeling of dynamic scenes, which is required for future AR/VR applications in immersive virtual universes and for training machines to behave like humans. Our code, data and model are available on our project page at http://virtualhumans.mpi-inf.mpg.de/ireplica/

Vojtech Panek, Zuzana Kukelova, Torsten Sattler

Visual localization is a core component in many applications, including augmented reality (AR). Localization algorithms compute the camera pose of a query image w.r.t. a scene representation, which is typically built from images. This often requires capturing and storing large amounts of data, followed by running Structure-from-Motion (SfM) algorithms. An interesting, and underexplored, source of data for building scene representations are 3D models that are readily available on the Internet, e.g., hand-drawn CAD models, 3D models generated from building footprints, or from aerial images. These models allow to perform visual localization right away without the time-consuming scene capturing and model building steps. Yet, it also comes with challenges as the available 3D models are often imperfect reflections of reality. E.g., the models might only have generic or no textures at all, might only provide a simple approximation of the scene geometry, or might be stretched. This paper studies how the imperfections of these models affect localization accuracy. We create a new benchmark for this task and provide a detailed experimental evaluation based on multiple 3D models per scene. We show that 3D models from the Internet show promise as an easy-to-obtain scene representation. At the same time, there is significant room for improvement for visual localization pipelines. To foster research on this interesting and challenging task, we release our benchmark at v-pnk.github.io/cadloc.

Jonas Kulhanek, Songyou Peng, Zuzana Kukelova et al.

While the field of 3D scene reconstruction is dominated by NeRFs due to their photorealistic quality, 3D Gaussian Splatting (3DGS) has recently emerged, offering similar quality with real-time rendering speeds. However, both methods primarily excel with well-controlled 3D scenes, while in-the-wild data - characterized by occlusions, dynamic objects, and varying illumination - remains challenging. NeRFs can adapt to such conditions easily through per-image embedding vectors, but 3DGS struggles due to its explicit representation and lack of shared parameters. To address this, we introduce WildGaussians, a novel approach to handle occlusions and appearance changes with 3DGS. By leveraging robust DINO features and integrating an appearance modeling module within 3DGS, our method achieves state-of-the-art results. We demonstrate that WildGaussians matches the real-time rendering speed of 3DGS while surpassing both 3DGS and NeRF baselines in handling in-the-wild data, all within a simple architectural framework.

Snehal Bhayani, Viktor Larsson, Torsten Sattler et al.

In this paper we study the problem of estimating the semi-generalized pose of a partially calibrated camera, i.e., the pose of a perspective camera with unknown focal length w.r.t. a generalized camera, from a hybrid set of 2D-2D and 2D-3D point correspondences. We study all possible camera configurations within the generalized camera system. To derive practical solvers to previously unsolved challenging configurations, we test different parameterizations as well as different solving strategies based on the state-of-the-art methods for generating efficient polynomial solvers. We evaluate the three most promising solvers, i.e., the H51f solver with five 2D-2D correspondences and one 2D-3D correspondence viewed by the same camera inside generalized camera, the H32f solver with three 2D-2D and two 2D-3D correspondences, and the H13f solver with one 2D-2D and three 2D-3D correspondences, on synthetic and real data. We show that in the presence of noise in the 3D points these solvers provide better estimates than the corresponding absolute pose solvers.

Kunal Chelani, Assia Benbihi, Torsten Sattler et al.

With their meaningful geometry and their omnipresence in the 3D world, edges are extremely useful primitives in computer vision. 3D edges comprise of lines and curves, and methods to reconstruct them use either multi-view images or point clouds as input. State-of-the-art image-based methods first learn a 3D edge point cloud then fit 3D edges to it. The edge point cloud is obtained by learning a 3D neural implicit edge field from which the 3D edge points are sampled on a specific level set (0 or 1). However, such methods present two important drawbacks: i) it is not realistic to sample points on exact level sets due to float imprecision and training inaccuracies. Instead, they are sampled within a range of levels so the points do not lie accurately on the 3D edges and require further processing. ii) Such implicit representations are computationally expensive and require long training times. In this paper, we address these two limitations and propose a 3D edge mapping that is simpler, more efficient, and preserves accuracy. Our method learns explicitly the 3D edge points and their edge direction hence bypassing the need for point sampling. It casts a 3D edge point as the center of a 3D Gaussian and the edge direction as the principal axis of the Gaussian. Such a representation has the advantage of being not only geometrically meaningful but also compatible with the efficient training optimization defined in Gaussian Splatting. Results show that the proposed method produces edges as accurate and complete as the state-of-the-art while being an order of magnitude faster. Code is released at https://github.com/kunalchelani/EdgeGaussians.

Charalambos Tzamos, Viktor Kocur, Yaqing Ding et al.

We study the challenging problem of estimating the relative pose of three calibrated cameras from four point correspondences. We propose novel efficient solutions to this problem that are based on the simple idea of using four correspondences to estimate an approximate geometry of the first two views. We model this geometry either as an affine or a fully perspective geometry estimated using one additional approximate correspondence. We generate such an approximate correspondence using a very simple and efficient strategy, where the new point is the mean point of three corresponding input points. The new solvers are efficient and easy to implement, since they are based on existing efficient minimal solvers, i.e., the 4-point affine fundamental matrix, the well-known 5-point relative pose solver, and the P3P solver. Extensive experiments on real data show that the proposed solvers, when properly coupled with local optimization, achieve state-of-the-art results, with the novel solver based on approximate mean-point correspondences being more robust and accurate than the affine-based solver.

Varun Burde, Assia Benbihi, Pavel Burget et al.

Object pose estimation is essential to many industrial applications involving robotic manipulation, navigation, and augmented reality. Current generalizable object pose estimators, i.e., approaches that do not need to be trained per object, rely on accurate 3D models. Predominantly, CAD models are used, which can be hard to obtain in practice. At the same time, it is often possible to acquire images of an object. Naturally, this leads to the question whether 3D models reconstructed from images are sufficient to facilitate accurate object pose estimation. We aim to answer this question by proposing a novel benchmark for measuring the impact of 3D reconstruction quality on pose estimation accuracy. Our benchmark provides calibrated images for object reconstruction registered with the test images of the YCB-V dataset for pose evaluation under the BOP benchmark format. Detailed experiments with multiple state-of-the-art 3D reconstruction and object pose estimation approaches show that the geometry produced by modern reconstruction methods is often sufficient for accurate pose estimation. Our experiments lead to interesting observations: (1) Standard metrics for measuring 3D reconstruction quality are not necessarily indicative of pose estimation accuracy, which shows the need for dedicated benchmarks such as ours. (2) Classical, non-learning-based approaches can perform on par with modern learning-based reconstruction techniques and can even offer a better reconstruction time-pose accuracy tradeoff. (3) There is still a sizable gap between performance with reconstructed and with CAD models. To foster research on closing this gap, our benchmark is publicly available at https://github.com/VarunBurde/reconstruction_pose_benchmark}.

Vojtech Panek, Patrik Beliansky, Zuzana Kukelova et al.

Visual localization is the task of estimating the camera pose of an image relative to a scene representation. In practice, visual localization systems are often cloud-based. Naturally, this raises privacy concerns in terms of revealing private details through the images sent to the server or through the representations stored on the server. Privacy-preserving localization aims to avoid such leakage of private details. However, the resulting localization approaches are significantly more complex, slower, and less accurate than their non-privacy-preserving counterparts. In this paper, we consider structureless localization methods in the context of privacy preservation. Structureless methods represent the scene through a set of reference images with known camera poses and intrinsics. In contrast to existing methods proposing representations that are as privacy-preserving as possible, we study a simple image obfuscation approach based on common image operations, e.g., replacing RGB images with (semantic) segmentations. We show that existing structureless pipelines do not need any special adjustments, as modern feature matchers can match obfuscated images out of the box. The results are easy-to-implement pipelines that can ensure both the privacy of the query images and the scene representations. Detailed experiments on multiple datasets show that the resulting methods achieve state-of-the-art pose accuracy for privacy-preserving approaches.

Vojtech Panek, Torsten Sattler, Zuzana Kukelova

Visual localization is the problem of estimating the camera pose of a given query image within a known scene. Most state-of-the-art localization approaches follow the structure-based paradigm and use 2D-3D matches between pixels in a query image and 3D points in the scene for pose estimation. These approaches assume an accurate 3D model of the scene, which might not always be available, especially if only a few images are available to compute the scene representation. In contrast, structure-less methods rely on 2D-2D matches and do not require any 3D scene model. However, they are also less accurate than structure-based methods. Although one prior work proposed to combine structure-based and structure-less pose estimation strategies, its practical relevance has not been shown. We analyze combining structure-based and structure-less strategies while exploring how to select between poses obtained from 2D-2D and 2D-3D matches, respectively. We show that combining both strategies improves localization performance in multiple practically relevant scenarios.

Gabriele Trivigno, Carlo Masone, Barbara Caputo et al.

Pose refinement is an interesting and practically relevant research direction. Pose refinement can be used to (1) obtain a more accurate pose estimate from an initial prior (e.g., from retrieval), (2) as pre-processing, i.e., to provide a better starting point to a more expensive pose estimator, (3) as post-processing of a more accurate localizer. Existing approaches focus on learning features / scene representations for the pose refinement task. This involves training an implicit scene representation or learning features while optimizing a camera pose-based loss. A natural question is whether training specific features / representations is truly necessary or whether similar results can be already achieved with more generic features. In this work, we present a simple approach that combines pre-trained features with a particle filter and a renderable representation of the scene. Despite its simplicity, it achieves state-of-the-art results, demonstrating that one can easily build a pose refiner without the need for specific training. The code is at https://github.com/ga1i13o/mcloc_poseref

Viktor Kocur, Sithu Aung, Gabrielle Flood et al.

Monocular depth estimation has improved significantly in recent years, driven by increasingly powerful models and large-scale training data. Predicted depth is increasingly used as an input signal for downstream tasks such as Structure-from-Motion (SfM), visual localization, and SLAM. However, monocular depth estimators (MDEs) are still primarily evaluated in terms of depth accuracy. Standard metrics aggregate errors globally and may not reflect the usefulness of depth for downstream geometric tasks. We therefore propose Depth2Pose, a framework for evaluating MDEs in the context of downstream tasks. By combining depth predictions with feature correspondences in depth-aware geometric solvers, we use relative camera pose estimation accuracy as a task-driven proxy for depth quality. Traditional benchmarks require dense ground truth in the form of per-pixel depth, which is expensive to obtain. In contrast, our formulation requires only camera poses, which can be estimated efficiently, e.g., using Structure-from-Motion pipelines. As a result, our framework can be applied to scenes where ground-truth depth is difficult to obtain, for example due to large scene scale or heavy occlusions (e.g., vegetated environments). Leveraging this, we introduce the D2P dataset, which contains challenging scenes outside the distribution of commonly used training data. We show that methods performing well under standard depth error metrics on existing benchmarks also perform well under our pose-based metric when evaluated on the same datasets, but do not necessarily generalize to our more challenging dataset. Finally, we provide a simple and extensible evaluation framework. The dataset and code are available at kocurvik.github.io/depth2pose.

Jhacson Meza, Martin R. Oswald, Torsten Sattler

Novel view synthesis (NVS) approaches such as NeRFs or 3DGS can produce photo-realistic 3D scene representation from a set of images with known extrinsic and intrinsic parameters. The necessary camera poses and calibrations are typically obtained from the images via Structure-from-Motion (SfM). Classical SfM approaches rely on local feature matches between the images to estimate both the poses and a sparse 3D model of the scene, using bundle adjustment to refine initial pose, intrinsics, and geometry estimates. In order to increase run-time efficiency, recent SfM systems forgo optimization via bundle adjustment. Instead, they train feed-forward (transformer-based) neural networks to directly regress camera parameters and the 3D structure. While orders of magnitude more efficient, such recent works produce significantly less accurate estimates. To stimulate research on developing SfM approaches that are both efficient \emph{and} effective, this paper develops a benchmark focused on SfM for novel view synthesis. Using existing datasets and two simple strategies for making the reconstruction process more efficient, we show that: (1) simply using fewer features already significantly accelerates classical SfM methods while maintaining high pose accuracy. (2) using feed-forward networks to obtain initial estimates and refining them using classical SfM techniques leads to the best efficiency-effectiveness trade-off. We will make our benchmark and code publicly available.

Zehao Yu, Torsten Sattler, Andreas Geiger

Recently, 3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results, while allowing the rendering of high-resolution images in real-time. However, leveraging 3D Gaussians for surface reconstruction poses significant challenges due to the explicit and disconnected nature of 3D Gaussians. In this work, we present Gaussian Opacity Fields (GOF), a novel approach for efficient, high-quality, and adaptive surface reconstruction in unbounded scenes. Our GOF is derived from ray-tracing-based volume rendering of 3D Gaussians, enabling direct geometry extraction from 3D Gaussians by identifying its levelset, without resorting to Poisson reconstruction or TSDF fusion as in previous work. We approximate the surface normal of Gaussians as the normal of the ray-Gaussian intersection plane, enabling the application of regularization that significantly enhances geometry. Furthermore, we develop an efficient geometry extraction method utilizing Marching Tetrahedra, where the tetrahedral grids are induced from 3D Gaussians and thus adapt to the scene's complexity. Our evaluations reveal that GOF surpasses existing 3DGS-based methods in surface reconstruction and novel view synthesis. Further, it compares favorably to or even outperforms, neural implicit methods in both quality and speed.

Simona Kocour, Assia Benbihi, Torsten Sattler

Understanding what semantic information persists after object removal is critical for privacy-preserving 3D reconstruction and editable scene representations. In this work, we introduce a novel benchmark and evaluation framework to measure semantic residuals, the unintended semantic traces left behind, after object removal in 3D Gaussian Splatting. We conduct experiments across a diverse set of indoor and outdoor scenes, showing that current methods can preserve semantic information despite the absence of visual geometry. We also release Remove360, a dataset of pre/post-removal RGB images and object-level masks captured in real-world environments. While prior datasets have focused on isolated object instances, Remove360 covers a broader and more complex range of indoor and outdoor scenes, enabling evaluation of object removal in the context of full-scene representations. Given ground truth images of a scene before and after object removal, we assess whether we can truly eliminate semantic presence, and if downstream models can still infer what was removed. Our findings reveal critical limitations in current 3D object removal techniques and underscore the need for more robust solutions capable of handling real-world complexity. The evaluation framework is available at github.com/spatial-intelligence-ai/Remove360.git. Data are available at huggingface.co/datasets/simkoc/Remove360.

Viktor Kocur, Charalambos Tzamos, Yaqing Ding et al.

Estimating the relative pose between two cameras is a fundamental step in many applications such as Structure-from-Motion. The common approach to relative pose estimation is to apply a minimal solver inside a RANSAC loop. Highly efficient solvers exist for pinhole cameras. Yet, (nearly) all cameras exhibit radial distortion. Not modeling radial distortion leads to (significantly) worse results. However, minimal radial distortion solvers are significantly more complex than pinhole solvers, both in terms of run-time and implementation efforts. This paper compares radial distortion solvers with two simple-to-implement approaches that do not use minimal radial distortion solvers: The first approach combines an efficient pinhole solver with sampled radial undistortion parameters, where the sampled parameters are used for undistortion prior to applying the pinhole solver. The second approach uses a state-of-the-art neural network to estimate the distortion parameters rather than sampling them from a set of potential values. Extensive experiments on multiple datasets, and different camera setups, show that complex minimal radial distortion solvers are not necessary in practice. We discuss under which conditions a simple sampling of radial undistortion parameters is preferable over calibrating cameras using a learning-based prior approach. Code and newly created benchmark for relative pose estimation under radial distortion are available at https://github.com/kocurvik/rdnet.

Paul-Edouard Sarlin, Ajaykumar Unagar, Måns Larsson et al.

Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, from an input image. This either fails to generalize to new viewpoints or ties the model parameters to a specific scene. In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms. We introduce PixLoc, a scene-agnostic neural network that estimates an accurate 6-DoF pose from an image and a 3D model. Our approach is based on the direct alignment of multiscale deep features, casting camera localization as metric learning. PixLoc learns strong data priors by end-to-end training from pixels to pose and exhibits exceptional generalization to new scenes by separating model parameters and scene geometry. The system can localize in large environments given coarse pose priors but also improve the accuracy of sparse feature matching by jointly refining keypoints and poses with little overhead. The code will be publicly available at https://github.com/cvg/pixloc.

Kunal Chelani, Fredrik Kahl, Torsten Sattler

Visual localization is the problem of estimating the camera pose of a given image with respect to a known scene. Visual localization algorithms are a fundamental building block in advanced computer vision applications, including Mixed and Virtual Reality systems. Many algorithms used in practice represent the scene through a Structure-from-Motion (SfM) point cloud and use 2D-3D matches between a query image and the 3D points for camera pose estimation. As recently shown, image details can be accurately recovered from SfM point clouds by translating renderings of the sparse point clouds to images. To address the resulting potential privacy risks for user-generated content, it was recently proposed to lift point clouds to line clouds by replacing 3D points by randomly oriented 3D lines passing through these points. The resulting representation is unintelligible to humans and effectively prevents point cloud-to-image translation. This paper shows that a significant amount of information about the 3D scene geometry is preserved in these line clouds, allowing us to (approximately) recover the 3D point positions and thus to (approximately) recover image content. Our approach is based on the observation that the closest points between lines can yield a good approximation to the original 3D points. Code is available at https://github.com/kunalchelani/Line2Point.

Qunjie Zhou, Torsten Sattler, Laura Leal-Taixe

The classical matching pipeline used for visual localization typically involves three steps: (i) local feature detection and description, (ii) feature matching, and (iii) outlier rejection. Recently emerged correspondence networks propose to perform those steps inside a single network but suffer from low matching resolution due to the memory bottleneck. In this work, we propose a new perspective to estimate correspondences in a detect-to-refine manner, where we first predict patch-level match proposals and then refine them. We present Patch2Pix, a novel refinement network that refines match proposals by regressing pixel-level matches from the local regions defined by those proposals and jointly rejecting outlier matches with confidence scores. Patch2Pix is weakly supervised to learn correspondences that are consistent with the epipolar geometry of an input image pair. We show that our refinement network significantly improves the performance of correspondence networks on image matching, homography estimation, and localization tasks. In addition, we show that our learned refinement generalizes to fully-supervised methods without re-training, which leads us to state-of-the-art localization performance. The code is available at https://github.com/GrumpyZhou/patch2pix.

Noé Pion, Martin Humenberger, Gabriela Csurka et al.

Visual localization, i.e., camera pose estimation in a known scene, is a core component of technologies such as autonomous driving and augmented reality. State-of-the-art localization approaches often rely on image retrieval techniques for one of two tasks: (1) provide an approximate pose estimate or (2) determine which parts of the scene are potentially visible in a given query image. It is common practice to use state-of-the-art image retrieval algorithms for these tasks. These algorithms are often trained for the goal of retrieving the same landmark under a large range of viewpoint changes. However, robustness to viewpoint changes is not necessarily desirable in the context of visual localization. This paper focuses on understanding the role of image retrieval for multiple visual localization tasks. We introduce a benchmark setup and compare state-of-the-art retrieval representations on multiple datasets. We show that retrieval performance on classical landmark retrieval/recognition tasks correlates only for some but not all tasks to localization performance. This indicates a need for retrieval approaches specifically designed for localization tasks. Our benchmark and evaluation protocols are available at https://github.com/naver/kapture-localization.

Jonathan Ventura, Zuzana Kukelova, Torsten Sattler et al.

Affine correspondences have traditionally been used to improve feature matching over wide baselines. While recent work has successfully used affine correspondences to solve various relative camera pose estimation problems, less attention has been given to their use in absolute pose estimation. We introduce the first general solution to the problem of estimating the pose of a calibrated camera given a single observation of an oriented point and an affine correspondence. The advantage of our approach (P1AC) is that it requires only a single correspondence, in comparison to the traditional point-based approach (P3P), significantly reducing the combinatorics in robust estimation. P1AC provides a general solution that removes restrictive assumptions made in prior work and is applicable to large-scale image-based localization. We propose a minimal solution to the P1AC problem and evaluate our novel solver on synthetic data, showing its numerical stability and performance under various types of noise. On standard image-based localization benchmarks we show that P1AC achieves more accurate results than the widely used P3P algorithm. Code for our method is available at https://github.com/jonathanventura/P1AC/ .

Yukai Lin, Viktor Larsson, Marcel Geppert et al.

Multi-camera systems are an important sensor platform for intelligent systems such as self-driving cars. Pattern-based calibration techniques can be used to calibrate the intrinsics of the cameras individually. However, extrinsic calibration of systems with little to no visual overlap between the cameras is a challenge. Given the camera intrinsics, infrastucture-based calibration techniques are able to estimate the extrinsics using 3D maps pre-built via SLAM or Structure-from-Motion. In this paper, we propose to fully calibrate a multi-camera system from scratch using an infrastructure-based approach. Assuming that the distortion is mainly radial, we introduce a two-stage approach. We first estimate the camera-rig extrinsics up to a single unknown translation component per camera. Next, we solve for both the intrinsic parameters and the missing translation components. Extensive experiments on multiple indoor and outdoor scenes with multiple multi-camera systems show that our calibration method achieves high accuracy and robustness. In particular, our approach is more robust than the naive approach of first estimating intrinsic parameters and pose per camera before refining the extrinsic parameters of the system. The implementation is available at https://github.com/youkely/InfrasCal.

Daniel Barath, Michal Polic, Wolfgang Förstner et al.

Local features e.g. SIFT and its affine and learned variants provide region-to-region rather than point-to-point correspondences. This has recently been exploited to create new minimal solvers for classical problems such as homography, essential and fundamental matrix estimation. The main advantage of such solvers is that their sample size is smaller, e.g., only two instead of four matches are required to estimate a homography. Works proposing such solvers often claim a significant improvement in run-time thanks to fewer RANSAC iterations. We show that this argument is not valid in practice if the solvers are used naively. To overcome this, we propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. We propose a method for refining the local feature geometries by symmetric intensity-based matching, combine uncertainty propagation inside RANSAC with preemptive model verification, show a general scheme for computing uncertainty of minimal solvers results, and adapt the sample cheirality check for homography estimation. Our experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times when following our guidelines. We make code available at https://github.com/danini/affine-correspondences-for-camera-geometry.

Thomas Schöps, Viktor Larsson, Marc Pollefeys et al.

Camera calibration is an essential first step in setting up 3D Computer Vision systems. Commonly used parametric camera models are limited to a few degrees of freedom and thus often do not optimally fit to complex real lens distortion. In contrast, generic camera models allow for very accurate calibration due to their flexibility. Despite this, they have seen little use in practice. In this paper, we argue that this should change. We propose a calibration pipeline for generic models that is fully automated, easy to use, and can act as a drop-in replacement for parametric calibration, with a focus on accuracy. We compare our results to parametric calibrations. Considering stereo depth estimation and camera pose estimation as examples, we show that the calibration error acts as a bias on the results. We thus argue that in contrast to current common practice, generic models should be preferred over parametric ones whenever possible. To facilitate this, we released our calibration pipeline at https://github.com/puzzlepaint/camera_calibration, making both easy-to-use and accurate camera calibration available to everyone.

Thomas Schöps, Torsten Sattler, Marc Pollefeys

We address the problem of mesh reconstruction from live RGB-D video, assuming a calibrated camera and poses provided externally (e.g., by a SLAM system). In contrast to most existing approaches, we do not fuse depth measurements in a volume but in a dense surfel cloud. We asynchronously (re)triangulate the smoothed surfels to reconstruct a surface mesh. This novel approach enables to maintain a dense surface representation of the scene during SLAM which can quickly adapt to loop closures. This is possible by deforming the surfel cloud and asynchronously remeshing the surface where necessary. The surfel-based representation also naturally supports strongly varying scan resolution. In particular, it reconstructs colors at the input camera's resolution. Moreover, in contrast to many volumetric approaches, ours can reconstruct thin objects since objects do not need to enclose a volume. We demonstrate our approach in a number of experiments, showing that it produces reconstructions that are competitive with the state-of-the-art, and we discuss its advantages and limitations. The algorithm (excluding loop closure functionality) is available as open source at https://github.com/puzzlepaint/surfelmeshing .

Ivan Desiatov, Torsten Sattler

3D Gaussian Splatting (3DGS) has become the method of choice for photo-realistic 3D reconstruction of scenes, due to being able to efficiently and accurately recover the scene appearance and geometry from images. 3DGS represents the scene through a set of 3D Gaussians, parameterized by their position, spatial extent, and view-dependent color. Starting from an initial point cloud, 3DGS refines the Gaussians' parameters as to reconstruct a set of training images as accurately as possible. Typically, a sparse Structure-from-Motion point cloud is used as initialization. In order to obtain dense Gaussian clouds, 3DGS methods thus rely on a densification stage. In this paper, we systematically study the relation between densification and initialization. Proposing a new benchmark, we study combinations of different types of initializations (dense laser scans, dense (multi-view) stereo point clouds, dense monocular depth estimates, sparse SfM point clouds) and different densification schemes. We show that current densification approaches are not able to take full advantage of dense initialization as they are often unable to (significantly) improve over sparse SfM-based initialization. We will make our benchmark publicly available.

Varun Burde, Pavel Burget, Torsten Sattler

3D reconstruction serves as the foundational layer for numerous robotic perception tasks, including 6D object pose estimation and grasp pose generation. Modern 3D reconstruction methods for objects can produce visually and geometrically impressive meshes from multi-view images, yet standard geometric evaluations do not reflect how reconstruction quality influences downstream tasks such as robotic manipulation performance. This paper addresses this gap by introducing a large-scale, physics-based benchmark that evaluates 6D pose estimators and 3D mesh models based on their functional efficacy in grasping. We analyze the impact of model fidelity by generating grasps on various reconstructed 3D meshes and executing them on the ground-truth model, simulating how grasp poses generated with an imperfect model affect interaction with the real object. This assesses the combined impact of pose error, grasp robustness, and geometric inaccuracies from 3D reconstruction. Our results show that reconstruction artifacts significantly decrease the number of grasp pose candidates but have a negligible effect on grasping performance given an accurately estimated pose. Our results also reveal that the relationship between grasp success and pose error is dominated by spatial error, and even a simple translation error provides insight into the success of the grasping pose of symmetric objects. This work provides insight into how perception systems relate to object manipulation using robots.

Jonas Kulhanek, Marie-Julie Rakotosaona, Fabian Manhardt et al.

In this work, we present a novel level-of-detail (LOD) method for 3D Gaussian Splatting that enables real-time rendering of large-scale scenes on memory-constrained devices. Our approach introduces a hierarchical LOD representation that iteratively selects optimal subsets of Gaussians based on camera distance, thus largely reducing both rendering time and GPU memory usage. We construct each LOD level by applying a depth-aware 3D smoothing filter, followed by importance-based pruning and fine-tuning to maintain visual fidelity. To further reduce memory overhead, we partition the scene into spatial chunks and dynamically load only relevant Gaussians during rendering, employing an opacity-blending mechanism to avoid visual artifacts at chunk boundaries. Our method achieves state-of-the-art performance on both outdoor (Hierarchical 3DGS) and indoor (Zip-NeRF) datasets, delivering high-quality renderings with reduced latency and memory requirements.

Maxime Pietrantoni, Gabriela Csurka, Torsten Sattler

Visual localization is the task of estimating a camera pose in a known environment. In this paper, we utilize 3D Gaussian Splatting (3DGS)-based representations for accurate and privacy-preserving visual localization. We propose Gaussian Splatting Feature Fields (GSFFs), a scene representation for visual localization that combines an explicit geometry model (3DGS) with an implicit feature field. We leverage the dense geometric information and differentiable rasterization algorithm from 3DGS to learn robust feature representations grounded in 3D. In particular, we align a 3D scale-aware feature field and a 2D feature encoder in a common embedding space through a contrastive framework. Using a 3D structure-informed clustering procedure, we further regularize the representation learning and seamlessly convert the features to segmentations, which can be used for privacy-preserving visual localization. Pose refinement, which involves aligning either feature maps or segmentations from a query image with those rendered from the GSFFs scene representation, is used to achieve localization. The resulting privacy- and non-privacy-preserving localization pipelines, evaluated on multiple real-world datasets, show state-of-the-art performances.

Vojtech Panek, Qunjie Zhou, Yaqing Ding et al.

Visual localization algorithms, i.e., methods that estimate the camera pose of a query image in a known scene, are core components of many applications, including self-driving cars and augmented / mixed reality systems. State-of-the-art visual localization algorithms are structure-based, i.e., they store a 3D model of the scene and use 2D-3D correspondences between the query image and 3D points in the model for camera pose estimation. While such approaches are highly accurate, they are also rather inflexible when it comes to adjusting the underlying 3D model after changes in the scene. Structureless localization approaches represent the scene as a database of images with known poses and thus offer a much more flexible representation that can be easily updated by adding or removing images. Although there is a large amount of literature on structure-based approaches, there is significantly less work on structureless methods. Hence, this paper is dedicated to providing the, to the best of our knowledge, first comprehensive discussion and comparison of structureless methods. Extensive experiments show that approaches that use a higher degree of classical geometric reasoning generally achieve higher pose accuracy. In particular, approaches based on classical absolute or semi-generalized relative pose estimation outperform very recent methods based on pose regression by a wide margin. Compared with state-of-the-art structure-based approaches, the flexibility of structureless methods comes at the cost of (slightly) lower pose accuracy, indicating an interesting direction for future work.

Yaqing Ding, Viktor Kocur, Václav Vávra et al.

Recent advances in monocular depth estimation methods (MDE) and their improved accuracy open new possibilities for their applications. In this paper, we investigate how monocular depth estimates can be used for relative pose estimation. In particular, we are interested in answering the question whether using MDEs improves results over traditional point-based methods. We propose a novel framework for estimating the relative pose of two cameras from point correspondences with associated monocular depths. Since depth predictions are typically defined up to an unknown scale or even both unknown scale and shift parameters, our solvers jointly estimate the scale or both the scale and shift parameters along with the relative pose. We derive efficient solvers considering different types of depths for three camera configurations: (1) two calibrated cameras, (2) two cameras with an unknown shared focal length, and (3) two cameras with unknown different focal lengths. Our new solvers outperform state-of-the-art depth-aware solvers in terms of speed and accuracy. In extensive real experiments on multiple datasets and with various MDEs, we discuss which depth-aware solvers are preferable in which situation. The code will be made publicly available.

Maxime Pietrantoni, Martin Humenberger, Torsten Sattler et al.

Visual localization (VL) is the task of estimating the camera pose in a known scene. VL methods, a.o., can be distinguished based on how they represent the scene, e.g., explicitly through a (sparse) point cloud or a collection of images or implicitly through the weights of a neural network. Recently, NeRF-based methods have become popular for VL. While NeRFs offer high-quality novel view synthesis, they inadvertently encode fine scene details, raising privacy concerns when deployed in cloud-based localization services as sensitive information could be recovered. In this paper, we tackle this challenge on two ends. We first propose a new protocol to assess privacy-preservation of NeRF-based representations. We show that NeRFs trained with photometric losses store fine-grained details in their geometry representations, making them vulnerable to privacy attacks, even if the head that predicts colors is removed. Second, we propose ppNeSF (Privacy-Preserving Neural Segmentation Field), a NeRF variant trained with segmentation supervision instead of RGB images. These segmentation labels are learned in a self-supervised manner, ensuring they are coarse enough to obscure identifiable scene details while remaining discriminativeness in 3D. The segmentation space of ppNeSF can be used for accurate visual localization, yielding state-of-the-art results.

Shuo Sun, Torsten Sattler, Malcolm Mielle et al.

Accurate and robust 3D scene reconstruction from casual, in-the-wild videos can significantly simplify robot deployment to new environments. However, reliable camera pose estimation and scene reconstruction from such unconstrained videos remains an open challenge. Existing visual-only SLAM methods perform well on benchmark datasets but struggle with real-world footage which often exhibits uncontrolled motion including rapid rotations and pure forward movements, textureless regions, and dynamic objects. We analyze the limitations of current methods and introduce a robust pipeline designed to improve 3D reconstruction from casual videos. We build upon recent deep visual odometry methods but increase robustness in several ways. Camera intrinsics are automatically recovered from the first few frames using structure-from-motion. Dynamic objects and less-constrained areas are masked with a predictive model. Additionally, we leverage monocular depth estimates to regularize bundle adjustment, mitigating errors in low-parallax situations. Finally, we integrate place recognition and loop closure to reduce long-term drift and refine both intrinsics and pose estimates through global bundle adjustment. We demonstrate large-scale contiguous 3D models from several online videos in various environments. In contrast, baseline methods typically produce locally inconsistent results at several points, producing separate segments or distorted maps. In lieu of ground-truth pose data, we evaluate map consistency, execution time and visual accuracy of re-rendered NeRF models. Our proposed system establishes a new baseline for visual reconstruction from casual uncontrolled videos found online, demonstrating more consistent reconstructions over longer sequences of in-the-wild videos than previously achieved.

Simona Kocour, Assia Benbihi, Aikaterini Adam et al.

Searching in and editing 3D scenes has become extremely intuitive with trainable scene representations that allow linking human concepts to elements in the scene. These operations are often evaluated on the basis of how accurately the searched element is segmented or extracted from the scene. In this paper, we address the inverse problem, that is, how much of the searched element remains in the scene after it is removed. This question is particularly important in the context of privacy-preserving mapping when a user reconstructs a 3D scene and wants to remove private elements before sharing the map. To the best of our knowledge, this is the first work to address this question. To answer this, we propose a quantitative evaluation that measures whether a removal operation leaves object residuals that can be reasoned over. The scene is not private when such residuals are present. Experiments on state-of-the-art scene representations show that the proposed metrics are meaningful and consistent with the user study that we also present. We also propose a method to refine the removal based on spatial and semantic consistency.

Jonas Kulhanek, Torsten Sattler

Novel view synthesis is an important problem with many applications, including AR/VR, gaming, and robotic simulations. With the recent rapid development of Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) methods, it is becoming difficult to keep track of the current state of the art (SoTA) due to methods using different evaluation protocols, codebases being difficult to install and use, and methods not generalizing well to novel 3D scenes. In our experiments, we show that even tiny differences in the evaluation protocols of various methods can artificially boost the performance of these methods. This raises questions about the validity of quantitative comparisons performed in the literature. To address these questions, we propose NerfBaselines, an evaluation framework which provides consistent benchmarking tools, ensures reproducibility, and simplifies the installation and use of various methods. We validate our implementation experimentally by reproducing the numbers reported in the original papers. For improved accessibility, we release a web platform that compares commonly used methods on standard benchmarks. We strongly believe NerfBaselines is a valuable contribution to the community as it ensures that quantitative results are comparable and thus truly measure progress in the field of novel view synthesis.

Maxime Pietrantoni, Gabriela Csurka, Martin Humenberger et al.

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.

Kunal Chelani, Torsten Sattler, Fredrik Kahl et al.

Visual localization is the task of estimating the camera pose from which a given image was taken and is central to several 3D computer vision applications. With the rapid growth in the popularity of AR/VR/MR devices and cloud-based applications, privacy issues are becoming a very important aspect of the localization process. Existing work on privacy-preserving localization aims to defend against an attacker who has access to a cloud-based service. In this paper, we show that an attacker can learn about details of a scene without any access by simply querying a localization service. The attack is based on the observation that modern visual localization algorithms are robust to variations in appearance and geometry. While this is in general a desired property, it also leads to algorithms localizing objects that are similar enough to those present in a scene. An attacker can thus query a server with a large enough set of images of objects, \eg, obtained from the Internet, and some of them will be localized. The attacker can thus learn about object placements from the camera poses returned by the service (which is the minimal information returned by such a service). In this paper, we develop a proof-of-concept version of this attack and demonstrate its practical feasibility. The attack does not place any requirements on the localization algorithm used, and thus also applies to privacy-preserving representations. Current work on privacy-preserving representations alone is thus insufficient.

Ara Jafarzadeh, Manuel Lopez Antequera, Pau Gargallo et al.

Visual localization is the problem of estimating the position and orientation from which a given image (or a sequence of images) is taken in a known scene. It is an important part of a wide range of computer vision and robotics applications, from self-driving cars to augmented/virtual reality systems. Visual localization techniques should work reliably and robustly under a wide range of conditions, including seasonal, weather, illumination and man-made changes. Recent benchmarking efforts model this by providing images under different conditions, and the community has made rapid progress on these datasets since their inception. However, they are limited to a few geographical regions and often recorded with a single device. We propose a new benchmark for visual localization in outdoor scenes, using crowd-sourced data to cover a wide range of geographical regions and camera devices with a focus on the failure cases of current algorithms. Experiments with state-of-the-art localization approaches show that our dataset is very challenging, with all evaluated methods failing on its hardest parts. As part of the dataset release, we provide the tooling used to generate it, enabling efficient and effective 2D correspondence annotation to obtain reference poses.

Eric Brachmann, Martin Humenberger, Carsten Rother et al.

Benchmark datasets that measure camera pose accuracy have driven progress in visual re-localisation research. To obtain poses for thousands of images, it is common to use a reference algorithm to generate pseudo ground truth. Popular choices include Structure-from-Motion (SfM) and Simultaneous-Localisation-and-Mapping (SLAM) using additional sensors like depth cameras if available. Re-localisation benchmarks thus measure how well each method replicates the results of the reference algorithm. This begs the question whether the choice of the reference algorithm favours a certain family of re-localisation methods. This paper analyzes two widely used re-localisation datasets and shows that evaluation outcomes indeed vary with the choice of the reference algorithm. We thus question common beliefs in the re-localisation literature, namely that learning-based scene coordinate regression outperforms classical feature-based methods, and that RGB-D-based methods outperform RGB-based methods. We argue that any claims on ranking re-localisation methods should take the type of the reference algorithm, and the similarity of the methods to the reference algorithm, into account.

Vladimir Guzov, Aymen Mir, Torsten Sattler et al.

We introduce (HPS) Human POSEitioning System, a method to recover the full 3D pose of a human registered with a 3D scan of the surrounding environment using wearable sensors. Using IMUs attached at the body limbs and a head mounted camera looking outwards, HPS fuses camera based self-localization with IMU-based human body tracking. The former provides drift-free but noisy position and orientation estimates while the latter is accurate in the short-term but subject to drift over longer periods of time. We show that our optimization-based integration exploits the benefits of the two, resulting in pose accuracy free of drift. Furthermore, we integrate 3D scene constraints into our optimization, such as foot contact with the ground, resulting in physically plausible motion. HPS complements more common third-person-based 3D pose estimation methods. It allows capturing larger recording volumes and longer periods of motion, and could be used for VR/AR applications where humans interact with the scene without requiring direct line of sight with an external camera, or to train agents that navigate and interact with the environment based on first-person visual input, like real humans. With HPS, we recorded a dataset of humans interacting with large 3D scenes (300-1000 sq.m) consisting of 7 subjects and more than 3 hours of diverse motion. The dataset, code and video will be available on the project page: http://virtualhumans.mpi-inf.mpg.de/hps/ .

Snehal Bhayani, Torsten Sattler, Daniel Barath et al.

In this paper, we propose the first minimal solutions for estimating the semi-generalized homography given a perspective and a generalized camera. The proposed solvers use five 2D-2D image point correspondences induced by a scene plane. One of them assumes the perspective camera to be fully calibrated, while the other solver estimates the unknown focal length together with the absolute pose parameters. This setup is particularly important in structure-from-motion and image-based localization pipelines, where a new camera is localized in each step with respect to a set of known cameras and 2D-3D correspondences might not be available. As a consequence of a clever parametrization and the elimination ideal method, our approach only needs to solve a univariate polynomial of degree five or three. The proposed solvers are stable and efficient as demonstrated by a number of synthetic and real-world experiments.

Carl Toft, Daniyar Turmukhambetov, Torsten Sattler et al.

Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines. The problem is that viewing angle and distance severely impact the recognizability of a local feature. Attempts to improve appearance invariance by choosing better local feature points or by leveraging outside information, have come with pre-requisites that made some of them impractical. In this paper, we propose a surprisingly effective enhancement to local feature extraction, which improves matching. We show that CNN-based depths inferred from single RGB images are quite helpful, despite their flaws. They allow us to pre-warp images and rectify perspective distortions, to significantly enhance SIFT and BRISK features, enabling more good matches, even when cameras are looking at the same scene but in opposite directions.