We introduce a novel neural volumetric pose feature, termed PoseMap, designed to enhance camera localization by encapsulating the information between images and the associated camera poses. Our framework leverages an Absolute Pose Regression (APR) architecture, together with an augmented NeRF module. This integration not only facilitates the generation of novel views to enrich the training dataset but also enables the learning of effective pose features. Additionally, we extend our architecture for self-supervised online alignment, allowing our method to be used and fine-tuned for unlabelled images within a unified framework. Experiments demonstrate that our method achieves 14.28% and 20.51% performance gain on average in indoor and outdoor benchmark scenes, outperforming existing APR methods with state-of-the-art accuracy.
Camera localization methods based on retrieval, local feature matching, and 3D structure-based pose estimation are accurate but require high storage, are slow, and are not privacy-preserving. A method based on scene landmark detection (SLD) was recently proposed to address these limitations. It involves training a convolutional neural network (CNN) to detect a few predetermined, salient, scene-specific 3D points or landmarks and computing camera pose from the associated 2D-3D correspondences. Although SLD outperformed existing learning-based approaches, it was notably less accurate than 3D structure-based methods. In this paper, we show that the accuracy gap was due to insufficient model capacity and noisy labels during training. To mitigate the capacity issue, we propose to split the landmarks into subgroups and train a separate network for each subgroup. To generate better training labels, we propose using dense reconstructions to estimate visibility of scene landmarks. Finally, we present a compact architecture to improve memory efficiency. Accuracy wise, our approach is on par with state of the art structure based methods on the INDOOR-6 dataset but runs significantly faster and uses less storage. Code and models can be found at https://github.com/microsoft/SceneLandmarkLocalization.
Current techniques in Visual Simultaneous Localization and Mapping (VSLAM) estimate camera displacement by comparing image features of consecutive scenes. These algorithms depend on scene continuity, hence requires frequent camera inputs. However, processing images frequently can lead to significant memory usage and computation overhead. In this study, we introduce SemanticSLAM, an end-to-end visual-inertial odometry system that utilizes semantic features extracted from an RGB-D sensor. This approach enables the creation of a semantic map of the environment and ensures reliable camera localization. SemanticSLAM is scene-agnostic, which means it doesn't require retraining for different environments. It operates effectively in indoor settings, even with infrequent camera input, without prior knowledge. The strength of SemanticSLAM lies in its ability to gradually refine the semantic map and improve pose estimation. This is achieved by a convolutional long-short-term-memory (ConvLSTM) network, trained to correct errors during map construction. Compared to existing VSLAM algorithms, SemanticSLAM improves pose estimation by 17%. The resulting semantic map provides interpretable information about the environment and can be easily applied to various downstream tasks, such as path planning, obstacle avoidance, and robot navigation. The code will be publicly available at https://github.com/Leomingyangli/SemanticSLAM
Local image feature descriptors have had a tremendous impact on the development and application of computer vision methods. It is therefore unsurprising that significant efforts are being made for learning-based image point descriptors. However, the advantage of learned methods over handcrafted methods in real applications is subtle and more nuanced than expected. Moreover, handcrafted descriptors such as SIFT and SURF still perform better point localization in Structure-from-Motion (SfM) compared to many learned counterparts. In this paper, we propose a very simple and effective approach to learning local image descriptors by using a hand-crafted detector and descriptor. Specifically, we choose to learn only the descriptors, supported by handcrafted descriptors while discarding the point localization head. We optimize the final descriptor by leveraging the knowledge already present in the handcrafted descriptor. Such an approach of optimization allows us to discard learning knowledge already present in non-differentiable functions such as the hand-crafted descriptors and only learn the residual knowledge in the main network branch. This offers 50X convergence speed compared to the standard baseline architecture of SuperPoint while at inference the combined descriptor provides superior performance over the learned and hand-crafted descriptors. This is done with minor increase in the computations over the baseline learned descriptor. Our approach has potential applications in ensemble learning and learning with non-differentiable functions. We perform experiments in matching, camera localization and Structure-from-Motion in order to showcase the advantages of our approach.
Cross-view image matching for geo-localisation is a challenging problem due to the significant visual difference between aerial and ground-level viewpoints. The method provides localisation capabilities from geo-referenced images, eliminating the need for external devices or costly equipment. This enhances the capacity of agents to autonomously determine their position, navigate, and operate effectively in GNSS-denied environments. Current research employs a variety of techniques to reduce the domain gap such as applying polar transforms to aerial images or synthesising between perspectives. However, these approaches generally rely on having a 360{\deg} field of view, limiting real-world feasibility. We propose BEV-CV, an approach introducing two key novelties with a focus on improving the real-world viability of cross-view geo-localisation. Firstly bringing ground-level images into a semantic Birds-Eye-View before matching embeddings, allowing for direct comparison with aerial image representations. Secondly, we adapt datasets into application realistic format - limited Field-of-View images aligned to vehicle direction. BEV-CV achieves state-of-the-art recall accuracies, improving Top-1 rates of 70{\deg} crops of CVUSA and CVACT by 23% and 24% respectively. Also decreasing computational requirements by reducing floating point operations to below previous works, and decreasing embedding dimensionality by 33% - together allowing for faster localisation capabilities.
With the widespread use of NeRF-based implicit 3D representation, the need for camera localization in the same representation becomes manifestly apparent. Doing so not only simplifies the localization process -- by avoiding an outside-the-NeRF-based localization -- but also has the potential to offer the benefit of enhanced localization. This paper studies the problem of localizing cameras in NeRF using a diffusion model for camera pose adjustment. More specifically, given a pre-trained NeRF model, we train a diffusion model that iteratively updates randomly initialized camera poses, conditioned upon the image to be localized. At test time, a new camera is localized in two steps: first, coarse localization using the proposed pose diffusion process, followed by local refinement steps of a pose inversion process in NeRF. In fact, the proposed camera localization by pose diffusion (CaLDiff) method also integrates the pose inversion steps within the diffusion process. Such integration offers significantly better localization, thanks to our downstream refinement-aware diffusion process. Our exhaustive experiments on challenging real-world data validate our method by providing significantly better results than the compared methods and the established baselines. Our source code will be made publicly available.
The existence of variable factors within the environment can cause a decline in camera localization accuracy, as it violates the fundamental assumption of a static environment in Simultaneous Localization and Mapping (SLAM) algorithms. Recent semantic SLAM systems towards dynamic environments either rely solely on 2D semantic information, or solely on geometric information, or combine their results in a loosely integrated manner. In this research paper, we introduce 3DS-SLAM, 3D Semantic SLAM, tailored for dynamic scenes with visual 3D object detection. The 3DS-SLAM is a tightly-coupled algorithm resolving both semantic and geometric constraints sequentially. We designed a 3D part-aware hybrid transformer for point cloud-based object detection to identify dynamic objects. Subsequently, we propose a dynamic feature filter based on HDBSCAN clustering to extract objects with significant absolute depth differences. When compared against ORB-SLAM2, 3DS-SLAM exhibits an average improvement of 98.01% across the dynamic sequences of the TUM RGB-D dataset. Furthermore, it surpasses the performance of the other four leading SLAM systems designed for dynamic environments.
This paper addresses the problem of estimating the 3-DoF camera pose for a ground-level image with respect to a satellite image that encompasses the local surroundings. We propose a novel end-to-end approach that leverages the learning of dense pixel-wise flow fields in pairs of ground and satellite images to calculate the camera pose. Our approach differs from existing methods by constructing the feature metric at the pixel level, enabling full-image supervision for learning distinctive geometric configurations and visual appearances across views. Specifically, our method employs two distinct convolution networks for ground and satellite feature extraction. Then, we project the ground feature map to the bird's eye view (BEV) using a fixed camera height assumption to achieve preliminary geometric alignment. To further establish content association between the BEV and satellite features, we introduce a residual convolution block to refine the projected BEV feature. Optical flow estimation is performed on the refined BEV feature map and the satellite feature map using flow decoder networks based on RAFT. After obtaining dense flow correspondences, we apply the least square method to filter matching inliers and regress the ground camera pose. Extensive experiments demonstrate significant improvements compared to state-of-the-art methods. Notably, our approach reduces the median localization error by 89%, 19%, 80% and 35% on the KITTI, Ford multi-AV, VIGOR and Oxford RobotCar datasets, respectively.
The accurate reconstruction of dynamic scenes with neural radiance fields is significantly dependent on the estimation of camera poses. Widely used structure-from-motion pipelines encounter difficulties in accurately tracking the camera trajectory when faced with separate dynamics of the scene content and the camera movement. To address this challenge, we propose Dynamic Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields (DynaMoN). DynaMoN utilizes semantic segmentation and generic motion masks to handle dynamic content for initial camera pose estimation and statics-focused ray sampling for fast and accurate novel-view synthesis. Our novel iterative learning scheme switches between training the NeRF and updating the pose parameters for an improved reconstruction and trajectory estimation quality. The proposed pipeline shows significant acceleration of the training process. We extensively evaluate our approach on two real-world dynamic datasets, the TUM RGB-D dataset and the BONN RGB-D Dynamic dataset. DynaMoN improves over the state-of-the-art both in terms of reconstruction quality and trajectory accuracy. We plan to make our code public to enhance research in this area.
Precise scene understanding is key for most robot monitoring and intervention tasks in agriculture. In this work we present PAg-NeRF which is a novel NeRF-based system that enables 3D panoptic scene understanding. Our representation is trained using an image sequence with noisy robot odometry poses and automatic panoptic predictions with inconsistent IDs between frames. Despite this noisy input, our system is able to output scene geometry, photo-realistic renders and 3D consistent panoptic representations with consistent instance IDs. We evaluate this novel system in a very challenging horticultural scenario and in doing so demonstrate an end-to-end trainable system that can make use of noisy robot poses rather than precise poses that have to be pre-calculated. Compared to a baseline approach the peak signal to noise ratio is improved from 21.34dB to 23.37dB while the panoptic quality improves from 56.65% to 70.08%. Furthermore, our approach is faster and can be tuned to improve inference time by more than a factor of 2 while being memory efficient with approximately 12 times fewer parameters.
Image retrieval-based cross-view localization methods often lead to very coarse camera pose estimation, due to the limited sampling density of the database satellite images. In this paper, we propose a method to increase the accuracy of a ground camera's location and orientation by estimating the relative rotation and translation between the ground-level image and its matched/retrieved satellite image. Our approach designs a geometry-guided cross-view transformer that combines the benefits of conventional geometry and learnable cross-view transformers to map the ground-view observations to an overhead view. Given the synthesized overhead view and observed satellite feature maps, we construct a neural pose optimizer with strong global information embedding ability to estimate the relative rotation between them. After aligning their rotations, we develop an uncertainty-guided spatial correlation to generate a probability map of the vehicle locations, from which the relative translation can be determined. Experimental results demonstrate that our method significantly outperforms the state-of-the-art. Notably, the likelihood of restricting the vehicle lateral pose to be within 1m of its Ground Truth (GT) value on the cross-view KITTI dataset has been improved from $35.54\%$ to $76.44\%$, and the likelihood of restricting the vehicle orientation to be within $1^{\circ}$ of its GT value has been improved from $19.64\%$ to $99.10\%$.
Collecting real-world data is often considered the bottleneck of Artificial Intelligence, stalling the research progress in several fields, one of which is camera localization. End-to-end camera localization methods are still outperformed by traditional methods, and we argue that the inconsistencies associated with the data collection techniques are restraining the potential of end-to-end methods. Inspired by the recent data-centric paradigm, we propose a framework that synthesizes large localization datasets based on realistic 3D reconstructions of the real world. Our framework, termed Synfeal: Synthetic from Real, is an open-source, data-driven simulator that synthesizes RGB images by moving a virtual camera through a realistic 3D textured mesh, while collecting the corresponding ground-truth camera poses. The results validate that the training of camera localization algorithms on datasets generated by Synfeal leads to better results when compared to datasets generated by state-of-the-art methods. Using Synfeal, we conducted the first analysis of the relationship between the size of the dataset and the performance of camera localization algorithms. Results show that the performance significantly increases with the dataset size. Our results also suggest that when a large localization dataset with high quality is available, training from scratch leads to better performances. Synfeal is publicly available at https://github.com/DanielCoelho112/synfeal.
Camera localization is a classical computer vision task that serves various Artificial Intelligence and Robotics applications. With the rapid developments of Deep Neural Networks (DNNs), end-to-end visual localization methods are prosperous in recent years. In this work, we focus on the scene coordinate prediction ones and propose a network architecture named as Structure Guidance Learning (SGL) which utilizes the receptive branch and the structure branch to extract both high-level and low-level features to estimate the 3D coordinates. We design a confidence strategy to refine and filter the predicted 3D observations, which enables us to estimate the camera poses by employing the Perspective-n-Point (PnP) with RANSAC. In the training part, we design the Bundle Adjustment trainer to help the network fit the scenes better. Comparisons with some state-of-the-art (SOTA) methods and sufficient ablation experiments confirm the validity of our proposed architecture.
The recent surge in interest in autonomous driving stems from its rapidly developing capacity to enhance safety, efficiency, and convenience. A pivotal aspect of autonomous driving technology is its perceptual systems, where core algorithms have yielded more precise algorithms applicable to autonomous driving, including vision-based Simultaneous Localization and Mapping (SLAMs), object detection, and tracking algorithms. This work introduces a visual-based perception system for autonomous driving that integrates trajectory tracking and prediction of moving objects to prevent collisions, while addressing autonomous driving's localization and mapping requirements. The system leverages motion cues from pedestrians to monitor and forecast their movements and simultaneously maps the environment. This integrated approach resolves camera localization and the tracking of other moving objects in the scene, subsequently generating a sparse map to facilitate vehicle navigation. The performance, efficiency, and resilience of this approach are substantiated through comprehensive evaluations of both simulated and real-world datasets.
We tackle a new problem of multi-view camera and subject registration in the bird's eye view (BEV) without pre-given camera calibration. This is a very challenging problem since its only input is several RGB images from different first-person views (FPVs) for a multi-person scene, without the BEV image and the calibration of the FPVs, while the output is a unified plane with the localization and orientation of both the subjects and cameras in a BEV. We propose an end-to-end framework solving this problem, whose main idea can be divided into following parts: i) creating a view-transform subject detection module to transform the FPV to a virtual BEV including localization and orientation of each pedestrian, ii) deriving a geometric transformation based method to estimate camera localization and view direction, i.e., the camera registration in a unified BEV, iii) making use of spatial and appearance information to aggregate the subjects into the unified BEV. We collect a new large-scale synthetic dataset with rich annotations for evaluation. The experimental results show the remarkable effectiveness of our proposed method.
Sparse local feature extraction is usually believed to be of important significance in typical vision tasks such as simultaneous localization and mapping, image matching and 3D reconstruction. At present, it still has some deficiencies needing further improvement, mainly including the discrimination power of extracted local descriptors, the localization accuracy of detected keypoints, and the efficiency of local feature learning. This paper focuses on promoting the currently popular sparse local feature learning with camera pose supervision. Therefore, it pertinently proposes a Shared Coupling-bridge scheme with four light-weight yet effective improvements for weakly-supervised local feature (SCFeat) learning. It mainly contains: i) the \emph{Feature-Fusion-ResUNet Backbone} (F2R-Backbone) for local descriptors learning, ii) a shared coupling-bridge normalization to improve the decoupling training of description network and detection network, iii) an improved detection network with peakiness measurement to detect keypoints and iv) the fundamental matrix error as a reward factor to further optimize feature detection training. Extensive experiments prove that our SCFeat improvement is effective. It could often obtain a state-of-the-art performance on classic image matching and visual localization. In terms of 3D reconstruction, it could still achieve competitive results. For sharing and communication, our source codes are available at https://github.com/sunjiayuanro/SCFeat.git.
Visual localization plays an important role for intelligent robots and autonomous driving, especially when the accuracy of GNSS is unreliable. Recently, camera localization in LiDAR maps has attracted more and more attention for its low cost and potential robustness to illumination and weather changes. However, the commonly used pinhole camera has a narrow Field-of-View, thus leading to limited information compared with the omni-directional LiDAR data. To overcome this limitation, we focus on correlating the information of 360 equirectangular images to point clouds, proposing an end-to-end learnable network to conduct cross-modal visual localization by establishing similarity in high-dimensional feature space. Inspired by the attention mechanism, we optimize the network to capture the salient feature for comparing images and point clouds. We construct several sequences containing 360 equirectangular images and corresponding point clouds based on the KITTI-360 dataset and conduct extensive experiments. The results demonstrate the effectiveness of our approach.
Camera relocalization involving a prior 3D reconstruction plays a crucial role in many mixed reality and robotics applications. Estimating the camera pose directly with respect to pre-built 3D models can be prohibitively expensive for several applications with limited storage and/or communication bandwidth. Although recent scene and absolute pose regression methods have become popular for efficient camera localization, most of them are computation-resource intensive and difficult to obtain a real-time inference with high accuracy constraints. This study proposes a simple scene regression method that requires only a multi-layer perceptron network for mapping scene coordinates to achieve accurate camera pose estimations. The proposed approach uses sparse descriptors to regress the scene coordinates, instead of a dense RGB image. The use of sparse features provides several advantages. First, the proposed regressor network is substantially smaller than those reported in previous studies. This makes our system highly efficient and scalable. Second, the pre-built 3D models provide the most reliable and robust 2D-3D matches. Therefore, learning from them can lead to an awareness of equivalent features and substantially improve the generalization performance. A detailed analysis of our approach and extensive evaluations using existing datasets are provided to support the proposed method. The implementation detail is available at https://github.com/aislab/feat2map
Visual Place Recognition is an essential component of systems for camera localization and loop closure detection, and it has attracted widespread interest in multiple domains such as computer vision, robotics and AR/VR. In this work, we propose a faster, lighter and stronger approach that can generate models with fewer parameters and can spend less time in the inference stage. We designed RepVGG-lite as the backbone network in our architecture, it is more discriminative than other general networks in the Place Recognition task. RepVGG-lite has more speed advantages while achieving higher performance. We extract only one scale patch-level descriptors from global descriptors in the feature extraction stage. Then we design a trainable feature matcher to exploit both spatial relationships of the features and their visual appearance, which is based on the attention mechanism. Comprehensive experiments on challenging benchmark datasets demonstrate the proposed method outperforming recent other state-of-the-art learned approaches, and achieving even higher inference speed. Our system has 14 times less params than Patch-NetVLAD, 6.8 times lower theoretical FLOPs, and run faster 21 and 33 times in feature extraction and feature matching. Moreover, the performance of our approach is 0.5\% better than Patch-NetVLAD in Recall@1. We used subsets of Mapillary Street Level Sequences dataset to conduct experiments for all other challenging conditions.
Camera relocalization has various applications in autonomous driving. Previous camera pose regression models consider only ideal scenarios where there is little environmental perturbation. To deal with challenging driving environments that may have changing seasons, weather, illumination, and the presence of unstable objects, we propose RobustLoc, which derives its robustness against perturbations from neural differential equations. Our model uses a convolutional neural network to extract feature maps from multi-view images, a robust neural differential equation diffusion block module to diffuse information interactively, and a branched pose decoder with multi-layer training to estimate the vehicle poses. Experiments demonstrate that RobustLoc surpasses current state-of-the-art camera pose regression models and achieves robust performance in various environments. Our code is released at: https://github.com/sijieaaa/RobustLoc