We present a novel method for scene change detection that leverages the robust feature extraction capabilities of a visual foundational model, DINOv2, and integrates full-image cross-attention to address key challenges such as varying lighting, seasonal variations, and viewpoint differences. In order to effectively learn correspondences and mis-correspondences between an image pair for the change detection task, we propose to a) “freeze” the backbone in order to retain the generality of dense foundation features, and b) employ “full-image” cross-attention to better tackle the viewpoint variations between the image pair. We evaluate our approach on two benchmark datasets, VL-CMU-CD and PSCD, along with their viewpoint-varied versions. Our experiments demonstrate significant improvements in F1-score, particularly in scenarios involving geometric changes between image pairs. The results indicate our method's superior generalization capabilities over existing state-of-the-art approaches, showing robustness against photometric and geometric variations as well as better overall generalization when fine-tuned to adapt to new environments. Detailed ablation studies further validate the contributions of each component in our architecture. Our source code is available at: https://github.com/ChadLin9596/Robust-Scene-Change-Detection.

Visual navigation in robotics traditionally relies on globally-consistent 3D maps or learned controllers, which can be computationally expensive and difficult to generalize across diverse environments. In this work, we present a novel RGB-only, object-level topometric navigation pipeline that enables zero-shot, long-horizon robot navigation without requiring 3D maps or pre-trained controllers. Our approach integrates global topological path planning with local metric trajectory control, allowing the robot to navigate towards object-level sub-goals while avoiding obstacles. We address key limitations of previous methods by continuously predicting local trajectory using monocular depth and traversability estimation, and in-corporating an auto-switching mechanism that falls back to a baseline controller when necessary. The system operates using foundational models, ensuring open-set applicability without the need for domain-specific fine-tuning. We demonstrate the effectiveness of our method in both simulated environments and real-world tests, highlighting its robustness and deployability. Our approach outperforms existing state-of-the-art methods, offering a more adaptable and effective solution for visual navigation in open-set environments. The source code is made publicly available: https://github.com/podgorki/TANGO.

Segment matching is an important intermediate task in computer vision that establishes correspondences between semantically or geometrically coherent regions across images. Unlike keypoint matching, which focuses on localized features, segment matching captures structured regions, offering greater robustness to occlusions, lighting variations, and viewpoint changes. In this paper, we leverage the spatial understanding of 3D foundation models to tackle wide-baseline segment matching, a challenging setting involving extreme viewpoint shifts. We propose an architecture that uses the inductive bias of these 3D foundation models to match segments across image pairs with up to $180^\circ$ rotation. Extensive experiments show that our approach outperforms state-of-the-art methods, including the SAM2 video propagator and local feature matching methods, by up to 30\% on the AUPRC metric, on ScanNet++ and Replica datasets. We further demonstrate benefits of the proposed model on relevant downstream tasks, including 3D instance mapping and object-relative navigation.

Recent research in Vision Language Navigation (VLN) has overlooked the development of agents' inquisitive abilities, which allow them to ask clarifying questions when instructions are incomplete. This paper addresses how agents can recognize “when” they lack sufficient information, without focusing on “what” is missing, particularly in VLN tasks with vague instructions. Equipping agents with this ability enhances efficiency by reducing potential digressions and seeking timely assistance. The challenge in identifying such uncertain points is balancing between being overly cautious (high recall) and overly confident (high precision). We propose an attention-based instruction-vagueness estimation module that learns associations between instructions and the agent's trajectory. By leveraging instruction-to-path alignment information during training, the module's vagueness estimation performance improves by around 52% in terms of precision-recall balance. In our ablative experiments, we also demonstrate the effectiveness of incorporating this additional instruction-to-path attention network alongside the cross-modal attention networks within the navigator module. Our results show that the attention scores from the instruction-to-path attention network serve as better indicators for estimating vagueness.

Mapping is crucial for spatial reasoning, planning and robot navigation. Existing approaches range from metric, which require precise geometry-based optimization, to purely topological, where image-as-node based graphs lack explicit object-level reasoning and interconnectivity. In this paper, we propose a novel topological representation of an environment based on , which are semantically meaningful and open-vocabulary queryable, conferring several advantages over previous works based on pixel-level features. Unlike 3D scene graphs, we create a purely topological graph with segments as nodes, where edges are formed by a) associating segment-level descriptors between pairs of consecutive images and b) connecting neighboring segments within an image using their pixel centroids. This unveils a continuous sense of a place, defined by inter-image persistence of segments along with their intra-image neighbours. It further enables us to represent and update segment-level descriptors through neighborhood aggregation using graph convolution layers, which improves robot localization based on segment-level retrieval. Using real-world data, we show how our proposed map representation can be used to i) generate navigation plans in the form of hops over segments and ii) search for target objects using natural language queries describing spatial relations of objects. Furthermore, we quantitatively analyze data association at the segment level, which underpins inter-image connectivity during mapping and segment-level localization when revisiting the same place. Finally, we show preliminary trials on segment-level ‘hopping’ based zero-shot real-world navigation. Project page with supplementary details: oravus.github.io/RoboHop/.

Semantic segmentation in adverse weather scenarios is a critical task for autonomous driving systems. While foundation models have shown promise, the need for specialized adaptors becomes evident for handling more challenging scenarios. We introduce DiffPrompter, a novel differentiable visual and latent prompting mechanism aimed at expanding the learning capabilities of existing adaptors in foundation models. Our proposed ∇HFC (High Frequency Components) based image processing block excels particularly in adverse weather conditions, where conventional methods often fall short. Furthermore, we investigate the advantages of jointly training visual and latent prompts, demonstrating that this combined approach significantly enhances performance in out-of-distribution scenarios. Our differentiable visual prompts leverage parallel and series architectures to generate prompts, effectively improving object segmentation tasks in adverse conditions. Through a comprehensive series of experiments and evaluations, we provide empirical evidence to support the efficacy of our approach. Project page: diffprompter.github.io

Robotic tasks such as planning and navigation require a hierarchical semantic understanding of a scene, which could include multiple floors and rooms. Current methods primarily focus on object segmentation for 3D scene understanding. However, such methods struggle to segment out topological regions like "kitchen" in the scene. In this work, we introduce a two-step pipeline to solve this problem. First, we extract a topological map, i.e., floorplan of the indoor scene using a novel multi-channel occupancy representation. Then, we generate CLIP-aligned features and semantic labels for every room instance based on the objects it contains using a self-attention transformer. Our language-topology alignment supports natural language querying, e.g., a "place to cook" locates the "kitchen". We outperform the current state-of-the-art on room segmentation by ~20% and room classification by ~12%. Our detailed qualitative analysis and ablation studies provide insights into the problem of joint structural and semantic 3D scene understanding. Project Page: quest-maps.github.io

Detecting objects under adverse weather and lighting conditions is crucial for the safe and continuous operation of an autonomous vehicle, and remains an unsolved problem. We present a Gated Differentiable Image Processing (GDIP) block, a domain-agnostic network architecture, which can be plugged into existing object detection networks (e.g., Yolo) and trained end-to-end with adverse condition images such as those captured under fog and low lighting. Our pro-posed GDIP block learns to enhance images directly through the downstream object detection loss. This is achieved by learning parameters of multiple image pre-processing (IP) techniques that operate concurrently, with their outputs combined using weights learned through a novel gating mechanism. We further improve GDIP through a multi-stage guidance procedure for progressive image enhancement. Finally, trading off accuracy for speed, we propose a variant of GDIP that can be used as a regularizer for training Yolo, which eliminates the need for GDIP-based image enhancement during inference, resulting in higher throughput and plausible real-world deployment. We demonstrate significant improvement in detection performance over several state-of-the-art methods through quantitative and qualitative studies on synthetic datasets such as PascalVOC, and real-world foggy (RTTS) and low-lighting (ExDark) datasets.

Can knowing where you are assist in perceiving objects in your surroundings, especially under adverse weather and lighting conditions? In this work we investigate whether a prior map can be leveraged to aid in the detection of dynamic objects in a scene without the need for a 3D map or pixel-level map-query correspondences. We contribute an algorithm which refines an initial set of candidate object detections and produces a refined subset of highly accurate detections using a prior map. We begin by using visual place recognition (VPR) to retrieve a prior map image for a given query image, then use a binary classification neural network that compares the query and prior map image regions to validate the query detection. Once our classification network is trained, on approximately 1000 query-map image pairs, it is able to improve the performance of vehicle detection when combined with an existing off-the-shelf vehicle detector. We demonstrate our approach using standard datasets across two cities (Oxford and Zurich) under different settings of train-test separation of map-query traverse pairs. We further emphasize the performance gains of our approach against alternative design choices and show that VPR suffices for the task, eliminating the need for precise ground truth localization.

Most 6-DoF localization and SLAM systems use static landmarks but ignore dynamic objects because they cannot be usefully incorporated into a typical pipeline. Where dynamic objects have been incorporated, typical approaches have attempted relatively sophisticated identification and localization of these objects, limiting their robustness or general utility. In this research, we propose a middle ground, demonstrated in the context of autonomous vehicles, using dynamic vehicles to provide limited pose constraint information in a 6-DoF frame-by-frame PnP-RANSAC localization pipeline. We refine initial pose estimates with a motion model and propose a method for calculating the predicted quality of future pose estimates, triggered by whether or not the autonomous vehicle's motion is constrained by the relative frame-to-frame location of dynamic vehicles in the environment. Our approach detects and identifies suitable dynamic vehicles to define these pose constraints to modify a pose filter, resulting in improved recall across a range of localization tolerances from 0.25m to 5m, compared to a state-of-the-art baseline single image PnP method and its vanilla pose filtering. Our constraint detection system is active for approximately 35% of the time on the Ford AV dataset and localization is particularly improved when the constraint detection is active.

Visual Place Recognition is a challenging task for robotics and autonomous systems, which must deal with the twin problems of appearance and viewpoint change in an always changing world. This paper introduces Patch-NetVLAD, which provides a novel formulation for combining the advantages of both local and global descriptor methods by deriving patch-level features from NetVLAD residuals. Unlike the fixed spatial neighborhood regime of existing local keypoint features, our method enables aggregation and matching of deep-learned local features defined over the feature-space grid. We further introduce a multi-scale fusion of patch features that have complementary scales (i.e. patch sizes) via an integral feature space and show that the fused features are highly invariant to both condition (season, structure, and illumination) and viewpoint (translation and rotation) changes. Patch-NetVLAD achieves state-of-the-art visual place recognition results in computationally limited scenarios, validated on a range of challenging real-world datasets, including winning the Facebook Mapillary Visual Place Recognition Challenge at ECCV2020. It is also adaptable to user requirements, with a speed-optimised version operating over an order of magnitude faster than the state-of-the-art. By combining superior performance with improved computational efficiency in a configurable framework, Patch-NetVLAD is well suited to enhance both stand-alone place recognition capabilities and the overall performance of SLAM systems.

We explore the zero-shot setting for day-night domain adaptation. The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting unlabeled data samples from the test set. As gathering relevant test data is expensive and sometimes even impossible, we remove any reliance on test data imagery and instead exploit a visual inductive prior derived from physics-based reflection models for domain adaptation. We cast a number of color invariant edge detectors as trainable layers in a convolutional neural network and evaluate their robustness to illumination changes. We show that the color invariant layer reduces the day-night distribution shift in feature map activations throughout the network. We demonstrate improved performance for zero-shot day to night domain adaptation on both synthetic as well as natural datasets in various tasks, including classification, segmentation and place recognition.

Visual Place Recognition (VPR) is often characterized as being able to recognize the same place despite significant changes in appearance and viewpoint. VPR is a key component of Spatial Artificial Intelligence, enabling robotic platforms and intelligent augmentation platforms such as augmented reality devices to perceive and understand the physical world. In this paper, we observe that there are three "drivers" that impose requirements on spatially intelligent agents and thus VPR systems: 1) the particular agent including its sensors and computational resources, 2) the operating environment of this agent, and 3) the specific task that the artificial agent carries out. In this paper, we characterize and survey key works in the VPR area considering those drivers, including their place representation and place matching choices. We also provide a new definition of VPR based on the visual overlap - akin to spatial view cells in the brain - that enables us to find similarities and differences to other research areas in the robotics and computer vision fields. We identify several open challenges and suggest areas that require more in-depth attention in future works.

The use of local detectors and descriptors in typical computer vision pipelines works well until variations in viewpoint and appearance change become extreme. Past research in this area has typically focused on one of two approaches to this challenge: the use of projections into spaces more suitable for feature matching under extreme viewpoint changes, and attempting to learn features that are inherently more robust to viewpoint change. In this paper, we present a novel framework that combines the learning of invariant descriptors through data augmentation and orthographic viewpoint projection. We propose rotation-robust local descriptors, learnt through training data augmentation based on rotation homographies, and a correspondence ensemble technique that combines vanilla feature correspondences with those obtained through rotation-robust features. Using a range of benchmark datasets as well as contributing a new bespoke dataset for this research domain, we evaluate the effectiveness of the proposed approach on key tasks including pose estimation and visual place recognition. Our system outperforms a range of baseline and state-of-the-art techniques, including enabling higher levels of place recognition precision across opposing place viewpoints, and achieves practically useful performance levels even under extreme viewpoint changes. We reduce pose estimation error by 86.72% relative to state of the art.

Abstract Visual place recognition (VPR) is the process of recognising a previously visited place using visual information, often under varying appearance conditions and viewpoint changes and with computational constraints. VPR is related to the concepts of localisation, loop closure, image retrieval and is a critical component of many autonomous navigation systems ranging from autonomous vehicles to drones and computer vision systems. While the concept of place recognition has been around for many years, VPR research has grown rapidly as a field over the past decade due to improving camera hardware and its potential for deep learning-based techniques, and has become a widely studied topic in both the computer vision and robotics communities. This growth however has led to fragmentation and a lack of standardisation in the field, especially concerning performance evaluation. Moreover, the notion of viewpoint and illumination invariance of VPR techniques has largely been assessed qualitatively and hence ambiguously in the past. In this paper, we address these gaps through a new comprehensive open-source framework for assessing the performance of VPR techniques, dubbed “VPR-Bench”. VPR-Bench (Open-sourced at: https://github.com/MubarizZaffar/VPR-Bench ) introduces two much-needed capabilities for VPR researchers: firstly, it contains a benchmark of 12 fully-integrated datasets and 10 VPR techniques, and secondly, it integrates a comprehensive variation-quantified dataset for quantifying viewpoint and illumination invariance. We apply and analyse popular evaluation metrics for VPR from both the computer vision and robotics communities, and discuss how these different metrics complement and/or replace each other, depending upon the underlying applications and system requirements. Our analysis reveals that no universal SOTA VPR technique exists, since: (a) state-of-the-art (SOTA) performance is achieved by 8 out of the 10 techniques on at least one dataset, (b) SOTA technique in one community does not necessarily yield SOTA performance in the other given the differences in datasets and metrics. Furthermore, we identify key open challenges since: (c) all 10 techniques suffer greatly in perceptually-aliased and less-structured environments, (d) all techniques suffer from viewpoint variance where lateral change has less effect than 3D change, and (e) directional illumination change has more adverse effects on matching confidence than uniform illumination change. We also present detailed meta-analyses regarding the roles of varying ground-truths, platforms, application requirements and technique parameters. Finally, VPR-Bench provides a unified implementation to deploy these VPR techniques, metrics and datasets, and is extensible through templates.

Visual place recognition algorithms trade off three key characteristics: their storage footprint, their computational requirements, and their resultant performance, often expressed in terms of recall rate. Significant prior work has investigated highly compact place representations, sub-linear computational scaling and sub-linear storage scaling techniques, but have always involved a significant compromise in one or more of these regards, and have only been demonstrated on relatively small datasets. In this paper we present a novel place recognition system which enables for the first time the combination of ultra-compact place representations, near sub-linear storage scaling and extremely lightweight compute requirements. Our approach exploits the inherently sequential nature of much spatial data in the robotics domain and inverts the typical target criteria, through intentionally coarse scalar quantization-based hashing that leads to more collisions but is resolved by sequence-based matching. For the first time, we show how effective place recognition rates can be achieved on a new very large 10 million place dataset, requiring only 8 bytes of storage per place and 37K unitary operations to achieve over 50% recall for matching a sequence of 100 frames, where a conventional stateof-the-art approach both consumes 1300 times more compute and fails catastrophically. We present analysis investigating the effectiveness of our hashing overload approach under varying sizes of quantized vector length, comparison of near miss matches with the actual match selections and characterise the effect of variance re-scaling of data on quantization. Resource link: https://github.com/oravus/CoarseHash.

Visual place recognition (VPR) - the act of recognizing a familiar visual place - becomes difficult when there is extreme environmental appearance change or viewpoint change. Particularly challenging is the scenario where both phenomena occur simultaneously, such as when returning for the first time along a road at night that was previously traversed during the day in the opposite direction. While such problems can be solved with panoramic sensors, humans solve this problem regularly with limited field-of-view vision and without needing to constantly turn around. In this paper, we present a new depth- and temporal-aware visual place recognition system that solves the opposing viewpoint, extreme appearance-change visual place recognition problem. Our system performs sequence-to-single frame matching by extracting depth-filtered keypoints using a state-of-the-art depth estimation pipeline, constructing a keypoint sequence over multiple frames from the reference dataset, and comparing these keypoints to the keypoints extracted from a single query image. We evaluate the system on a challenging benchmark dataset and show that it consistently outperforms state-of-the-art techniques. We also develop a range of diagnostic simulation experiments that characterize the contribution of depth-filtered keypoint sequences with respect to key domain parameters including the degree of appearance change and camera motion.

When a human drives a car along a road for the first time, they later recognize where they are on the return journey typically without needing to look in their rear view mirror or turn around to look back, despite significant viewpoint and appearance change. Such navigation capabilities are typically attributed to our semantic visual understanding of the environment [1] beyond geometry to recognizing the types of places we are passing through such as “passing a shop on the left” or “moving through a forested area”. Humans are in effect using place categorization [2] to perform specific place recognition even when the viewpoint is 180 degrees reversed. Recent advances in deep neural networks have enabled high performance semantic understanding of visual places and scenes, opening up the possibility of emulating what humans do. In this work, we develop a novel methodology for using the semantics-aware higher-order layers of deep neural networks for recognizing specific places from within a reference database. To further improve the robustness to appearance change, we develop a descriptor normalization scheme that builds on the success of normalization schemes for pure appearance-based techniques such as SeqSLAM [3]. Using two different datasets - one road-based, one pedestrian-based, we evaluate the performance of the system in performing place recognition on reverse traversals of a route with a limited field of view camera and no turn-back-and-Iook behaviours, and compare to existing state-of-the-art techniques and vanilla off-the-shelf features. The results demonstrate significant improvements over the existing state of the art, especially for extreme perceptual challenges that involve both great viewpoint change and environmental appearance change. We also provide experimental analyses of the contributions of the various system components: the use of spatio-temporal sequences, place categorization and place-centric characteristics as opposed to object-centric semantics.

Visually recognising a traversed route - regardless of whether seen during the day or night, in clear or inclement conditions, or in summer or winter - is an important capability for navigating robots. Since SeqSLAM was introduced in 2012, a large body of work has followed exploring how robotic systems can use the algorithm to meet the challenges posed by navigation in changing environmental conditions. The following paper describes OpenSeqSLAM2.0, a fully open-source toolbox for visual place recognition under changing conditions. Beyond the benefits of open access to the source code, OpenSeqSLAM2.0 provides a number of tools to facilitate exploration of the visual place recognition problem and interactive parameter tuning. Using the new open source platform, it is shown for the first time how comprehensive parameter characterisations provide new insights into many of the system components previously presented in ad hoc ways and provide users with a guide to what system component options should be used under what circumstances and why.

The place recognition problem comprises two distinct subproblems; recognizing a specific location in the world (“specific” or “ordinary” place recognition) and recognizing the type of place (place categorization). Both are important competencies for mobile robots and have each received significant attention in the robotics and computer vision community, but usually as separate areas of investigation. In this paper, we leverage the powerful complementary nature of place recognition and place categorization processes to create a new hybrid place recognition system that uses place context to inform place recognition. We show that semantic place categorization creates an informative natural segmenting of physical space that in turn enables significantly better place recognition performance in comparison to existing techniques. In particular, this new semantically-informed approach adds robustness to significant local changes within the environment, such as transitioning between indoor and outdoor environments or between dark and light rooms in a house, complementing the capabilities of current condition-invariant techniques that are robust to globally consistent change (such as day to night cycles). We perform experiments using 4 novel benchmark datasets and show that semantically-informed place recognition outperforms the previous state-of-the-art systems. Like it does for object recognition [1], we believe that semantics can play a key role in boosting conventional place recognition and navigation performance for robotic systems.

Robotic vision, unlike computer vision, typically involves processing a stream of images from a camera with time varying pose operating in an environment with time varying lighting conditions and moving objects. Repeating robotic vision experiments under identical conditions is often impossible, making it difficult to compare different algorithms. For machine learning applications a critical bottleneck is the limited amount of real world image data that can be captured and labelled for both training and testing purposes. In this paper we investigate the use of a photo-realistic simulation tool to address these challenges, in three specific domains: robust place recognition, visual SLAM and object recognition. For the first two problems we generate images from a complex 3D environment with systematically varying camera paths, camera viewpoints and lighting conditions. For the first time we are able to systematically characterise the performance of these algorithms as paths and lighting conditions change. In particular, we are able to systematically generate varying camera viewpoint datasets that would be difficult or impossible to generate in the real world. We also compare algorithm results for a camera in a real environment and a simulated camera in a simulation model of that real environment. Finally, for the object recognition domain, we generate labelled image data and characterise the viewpoint dependency of a current convolution neural network in performing object recognition. Together these results provide a multi-domain demonstration of the beneficial properties of using simulation to characterise and analyse a wide range of robotic vision algorithms.

This paper looks into the problem of pedestrian tracking using a monocular, potentially moving, uncalibrated camera. The pedestrians are located in each frame using a standard human detector, which are then tracked in subsequent frames. This is a challenging problem as one has to deal with complex situations like changing background, partial or full occlusion and camera motion. In order to carry out successful tracking, it is necessary to resolve associations between the detected windows in the current frame with those obtained from the previous frame. Compared to methods that use temporal windows incorporating past as well as future information, we attempt to make decision on a frame-by-frame basis. An occlusion reasoning scheme is proposed to resolve the association problem between a pair of consecutive frames by using an affinity matrix that defines the closeness between a pair of windows and then, uses a binary integer programming to obtain unique association between them. A second stage of verification based on SURF matching is used to deal with those cases where the above optimization scheme might yield wrong associations. The efficacy of the approach is demonstrated through experiments on several standard pedestrian datasets.

Detecting and tracking a human from a mobile robot platform has several applications in service robotics where a robot is expected to assist humans. In this paper, we propose a novel interest point-based algorithm that can track a human reliably under several challenging situations like variation in illumination, pose change, scaling, camera motion and occlusion. The limitations of point-based methods are overcome using colour information and imposing a structure on the colour blobs. Whenever sufficient number of SURF matching points are not available for a given frame, the presence of human is detected using Markov random field based graph matching algorithm. Imposition of structure on coloured blobs helps in eliminating background objects having similar colour distribution. The stability-versus-plasticity dilemma inherent in tracking over long run is resolved by selecting new templates on-line and maintaining a tree of templates which is updated with new information. The performance of the algorithm is demonstrated through simulation on standard datasets and the computation time is found to be comparable with existing SURF-based tracking methods.

The interest point based tracking methods suffer from the limitation of unavailability of sufficient number of matching key points for the target in all frames of a running video. In this paper, a dynamic model is proposed for describing the object model which is used for tracking a human in a non-stationary video. This dynamic model takes into account the change in the pose as well as the motion of the human. A simple autoregression based predictor is used for dealing with the case of full occlusion. Simulation results are provided to show the efficacy of the algorithm.