Sourav Garg

Nikhil Keetha, Avneesh Mishra, Jay Karhade et al. · mit

Visual Place Recognition (VPR) is vital for robot localization. To date, the most performant VPR approaches are environment- and task-specific: while they exhibit strong performance in structured environments (predominantly urban driving), their performance degrades severely in unstructured environments, rendering most approaches brittle to robust real-world deployment. In this work, we develop a universal solution to VPR -- a technique that works across a broad range of structured and unstructured environments (urban, outdoors, indoors, aerial, underwater, and subterranean environments) without any re-training or fine-tuning. We demonstrate that general-purpose feature representations derived from off-the-shelf self-supervised models with no VPR-specific training are the right substrate upon which to build such a universal VPR solution. Combining these derived features with unsupervised feature aggregation enables our suite of methods, AnyLoc, to achieve up to 4X significantly higher performance than existing approaches. We further obtain a 6% improvement in performance by characterizing the semantic properties of these features, uncovering unique domains which encapsulate datasets from similar environments. Our detailed experiments and analysis lay a foundation for building VPR solutions that may be deployed anywhere, anytime, and across anyview. We encourage the readers to explore our project page and interactive demos: https://anyloc.github.io/.

Chun-Jung Lin, Sourav Garg, Tat-Jun Chin et al.

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.

Kartik Garg, Sai Shubodh Puligilla, Shishir Kolathaya et al.

Accurately recognizing a revisited place is crucial for embodied agents to localize and navigate. This requires visual representations to be distinct, despite strong variations in camera viewpoint and scene appearance. Existing visual place recognition pipelines encode the "whole" image and search for matches. This poses a fundamental challenge in matching two images of the same place captured from different camera viewpoints: "the similarity of what overlaps can be dominated by the dissimilarity of what does not overlap". We address this by encoding and searching for "image segments" instead of the whole images. We propose to use open-set image segmentation to decompose an image into `meaningful' entities (i.e., things and stuff). This enables us to create a novel image representation as a collection of multiple overlapping subgraphs connecting a segment with its neighboring segments, dubbed SuperSegment. Furthermore, to efficiently encode these SuperSegments into compact vector representations, we propose a novel factorized representation of feature aggregation. We show that retrieving these partial representations leads to significantly higher recognition recall than the typical whole image based retrieval. Our segments-based approach, dubbed SegVLAD, sets a new state-of-the-art in place recognition on a diverse selection of benchmark datasets, while being applicable to both generic and task-specialized image encoders. Finally, we demonstrate the potential of our method to ``revisit anything'' by evaluating our method on an object instance retrieval task, which bridges the two disparate areas of research: visual place recognition and object-goal navigation, through their common aim of recognizing goal objects specific to a place. Source code: https://github.com/AnyLoc/Revisit-Anything.

Krishan Rana, Jesse Haviland, Sourav Garg et al.

Large language models (LLMs) have demonstrated impressive results in developing generalist planning agents for diverse tasks. However, grounding these plans in expansive, multi-floor, and multi-room environments presents a significant challenge for robotics. We introduce SayPlan, a scalable approach to LLM-based, large-scale task planning for robotics using 3D scene graph (3DSG) representations. To ensure the scalability of our approach, we: (1) exploit the hierarchical nature of 3DSGs to allow LLMs to conduct a 'semantic search' for task-relevant subgraphs from a smaller, collapsed representation of the full graph; (2) reduce the planning horizon for the LLM by integrating a classical path planner and (3) introduce an 'iterative replanning' pipeline that refines the initial plan using feedback from a scene graph simulator, correcting infeasible actions and avoiding planning failures. We evaluate our approach on two large-scale environments spanning up to 3 floors and 36 rooms with 140 assets and objects and show that our approach is capable of grounding large-scale, long-horizon task plans from abstract, and natural language instruction for a mobile manipulator robot to execute. We provide real robot video demonstrations on our project page https://sayplan.github.io.

Ahmad Khaliq, Ming Xu, Stephen Hausler et al.

Visual Place Recognition (VPR) is a crucial component of many visual localization pipelines for embodied agents. VPR is often formulated as an image retrieval task aimed at jointly learning local features and an aggregation method. The current state-of-the-art VPR methods rely on VLAD aggregation, which can be trained to learn a weighted contribution of features through their soft assignment to cluster centers. However, this process has two key limitations. Firstly, the feature-to-cluster weighting does not account for over-represented repetitive structures within a cluster, e.g., shadows or window panes; this phenomenon is also referred to as the `burstiness' problem, classically solved by discounting repetitive features before aggregation. Secondly, feature to cluster comparisons are compute-intensive for state-of-the-art image encoders with high-dimensional local features. This paper addresses these limitations by introducing VLAD-BuFF with two novel contributions: i) a self-similarity based feature discounting mechanism to learn Burst-aware features within end-to-end VPR training, and ii) Fast Feature aggregation by reducing local feature dimensions specifically through PCA-initialized learnable pre-projection. We benchmark our method on 9 public datasets, where VLAD-BuFF sets a new state of the art. Our method is able to maintain its high recall even for 12x reduced local feature dimensions, thus enabling fast feature aggregation without compromising on recall. Through additional qualitative studies, we show how our proposed weighting method effectively downweights the non-distinctive features. Source code: https://github.com/Ahmedest61/VLAD-BuFF/.

Madhu Vankadari, Stuart Golodetz, Sourav Garg et al.

Self-supervised deep learning methods for joint depth and ego-motion estimation can yield accurate trajectories without needing ground-truth training data. However, as they typically use photometric losses, their performance can degrade significantly when the assumptions these losses make (e.g. temporal illumination consistency, a static scene, and the absence of noise and occlusions) are violated. This limits their use for e.g. nighttime sequences, which tend to contain many point light sources (including on dynamic objects) and low signal-to-noise ratio (SNR) in darker image regions. In this paper, we show how to use a combination of three techniques to allow the existing photometric losses to work for both day and nighttime images. First, we introduce a per-pixel neural intensity transformation to compensate for the light changes that occur between successive frames. Second, we predict a per-pixel residual flow map that we use to correct the reprojection correspondences induced by the estimated ego-motion and depth from the networks. And third, we denoise the training images to improve the robustness and accuracy of our approach. These changes allow us to train a single model for both day and nighttime images without needing separate encoders or extra feature networks like existing methods. We perform extensive experiments and ablation studies on the challenging Oxford RobotCar dataset to demonstrate the efficacy of our approach for both day and nighttime sequences.

Stefan Schubert, Peer Neubert, Sourav Garg et al.

Localization is an essential capability for mobile robots. A rapidly growing field of research in this area is Visual Place Recognition (VPR), which is the ability to recognize previously seen places in the world based solely on images. This present work is the first tutorial paper on visual place recognition. It unifies the terminology of VPR and complements prior research in two important directions: 1) It provides a systematic introduction for newcomers to the field, covering topics such as the formulation of the VPR problem, a general-purpose algorithmic pipeline, an evaluation methodology for VPR approaches, and the major challenges for VPR and how they may be addressed. 2) As a contribution for researchers acquainted with the VPR problem, it examines the intricacies of different VPR problem types regarding input, data processing, and output. The tutorial also discusses the subtleties behind the evaluation of VPR algorithms, e.g., the evaluation of a VPR system that has to find all matching database images per query, as opposed to just a single match. Practical code examples in Python illustrate to prospective practitioners and researchers how VPR is implemented and evaluated.

Sanket Kalwar, Dhruv Patel, Aakash Aanegola et al.

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 proposed 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.

Stephen Hausler, Ming Xu, Sourav Garg et al.

6-DoF visual localization systems utilize principled approaches rooted in 3D geometry to perform accurate camera pose estimation of images to a map. Current techniques use hierarchical pipelines and learned 2D feature extractors to improve scalability and increase performance. However, despite gains in typical recall@0.25m type metrics, these systems still have limited utility for real-world applications like autonomous vehicles because of their `worst' areas of performance - the locations where they provide insufficient recall at a certain required error tolerance. Here we investigate the utility of using `place specific configurations', where a map is segmented into a number of places, each with its own configuration for modulating the pose estimation step, in this case selecting a camera within a multi-camera system. On the Ford AV benchmark dataset, we demonstrate substantially improved worst-case localization performance compared to using off-the-shelf pipelines - minimizing the percentage of the dataset which has low recall at a certain error tolerance, as well as improved overall localization performance. Our proposed approach is particularly applicable to the crowdsharing model of autonomous vehicle deployment, where a fleet of AVs are regularly traversing a known route.

Ming Xu, Sourav Garg, Michael Milford et al.

This paper addresses learning end-to-end models for time series data that include a temporal alignment step via dynamic time warping (DTW). Existing approaches to differentiable DTW either differentiate through a fixed warping path or apply a differentiable relaxation to the min operator found in the recursive steps used to solve the DTW problem. We instead propose a DTW layer based around bi-level optimisation and deep declarative networks, which we name DecDTW. By formulating DTW as a continuous, inequality constrained optimisation problem, we can compute gradients for the solution of the optimal alignment (with respect to the underlying time series) using implicit differentiation. An interesting byproduct of this formulation is that DecDTW outputs the optimal warping path between two time series as opposed to a soft approximation, recoverable from Soft-DTW. We show that this property is particularly useful for applications where downstream loss functions are defined on the optimal alignment path itself. This naturally occurs, for instance, when learning to improve the accuracy of predicted alignments against ground truth alignments. We evaluate DecDTW on two such applications, namely the audio-to-score alignment task in music information retrieval and the visual place recognition task in robotics, demonstrating state-of-the-art results in both.

Abhishek Peri, Kinal Mehta, Avneesh Mishra et al.

Sparse local feature matching is pivotal for many computer vision and robotics tasks. To improve their invariance to challenging appearance conditions and viewing angles, and hence their usefulness, existing learning-based methods have primarily focused on data augmentation-based training. In this work, we propose an alternative, complementary approach that centers on inducing bias in the model architecture itself to generate `rotation-specific' features using Steerable E2-CNNs, that are then group-pooled to achieve rotation-invariant local features. We demonstrate that this high performance, rotation-specific coverage from the steerable CNNs can be expanded to all rotation angles by combining it with augmentation-trained standard CNNs which have broader coverage but are often inaccurate, thus creating a state-of-the-art rotation-robust local feature matcher. We benchmark our proposed methods against existing techniques on HPatches and a newly proposed UrbanScenes3D-Air dataset for visual place recognition. Furthermore, we present a detailed analysis of the performance effects of ensembling, robust estimation, network architecture variations, and the use of rotation priors.

Connor Malone, Sourav Garg, Ming Xu et al.

Road segmentation in challenging domains, such as night, snow or rain, is a difficult task. Most current approaches boost performance using fine-tuning, domain adaptation, style transfer, or by referencing previously acquired imagery. These approaches share one or more of three significant limitations: a reliance on large amounts of annotated training data that can be costly to obtain, both anticipation of and training data from the type of environmental conditions expected at inference time, and/or imagery captured from a previous visit to the location. In this research, we remove these restrictions by improving road segmentation based on similar places. We use Visual Place Recognition (VPR) to find similar but geographically distinct places, and fuse segmentations for query images and these similar place priors using a Bayesian approach and novel segmentation quality metric. Ablation studies show the need to re-evaluate notions of VPR utility for this task. We demonstrate the system achieving state-of-the-art road segmentation performance across multiple challenging condition scenarios including night time and snow, without requiring any prior training or previous access to the same geographical locations. Furthermore, we show that this method is network agnostic, improves multiple baseline techniques and is competitive against methods specialised for road prediction.

Stephen Hausler, Sourav Garg, Punarjay Chakravarty et al.

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 reference map image for a given query image, then use a binary classification neural network that compares the query and mapping 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.

Stephen Hausler, Sourav Garg, Punarjay Chakravarty et al.

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 based on 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.

Vansh Garg, Rohit Jayanti, Krish Pandya et al.

Visual navigation ability is strongly tied to its underlying representation of the world. Unlike classical 3D maps that require globally-consistent geometry, image- or object-relative topological graphs almost entirely do away with geometric understanding. But, this comes at the cost of navigation capability, often limiting it to merely teach-and-repeat. In this work, we propose a novel map representation in the form of pixel-relative connectivity, which is geometrically accurate but does not require global geometric consistency. Inspired by recent progress in 3D grounded image matching, we construct a map from an image sequence through inter-image connectivity based on pixel correspondences in the relative 3D coordinate systems of individual image pairs. We then use this pixel-level graph to perform global path planning by approximating and sparsifying intra-image pixel connectivity. Through this, we derive a ''WayPixel Costmap'' representation and train a controller conditioned on it to predict a trajectory rollout. We show that this dense pixel-level costmap based on relative geometry is a more accurate conditioning variable for control prediction than its image- and object-level counterparts. This enables a highly capable navigation system, as validated on four types of navigation tasks in the simulator and through real world demonstrations.

Sanket Kalwar, Mihir Ungarala, Shruti Jain et al.

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 $\nabla$HFC 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 at https://diffprompter.github.io.

Stefan Podgorski, Sourav Garg, Mehdi Hosseinzadeh et al.

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 incorporating 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.

Chun-Jung Lin, Tat-Jun Chin, Sourav Garg et al.

Accurate, up-to-date High-Definition (HD) maps are critical for urban planning, infrastructure monitoring, and autonomous navigation. However, these maps quickly become outdated as environments evolve, creating a need for robust methods that not only detect changes but also incorporate them into updated 3D representations. While change detection techniques have advanced significantly, there remains a clear gap between detecting changes and actually updating 3D maps, particularly when relying on 2D image-based change detection. To address this gap, we introduce SceneEdited, the first city-scale dataset explicitly designed to support research on HD map maintenance through 3D point cloud updating. SceneEdited contains over 800 up-to-date scenes covering 73 km of driving and approximate 3 $\text{km}^2$ of urban area, with more than 23,000 synthesized object changes created both manually and automatically across 2000+ out-of-date versions, simulating realistic urban modifications such as missing roadside infrastructure, buildings, overpasses, and utility poles. Each scene includes calibrated RGB images, LiDAR scans, and detailed change masks for training and evaluation. We also provide baseline methods using a foundational image-based structure-from-motion pipeline for updating outdated scenes, as well as a comprehensive toolkit supporting scalability, trackability, and portability for future dataset expansion and unification of out-of-date object annotations. Both the dataset and the toolkit are publicly available at https://github.com/ChadLin9596/ScenePoint-ETK, establising a standardized benchmark for 3D map updating research.

Ahmad Khaliq, Michael Milford, Sourav Garg

Visual Place Recognition (VPR) is a crucial component of 6-DoF localization, visual SLAM and structure-from-motion pipelines, tasked to generate an initial list of place match hypotheses by matching global place descriptors. However, commonly-used CNN-based methods either process multiple image resolutions after training or use a single resolution and limit multi-scale feature extraction to the last convolutional layer during training. In this paper, we augment NetVLAD representation learning with low-resolution image pyramid encoding which leads to richer place representations. The resultant multi-resolution feature pyramid can be conveniently aggregated through VLAD into a single compact representation, avoiding the need for concatenation or summation of multiple patches in recent multi-scale approaches. Furthermore, we show that the underlying learnt feature tensor can be combined with existing multi-scale approaches to improve their baseline performance. Evaluation on 15 viewpoint-varying and viewpoint-consistent benchmarking datasets confirm that the proposed MultiRes-NetVLAD leads to state-of-the-art Recall@N performance for global descriptor based retrieval, compared against 11 existing techniques. Source code is publicly available at https://github.com/Ahmedest61/MultiRes-NetVLAD.

Nikhil Varma Keetha, Michael Milford, Sourav Garg

Visual Place Recognition (VPR) approaches have typically attempted to match places by identifying visual cues, image regions or landmarks that have high ``utility'' in identifying a specific place. But this concept of utility is not singular - rather it can take a range of forms. In this paper, we present a novel approach to deduce two key types of utility for VPR: the utility of visual cues `specific' to an environment, and to a particular place. We employ contrastive learning principles to estimate both the environment- and place-specific utility of Vector of Locally Aggregated Descriptors (VLAD) clusters in an unsupervised manner, which is then used to guide local feature matching through keypoint selection. By combining these two utility measures, our approach achieves state-of-the-art performance on three challenging benchmark datasets, while simultaneously reducing the required storage and compute time. We provide further analysis demonstrating that unsupervised cluster selection results in semantically meaningful results, that finer grained categorization often has higher utility for VPR than high level semantic categorization (e.g. building, road), and characterise how these two utility measures vary across different places and environments. Source code is made publicly available at https://github.com/Nik-V9/HEAPUtil.

Sourav Garg, Michael Milford

Place Recognition is a crucial capability for mobile robot localization and navigation. Image-based or Visual Place Recognition (VPR) is a challenging problem as scene appearance and camera viewpoint can change significantly when places are revisited. Recent VPR methods based on ``sequential representations'' have shown promising results as compared to traditional sequence score aggregation or single image based techniques. In parallel to these endeavors, 3D point clouds based place recognition is also being explored following the advances in deep learning based point cloud processing. However, a key question remains: is an explicit 3D structure based place representation always superior to an implicit ``spatial'' representation based on sequence of RGB images which can inherently learn scene structure. In this extended abstract, we attempt to compare these two types of methods by considering a similar ``metric span'' to represent places. We compare a 3D point cloud based method (PointNetVLAD) with image sequence based methods (SeqNet and others) and showcase that image sequence based techniques approach, and can even surpass, the performance achieved by point cloud based methods for a given metric span. These performance variations can be attributed to differences in data richness of input sensors as well as data accumulation strategies for a mobile robot. While a perfect apple-to-apple comparison may not be feasible for these two different modalities, the presented comparison takes a step in the direction of answering deeper questions regarding spatial representations, relevant to several applications like Autonomous Driving and Augmented/Virtual Reality. Source code available publicly https://github.com/oravus/seqNet.

Sourav Garg, Michael Milford

Visual Place Recognition (VPR) is the task of matching current visual imagery from a camera to images stored in a reference map of the environment. While initial VPR systems used simple direct image methods or hand-crafted visual features, recent work has focused on learning more powerful visual features and further improving performance through either some form of sequential matcher / filter or a hierarchical matching process. In both cases the performance of the initial single-image based system is still far from perfect, putting significant pressure on the sequence matching or (in the case of hierarchical systems) pose refinement stages. In this paper we present a novel hybrid system that creates a high performance initial match hypothesis generator using short learnt sequential descriptors, which enable selective control sequential score aggregation using single image learnt descriptors. Sequential descriptors are generated using a temporal convolutional network dubbed SeqNet, encoding short image sequences using 1-D convolutions, which are then matched against the corresponding temporal descriptors from the reference dataset to provide an ordered list of place match hypotheses. We then perform selective sequential score aggregation using shortlisted single image learnt descriptors from a separate pipeline to produce an overall place match hypothesis. Comprehensive experiments on challenging benchmark datasets demonstrate the proposed method outperforming recent state-of-the-art methods using the same amount of sequential information. Source code and supplementary material can be found at https://github.com/oravus/seqNet.

Sourav Garg, Ben Harwood, Gaurangi Anand et al.

Visual place recognition is challenging because there are so many factors that can cause the appearance of a place to change, from day-night cycles to seasonal change to atmospheric conditions. In recent years a large range of approaches have been developed to address this challenge including deep-learnt image descriptors, domain translation, and sequential filtering, all with shortcomings including generality and velocity-sensitivity. In this paper we propose a novel descriptor derived from tracking changes in any learned global descriptor over time, dubbed Delta Descriptors. Delta Descriptors mitigate the offsets induced in the original descriptor matching space in an unsupervised manner by considering temporal differences across places observed along a route. Like all other approaches, Delta Descriptors have a shortcoming - volatility on a frame to frame basis - which can be overcome by combining them with sequential filtering methods. Using two benchmark datasets, we first demonstrate the high performance of Delta Descriptors in isolation, before showing new state-of-the-art performance when combined with sequence-based matching. We also present results demonstrating the approach working with four different underlying descriptor types, and two other beneficial properties of Delta Descriptors in comparison to existing techniques: their increased inherent robustness to variations in camera motion and a reduced rate of performance degradation as dimensional reduction is applied. Source code is made available at https://github.com/oravus/DeltaDescriptors.

Mubariz Zaffar, Sourav Garg, Michael Milford et al.

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.

Ben Talbot, Sourav Garg, Michael Milford

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.

Krishan Rana, Jad Abou-Chakra, Sourav Garg et al.

Imitation learning has unlocked the potential for robots to exhibit highly dexterous behaviours. However, it still struggles with long-horizon, multi-object tasks due to poor sample efficiency and limited generalisation. Existing methods require a substantial number of demonstrations to cover possible task variations, making them costly and often impractical for real-world deployment. We address this challenge by introducing oriented affordance frames, a structured representation for state and action spaces that improves spatial and intra-category generalisation and enables policies to be learned efficiently from only 10 demonstrations. More importantly, we show how this abstraction allows for compositional generalisation of independently trained sub-policies to solve long-horizon, multi-object tasks. To seamlessly transition between sub-policies, we introduce the notion of self-progress prediction, which we directly derive from the duration of the training demonstrations. We validate our method across three real-world tasks, each requiring multi-step, multi-object interactions. Despite the small dataset, our policies generalise robustly to unseen object appearances, geometries, and spatial arrangements, achieving high success rates without reliance on exhaustive training data. Video demonstration can be found on our project page: https://affordance-policy.github.io/.

Yash Mehan, Kumaraditya Gupta, Rohit Jayanti et al.

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

Sourav Garg, Dustin Craggs, Vineeth Bhat et al.

Visual navigation using only a single camera and a topological map has recently become an appealing alternative to methods that require additional sensors and 3D maps. This is typically achieved through an "image-relative" approach to estimating control from a given pair of current observation and subgoal image. However, image-level representations of the world have limitations because images are strictly tied to the agent's pose and embodiment. In contrast, objects, being a property of the map, offer an embodiment- and trajectory-invariant world representation. In this work, we present a new paradigm of learning "object-relative" control that exhibits several desirable characteristics: a) new routes can be traversed without strictly requiring to imitate prior experience, b) the control prediction problem can be decoupled from solving the image matching problem, and c) high invariance can be achieved in cross-embodiment deployment for variations across both training-testing and mapping-execution settings. We propose a topometric map representation in the form of a "relative" 3D scene graph, which is used to obtain more informative object-level global path planning costs. We train a local controller, dubbed "ObjectReact", conditioned directly on a high-level "WayObject Costmap" representation that eliminates the need for an explicit RGB input. We demonstrate the advantages of learning object-relative control over its image-relative counterpart across sensor height variations and multiple navigation tasks that challenge the underlying spatial understanding capability, e.g., navigating a map trajectory in the reverse direction. We further show that our sim-only policy is able to generalize well to real-world indoor environments. Code and supplementary material are accessible via project page: https://object-react.github.io/

Rohit Jayanti, Swayam Agrawal, Vansh Garg et al.

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 degree view-point change 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. Project Page: https://segmast3r.github.io/

Savitha Sam Abraham, Sourav Garg, Feras Dayoub

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.

Sourav Garg, Krishan Rana, Mehdi Hosseinzadeh et al.

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 "image segments", 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/

Attila Lengyel, Sourav Garg, Michael Milford et al.

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.

Udit Singh Parihar, Aniket Gujarathi, Kinal Mehta et al.

The use of local detectors and descriptors in typical computer vision pipelines work 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 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.

Sourav Garg, Tobias Fischer, Michael Milford

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 numerous open challenges and suggest areas that require more in-depth attention in future works.

Stephen Hausler, Sourav Garg, Ming Xu et al.

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 outperforms both global and local feature descriptor-based methods with comparable compute, achieving state-of-the-art visual place recognition results 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.

Sourav Garg, Niko Sünderhauf, Feras Dayoub et al.

For robots to navigate and interact more richly with the world around them, they will likely require a deeper understanding of the world in which they operate. In robotics and related research fields, the study of understanding is often referred to as semantics, which dictates what does the world "mean" to a robot, and is strongly tied to the question of how to represent that meaning. With humans and robots increasingly operating in the same world, the prospects of human-robot interaction also bring semantics and ontology of natural language into the picture. Driven by need, as well as by enablers like increasing availability of training data and computational resources, semantics is a rapidly growing research area in robotics. The field has received significant attention in the research literature to date, but most reviews and surveys have focused on particular aspects of the topic: the technical research issues regarding its use in specific robotic topics like mapping or segmentation, or its relevance to one particular application domain like autonomous driving. A new treatment is therefore required, and is also timely because so much relevant research has occurred since many of the key surveys were published. This survey therefore provides an overarching snapshot of where semantics in robotics stands today. We establish a taxonomy for semantics research in or relevant to robotics, split into four broad categories of activity, in which semantics are extracted, used, or both. Within these broad categories we survey dozens of major topics including fundamentals from the computer vision field and key robotics research areas utilizing semantics, including mapping, navigation and interaction with the world. The survey also covers key practical considerations, including enablers like increased data availability and improved computational hardware, and major application areas where...

Satyajit Tourani, Dhagash Desai, Udit Singh Parihar et al.

Significant advances have been made recently in Visual Place Recognition (VPR), feature correspondence, and localization due to the proliferation of deep-learning-based methods. However, existing approaches tend to address, partially or fully, only one of two key challenges: viewpoint change and perceptual aliasing. In this paper, we present novel research that simultaneously addresses both challenges by combining deep-learned features with geometric transformations based on reasonable domain assumptions about navigation on a ground-plane, whilst also removing the requirement for specialized hardware setup (e.g. lighting, downwards facing cameras). In particular, our integration of VPR with SLAM by leveraging the robustness of deep-learned features and our homography-based extreme viewpoint invariance significantly boosts the performance of VPR, feature correspondence, and pose graph submodules of the SLAM pipeline. For the first time, we demonstrate a localization system capable of state-of-the-art performance despite perceptual aliasing and extreme 180-degree-rotated viewpoint change in a range of real-world and simulated experiments. Our system is able to achieve early loop closures that prevent significant drifts in SLAM trajectories. We also compare extensively several deep architectures for VPR and descriptor matching. We also show that superior place recognition and descriptor matching across opposite views results in a similar performance gain in back-end pose graph optimization.

Madhu Vankadari, Sourav Garg, Anima Majumder et al.

In this paper, we look into the problem of estimating per-pixel depth maps from unconstrained RGB monocular night-time images which is a difficult task that has not been addressed adequately in the literature. The state-of-the-art day-time depth estimation methods fail miserably when tested with night-time images due to a large domain shift between them. The usual photo metric losses used for training these networks may not work for night-time images due to the absence of uniform lighting which is commonly present in day-time images, making it a difficult problem to solve. We propose to solve this problem by posing it as a domain adaptation problem where a network trained with day-time images is adapted to work for night-time images. Specifically, an encoder is trained to generate features from night-time images that are indistinguishable from those obtained from day-time images by using a PatchGAN-based adversarial discriminative learning method. Unlike the existing methods that directly adapt depth prediction (network output), we propose to adapt feature maps obtained from the encoder network so that a pre-trained day-time depth decoder can be directly used for predicting depth from these adapted features. Hence, the resulting method is termed as "Adversarial Domain Feature Adaptation (ADFA)" and its efficacy is demonstrated through experimentation on the challenging Oxford night driving dataset. Also, The modular encoder-decoder architecture for the proposed ADFA method allows us to use the encoder module as a feature extractor which can be used in many other applications. One such application is demonstrated where the features obtained from our adapted encoder network are shown to outperform other state-of-the-art methods in a visual place recognition problem, thereby, further establishing the usefulness and effectiveness of the proposed approach.

Sourav Garg, Michael Milford

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 state-of-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.

Sourav Garg, Madhu Babu, Thanuja Dharmasiri et al.

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 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 those keypoints to those in 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 degree of appearance change and camera motion.

Sourav Garg, Niko Suenderhauf, Michael Milford

Human visual scene understanding is so remarkable that we are able to recognize a revisited place when entering it from the opposite direction it was first visited, even in the presence of extreme variations in appearance. This capability is especially apparent during driving: a human driver can recognize where they are when travelling in the reverse direction along a route for the first time, without having to turn back and look. The difficulty of this problem exceeds any addressed in past appearance- and viewpoint-invariant visual place recognition (VPR) research, in part because large parts of the scene are not commonly observable from opposite directions. Consequently, as shown in this paper, the precision-recall performance of current state-of-the-art viewpoint- and appearance-invariant VPR techniques is orders of magnitude below what would be usable in a closed-loop system. Current engineered solutions predominantly rely on panoramic camera or LIDAR sensing setups; an eminently suitable engineering solution but one that is clearly very different to how humans navigate, which also has implications for how naturally humans could interact and communicate with the navigation system. In this paper we develop a suite of novel semantic- and appearance-based techniques to enable for the first time high performance place recognition in this challenging scenario. We first propose a novel Local Semantic Tensor (LoST) descriptor of images using the convolutional feature maps from a state-of-the-art dense semantic segmentation network. Then, to verify the spatial semantic arrangement of the top matching candidates, we develop a novel approach for mining semantically-salient keypoint correspondences.

Sourav Garg, Niko Suenderhauf, Michael Milford

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-look 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.

Sourav Garg, Adam Jacobson, Swagat Kumar et al.

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 benchmark and new 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.

Sourav Garg, Swagat Kumar, Rajesh Ratnakaram et al.

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.