← Search

Sourav Garg

35 accepted papers

2025

Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames

CoRL 2025poster

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 possib…

Cited by 0SourcecodeScholar
2025

ObjectReact: Learning Object-Relative Control for Visual Navigation

CoRL 2025poster

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 s…

Cited by 0SourceScholar
2025

Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention Mechanisms

ICRA 2025

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 orde

Cited by 12SourcecodeScholar
2025

SegMASt3R: Geometry Grounded Segment Matching

NeurIPS 2025spotlight

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 r…

Cited by 0SourceScholar
2025

TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals

ICRA 2025

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 enable

Cited by 4SourcecodeScholar
2024

AnyLoc: Towards Universal Visual Place Recognition

RA-L 2024

Visual Place Recognition (VPR) is vital for robot localization. To date, the most performant VPR approaches are <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">environment- and task-specific:</i> while they exhibit strong performance in structured en

Cited by 253SourcecodeScholar
2024

DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions

IROS 2024poster

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 la…

Cited by 0SourcecodeScholar
2024

QueSTMaps: Queryable Semantic Topological Maps for 3D Scene Understanding

IROS 2024

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

Cited by 10SourcecodeScholar
2024

RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation

ICRA 2024poster

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 pro…

Cited by 19SourcecodeScholar
2023

Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths

ICLR 2023poster

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 th…

2023

DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions

IROS 2023poster

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 m…

Cited by 6SourceScholar
2023

GDIP: Gated Differentiable Image Processing for Object Detection in Adverse Conditions

ICRA 2023poster

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 in…

Cited by 68SourcecodeScholar
2023

Locking On: Leveraging Dynamic Vehicle-Imposed Motion Constraints to Improve Visual Localization

IROS 2023poster

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 t…

Cited by 0SourceScholar
2023

SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning

CoRL 2023oral

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…

Cited by 315SourcecodeScholar
2022

Improving Road Segmentation in Challenging Domains Using Similar Place Priors

RA-L 2022

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 limitatio

Cited by 4SourceScholar
2022

Improving Worst Case Visual Localization Coverage via Place-Specific Sub-Selection in Multi-Camera Systems

RA-L 2022

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

Cited by 10SourceScholar
2022

MultiRes-NetVLAD: Augmenting Place Recognition Training With Low-Resolution Imagery

RA-L 2022

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 reso

Cited by 41SourcecodeScholar
2022

When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation

CoRL 2022poster

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. temp…

Cited by 27SourceScholar
2021

A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place Recognition

RA-L 2021

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 letter, we pr

Cited by 30SourcecodeScholar
2021

Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition

CVPR 2021poster

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 loca…

Cited by 463PDFcodeScholar
2021

RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching

IROS 2021poster

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…

Cited by 35SourcecodeScholar
2021

SeqMatchNet: Contrastive Learning with Sequence Matching for Place Recognition & Relocalization

CoRL 2021oral

Visual Place Recognition (VPR) for mobile robot global relocalization is a well-studied problem, where contrastive learning based representation training methods have led to state-of-the-art performance. However, these methods are mainly designed for single image based VPR, where sequential informat…

Cited by 35SourcecodeScholar
2021

Zero-Shot Day-Night Domain Adaptation With a Physics Prior

ICCV 2021poster

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…

Cited by 92PDFcodeScholar
2020

Delta Descriptors: Change-Based Place Representation for Robust Visual Localization

RA-L 2020

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-l

Cited by 48SourcecodeScholar
2020

Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations

ICRA 2020poster

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 compu…

Cited by 33SourcecodeScholar
2020

Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation

ECCV 2020poster

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 nig…

2019

Look No Deeper: Recognizing Places from Opposing Viewpoints under Varying Scene Appearance using Single-View Depth Estimation

ICRA 2019poster

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…

Cited by 29SourcecodeScholar
2018

Don't Look Back: Robustifying Place Categorization for Viewpoint- and Condition-Invariant Place Recognition

ICRA 2018poster

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 typicall…

Cited by 94SourceScholar
2018

LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics

RSS 2018poster

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 rec…

2018

OpenSeqSLAM2.0: An Open Source Toolbox for Visual Place Recognition Under Changing Conditions

IROS 2018poster

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 syst…

Cited by 30SourceScholar
2017

Improving condition- and environment-invariant place recognition with semantic place categorization

IROS 2017poster

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 a…

Cited by 38SourceScholar
2016

High-fidelity simulation for evaluating robotic vision performance

IROS 2016poster

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, mak…

Cited by 36SourceScholar