Sourav Garg

88 papers A* 11A 9B 2C 1Misc 3Journal 54Unranked 8
YearRankTypeTitle / Venue / Authors
2025 J jnl
ObjectReact: Learning Object-Relative Control for Visual Navigation.
CoRR
Sourav Garg, Dustin Craggs, Vineeth Bhat, Lachlan Mares, Stefan Podgorski, Madhava Krishna, Feras Dayoub, Ian D. Reid
2025 A* conf
Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention Mechanisms.
ICRA
Chun-Jung Lin, Sourav Garg, Tat-Jun Chin, Feras Dayoub
2025 J jnl
SceneEdited: A City-Scale Benchmark for 3D HD Map Updating via Image-Guided Change Detection.
CoRR
Chun-Jung Lin, Tat-Jun Chin, Sourav Garg, Feras Dayoub
2025 J jnl
SegMASt3R: Geometry Grounded Segment Matching.
CoRR
Rohit Jayanti, Swayam Agrawal, Vansh Garg, Siddharth Tourani, Muhammad Haris Khan, Sourav Garg, Madhava Krishna
2025 A* conf
TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals.
ICRA
Stefan Podgorski, Sourav Garg, Mehdi Hosseinzadeh, Lachlan Mares, Feras Dayoub, Ian Reid
2025 J jnl
TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals.
CoRR
Stefan Podgorski, Sourav Garg, Mehdi Hosseinzadeh, Lachlan Mares, Feras Dayoub, Ian D. Reid
2025 A conf
To Ask or Not to Ask? Detecting Absence of Information in Vision and Language Navigation.
WACV
Savitha Sam Abraham, Sourav Garg, Feras Dayoub
2024 J jnl
Affordance-Centric Policy Learning: Sample Efficient and Generalisable Robot Policy Learning using Affordance-Centric Task Frames.
CoRR
Krishan Rana, Jad Abou-Chakra, Sourav Garg, Robert Lee, Ian D. Reid, Niko Sünderhauf
2024 J jnl
AnyLoc: Towards Universal Visual Place Recognition.
IEEE Robotics Autom. Lett.
Nikhil Varma Keetha, Avneesh Mishra, Jay Karhade, Krishna Murthy Jatavallabhula, Sebastian A. Scherer, Madhava Krishna, Sourav Garg
2024 A conf
DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions.
IROS
Sanket Kalwar, Mihir Ungarala, Shruti Jain, Aaron Monis, Krishna Reddy Konda, Sourav Garg, K. Madhava Krishna
2024 A conf
QueSTMaps: Queryable Semantic Topological Maps for 3D Scene Understanding.
IROS
Yash Mehan, Kumaraditya Gupta, Rohit Jayanti, Anirudh Govil, Sourav Garg, Madhava Krishna
2024 J jnl
QueSTMaps: Queryable Semantic Topological Maps for 3D Scene Understanding.
CoRR
Yash Mehan, Kumaraditya Gupta, Rohit Jayanti, Anirudh Govil, Sourav Garg, Madhava Krishna
2024 — conf
Revisit Anything: Visual Place Recognition via Image Segment Retrieval.
ECCV (68)
Kartik Garg, Sai Shubodh Puligilla, Shishir Kolathaya, Madhava Krishna, Sourav Garg
2024 J jnl
Revisit Anything: Visual Place Recognition via Image Segment Retrieval.
CoRR
Kartik Garg, Sai Shubodh Puligilla, Shishir Kolathaya, Madhava Krishna, Sourav Garg
2024 A* conf
RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation.
ICRA
Sourav Garg, Krishan Rana, Mehdi Hosseinzadeh, Lachlan Mares, Niko Sünderhauf, Feras Dayoub, Ian D. Reid
2024 J jnl
RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation.
CoRR
Sourav Garg, Krishan Rana, Mehdi Hosseinzadeh, Lachlan Mares, Niko Sünderhauf, Feras Dayoub, Ian Reid
2024 J jnl
Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention Mechanisms.
CoRR
Chun-Jung Lin, Sourav Garg, Tat-Jun Chin, Feras Dayoub
2024 J jnl
To Ask or Not to Ask? Detecting Absence of Information in Vision and Language Navigation.
CoRR
Savitha Sam Abraham, Sourav Garg, Feras Dayoub
2024 — conf
VLAD-BuFF: Burst-Aware Fast Feature Aggregation for Visual Place Recognition.
ECCV (44)
Ahmad Khaliq, Ming Xu, Stephen Hausler, Michael Milford, Sourav Garg
2024 J jnl
VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition.
CoRR
Ahmad Khaliq, Ming Xu, Stephen Hausler, Michael Milford, Sourav Garg
2024 J jnl
Visual Place Recognition: A Tutorial [Tutorial].
IEEE Robotics Autom. Mag.
Stefan Schubert, Peer Neubert, Sourav Garg, Michael Milford, Tobias Fischer
2023 J jnl
AnyLoc: Towards Universal Visual Place Recognition.
CoRR
Nikhil Varma Keetha, Avneesh Mishra, Jay Karhade, Krishna Murthy Jatavallabhula, Sebastian A. Scherer, K. Madhava Krishna, Sourav Garg
2023 A* conf
Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths.
ICLR
Ming Xu, Sourav Garg, Michael Milford, Stephen Gould
2023 J jnl
Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths.
CoRR
Ming Xu, Sourav Garg, Michael Milford, Stephen Gould
2023 J jnl
DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions.
CoRR
Sanket Kalwar, Mihir Ungarala, Shruti Jain, Aaron Monis, Krishna Reddy Konda, Sourav Garg, K. Madhava Krishna
2023 A conf
DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions.
IROS
Stephen Hausler, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
2023 J jnl
DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions.
CoRR
Stephen Hausler, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
2023 A* conf
GDIP: Gated Differentiable Image Processing for Object Detection in Adverse Conditions.
ICRA
Sanket Kalwar, Dhruv Patel, Aakash Aanegola, Krishna Reddy Konda, Sourav Garg, K. Madhava Krishna
2023 — conf
Hierarchical Unsupervised Topological SLAM.
ITSC
Ayush Sharma, Yash Mehan, Pradyumna Dasu, Sourav Garg, K. Madhava Krishna
2023 J jnl
Hierarchical Unsupervised Topological SLAM.
CoRR
Ayush Sharma, Yash Mehan, Pradyumna Dasu, Sourav Garg, K. Madhava Krishna
2023 A conf
Locking On: Leveraging Dynamic Vehicle-Imposed Motion Constraints to Improve Visual Localization.
IROS
Stephen Hausler, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
2023 J jnl
Locking On: Leveraging Dynamic Vehicle-Imposed Motion Constraints to Improve Visual Localization.
CoRR
Stephen Hausler, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
2023 Misc conf
SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning.
CoRL
Krishan Rana, Jesse Haviland, Sourav Garg, Jad Abou-Chakra, Ian D. Reid, Niko Sünderhauf
2023 J jnl
SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Task Planning.
CoRR
Krishan Rana, Jesse Haviland, Sourav Garg, Jad Abou-Chakra, Ian D. Reid, Niko Sünderhauf
2023 J jnl
Visual Place Recognition: A Tutorial.
CoRR
Stefan Schubert, Peer Neubert, Sourav Garg, Michael Milford, Tobias Fischer
2022 J jnl
GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions.
CoRR
Sanket Kalwar, Dhruv Patel, Aakash Aanegola, Krishna Reddy Konda, Sourav Garg, K. Madhava Krishna
2022 J jnl
Improving Road Segmentation in Challenging Domains Using Similar Place Priors.
CoRR
Connor Malone, Sourav Garg, Ming Xu, Thierry Peynot, Michael Milford
2022 J jnl
Improving Road Segmentation in Challenging Domains Using Similar Place Priors.
IEEE Robotics Autom. Lett.
Connor Malone, Sourav Garg, Ming Xu, Thierry Peynot, Michael Milford
2022 J jnl
Improving Worst Case Visual Localization Coverage via Place-Specific Sub-Selection in Multi-Camera Systems.
IEEE Robotics Autom. Lett.
Stephen Hausler, Ming Xu, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
2022 J jnl
Improving Worst Case Visual Localization Coverage via Place-specific Sub-selection in Multi-camera Systems.
CoRR
Stephen Hausler, Ming Xu, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
2022 J jnl
MultiRes-NetVLAD: Augmenting Place Recognition Training With Low-Resolution Imagery.
IEEE Robotics Autom. Lett.
Ahmad Khaliq, Michael Milford, Sourav Garg
2022 J jnl
MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery.
CoRR
Ahmad Khaliq, Michael Milford, Sourav Garg
2022 J jnl
ReF - Rotation Equivariant Features for Local Feature Matching.
CoRR
Abhishek Peri, Kinal Mehta, Avneesh Mishra, Michael Milford, Sourav Garg, K. Madhava Krishna
2022 J jnl
Semantic-geometric visual place recognition: a new perspective for reconciling opposing views.
Int. J. Robotics Res.
Sourav Garg, Niko Sünderhauf, Michael Milford
2022 Misc conf
When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation.
CoRL
Madhu Vankadari, Stuart Golodetz, Sourav Garg, Sangyun Shin, Andrew Markham, Niki Trigoni
2022 J jnl
When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation.
CoRR
Madhu Vankadari, Stuart Golodetz, Sourav Garg, Sangyun Shin, Andrew Markham, Niki Trigoni
2021 J jnl
A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place Recognition.
CoRR
Nikhil Varma Keetha, Michael Milford, Sourav Garg
2021 J jnl
A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place Recognition.
IEEE Robotics Autom. Lett.
Nikhil Varma Keetha, Michael Milford, Sourav Garg
2021 — conf
Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-aliased Indoor Environments.
VISIGRAPP (5: VISAPP)
Satyajit Tourani, Dhagash Desai, Udit Singh Parihar, Sourav Garg, Ravi Kiran Sarvadevabhatla, Michael Milford, K. Madhava Krishna
2021 A* conf
Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition.
CVPR
Stephen Hausler, Sourav Garg, Ming Xu, Michael Milford, Tobias Fischer
2021 J jnl
Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition.
CoRR
Stephen Hausler, Sourav Garg, Ming Xu, Michael Milford, Tobias Fischer
2021 A conf
RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching.
IROS
Udit Singh Parihar, Aniket Gujarathi, Kinal Mehta, Satyajit Tourani, Sourav Garg, Michael Milford, K. Madhava Krishna
2021 J jnl
RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching.
CoRR
Udit Singh Parihar, Aniket Gujarathi, Kinal Mehta, Satyajit Tourani, Sourav Garg, Michael Milford, K. Madhava Krishna
2021 J jnl
Semantics for Robotic Mapping, Perception and Interaction: A Survey.
CoRR
Sourav Garg, Niko Sünderhauf, Feras Dayoub, Douglas Morrison, Akansel Cosgun, Gustavo Carneiro, Qi Wu, Tat-Jun Chin, Ian D. Reid, Stephen Gould, Peter Corke, Michael Milford
2021 Misc conf
SeqMatchNet: Contrastive Learning with Sequence Matching for Place Recognition & Relocalization.
CoRL
Sourav Garg, Madhu Babu Vankadari, Michael Milford
2021 J jnl
SeqNet: Learning Descriptors for Sequence-Based Hierarchical Place Recognition.
IEEE Robotics Autom. Lett.
Sourav Garg, Michael Milford
2021 J jnl
SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition.
CoRR
Sourav Garg, Michael Milford
2021 J jnl
SeqNetVLAD vs PointNetVLAD: Image Sequence vs 3D Point Clouds for Day-Night Place Recognition.
CoRR
Sourav Garg, Michael Milford
2021 J jnl
VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change.
Int. J. Comput. Vis.
Mubariz Zaffar, Sourav Garg, Michael Milford, Julian F. P. Kooij, David Flynn, Klaus D. McDonald-Maier, Shoaib Ehsan
2021 A* conf
Where Is Your Place, Visual Place Recognition?
IJCAI
Sourav Garg, Tobias Fischer, Michael Milford
2021 J jnl
Where is your place, Visual Place Recognition?
CoRR
Sourav Garg, Tobias Fischer, Michael Milford
2021 A* conf
Zero-Shot Day-Night Domain Adaptation with a Physics Prior.
ICCV
Attila Lengyel, Sourav Garg, Michael Milford, Jan C. van Gemert
2021 J jnl
Zero-Shot Domain Adaptation with a Physics Prior.
CoRR
Attila Lengyel, Sourav Garg, Michael Milford, Jan C. van Gemert
2020 J jnl
Delta Descriptors: Change-Based Place Representation for Robust Visual Localization.
CoRR
Sourav Garg, Ben Harwood, Gaurangi Anand, Michael Milford
2020 J jnl
Delta Descriptors: Change-Based Place Representation for Robust Visual Localization.
IEEE Robotics Autom. Lett.
Sourav Garg, Ben Harwood, Gaurangi Anand, Michael Milford
2020 J jnl
Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments.
CoRR
Satyajit Tourani, Dhagash Desai, Udit Singh Parihar, Sourav Garg, Ravi Kiran Sarvadevabhatla, K. Madhava Krishna
2020 A* conf
Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations.
ICRA
Sourav Garg, Michael Milford
2020 J jnl
Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations.
CoRR
Sourav Garg, Michael Milford
2020 J jnl
Semantics for Robotic Mapping, Perception and Interaction: A Survey.
Found. Trends Robotics
Sourav Garg, Niko Sünderhauf, Feras Dayoub, Douglas Morrison, Akansel Cosgun, Gustavo Carneiro, Qi Wu, Tat-Jun Chin, Ian D. Reid, Stephen Gould, Peter Corke, Michael Milford
2020 — conf
Unsupervised Monocular Depth Estimation for Night-Time Images Using Adversarial Domain Feature Adaptation.
ECCV (28)
Madhu Babu Vankadari, Sourav Garg, Anima Majumder, Swagat Kumar, Ardhendu Behera
2020 J jnl
Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation.
CoRR
Madhu Babu Vankadari, Sourav Garg, Anima Majumder, Swagat Kumar, Ardhendu Behera
2019 A* conf
Look No Deeper: Recognizing Places from Opposing Viewpoints under Varying Scene Appearance using Single-View Depth Estimation.
ICRA
Sourav Garg, Madhu Babu Vankadari, Thanuja Dharmasiri, Stephen Hausler, Niko Sünderhauf, Swagat Kumar, Tom Drummond, Michael Milford
2019 J jnl
Look No Deeper: Recognizing Places from Opposing Viewpoints under Varying Scene Appearance using Single-View Depth Estimation.
CoRR
Sourav Garg, V. Madhu Babu, Thanuja Dharmasiri, Stephen Hausler, Niko Sünderhauf, Swagat Kumar, Tom Drummond, Michael Milford
2018 A* conf
Don't Look Back: Robustifying Place Categorization for Viewpoint- and Condition-Invariant Place Recognition.
ICRA
Sourav Garg, Niko Sünderhauf, Michael Milford
2018 J jnl
Don't Look Back: Robustifying Place Categorization for Viewpoint- and Condition-Invariant Place Recognition.
CoRR
Sourav Garg, Niko Sünderhauf, Michael Milford
2018 — conf
LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics.
Robotics: Science and Systems
Sourav Garg, Niko Sünderhauf, Michael Milford
2018 J jnl
LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics.
CoRR
Sourav Garg, Niko Sünderhauf, Michael Milford
2018 A conf
OpenSeqSLAM2.0: An Open Source Toolbox for Visual Place Recognition Under Changing Conditions.
IROS
Ben Talbot, Sourav Garg, Michael Milford
2018 J jnl
OpenSeqSLAM2.0: An Open Source Toolbox for Visual Place Recognition Under Changing Conditions.
CoRR
Ben Talbot, Sourav Garg, Michael Milford
2017 J jnl
Improving Condition- and Environment-Invariant Place Recognition with Semantic Place Categorization.
CoRR
Sourav Garg, Adam Jacobson, Swagat Kumar, Michael Milford
2017 A conf
Improving condition- and environment-invariant place recognition with semantic place categorization.
IROS
Sourav Garg, Adam Jacobson, Swagat Kumar, Michael Milford
2016 A conf
High-fidelity simulation for evaluating robotic vision performance.
IROS
John Skinner, Sourav Garg, Niko Sünderhauf, Peter I. Corke, Ben Upcroft, Michael Milford
2015 — conf
A Hierarchical Frame-by-Frame Association Method Based on Graph Matching for Multi-object Tracking.
ISVC (1)
Sourav Garg, Ehtesham Hassan, Swagat Kumar, Prithwijit Guha
2015 J jnl
An Occlusion Reasoning Scheme for Monocular Pedestrian Tracking in Dynamic Scenes.
CoRR
Sourav Garg, Swagat Kumar, Rajesh Ratnakaram, Prithwijit Guha
2015 B conf
An occlusion reasoning scheme for monocular pedestrian tracking in dynamic scenes.
AVSS
Sourav Garg, Swagat Kumar, Rajesh Ratnakaram, Prithwijit Guha
2015 — conf
Product counting using images with application to robot-based retail stock assessment.
TePRA
Nishant Kejriwal, Sourav Garg, Swagat Kumar
2014 C conf
A novel SURF-based algorithm for tracking a 'Human' in a dynamic environment.
ICARCV
Meenakshi Gupta, Swagat Kumar, Sourav Garg, Nishant Kejriwal, Laxmidhar Behera
2013 B conf
An on-line visual human tracking algorithm using SURF-based dynamic object model.
ICIP
Meenakshi Gupta, Sourav Garg, Swagat Kumar, Laxmidhar Behera