Search Results for author: Sourav Garg

Found 30 papers, 17 papers with code

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

no code implementations6 Oct 2023 Sanket Kalwar, Mihir Ungarala, Shruti Jain, Aaron Monis, Krishna Reddy Konda, Sourav Garg, K Madhava Krishna

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.

Autonomous Driving Segmentation +1

AnyLoc: Towards Universal Visual Place Recognition

1 code implementation1 Aug 2023 Nikhil Keetha, Avneesh Mishra, Jay Karhade, Krishna Murthy Jatavallabhula, Sebastian Scherer, Madhava Krishna, Sourav Garg

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.

Image Retrieval Visual Place Recognition

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

no code implementations12 Jul 2023 Krishan Rana, Jesse Haviland, Sourav Garg, Jad Abou-Chakra, Ian Reid, Niko Suenderhauf

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.

Robot Task Planning

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

no code implementations30 Jun 2023 Stephen Hausler, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford

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.

Binary Classification Visual Place Recognition

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

no code implementations30 Jun 2023 Stephen Hausler, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford

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.

Autonomous Vehicles Visual Localization

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

1 code implementation19 Mar 2023 Ming Xu, Sourav Garg, Michael Milford, Stephen Gould

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.

Dynamic Time Warping Information Retrieval +4

Visual Place Recognition: A Tutorial

1 code implementation6 Mar 2023 Stefan Schubert, Peer Neubert, Sourav Garg, Michael Milford, Tobias Fischer

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.

Visual Place Recognition

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

1 code implementation29 Sep 2022 Sanket Kalwar, Dhruv Patel, Aakash Aanegola, Krishna Reddy Konda, Sourav Garg, K Madhava Krishna

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.

Image Enhancement object-detection +1

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

no code implementations28 Jun 2022 Madhu Vankadari, Stuart Golodetz, Sourav Garg, Sangyun Shin, Andrew Markham, Niki Trigoni

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.

Depth Estimation Motion Estimation

Improving Road Segmentation in Challenging Domains Using Similar Place Priors

no code implementations27 May 2022 Connor Malone, Sourav Garg, Ming Xu, Thierry Peynot, Michael Milford

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.

Domain Adaptation Road Segmentation +3

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

1 code implementation18 Feb 2022 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.

Benchmarking Representation Learning +2

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

1 code implementation ICCV 2021 Attila Lengyel, Sourav Garg, Michael Milford, Jan C. van Gemert

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.

Domain Adaptation Image Retrieval +1

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

1 code implementation6 Jul 2021 Nikhil Varma Keetha, Michael Milford, Sourav Garg

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.

Contrastive Learning Image Retrieval +1

SeqNetVLAD vs PointNetVLAD: Image Sequence vs 3D Point Clouds for Day-Night Place Recognition

1 code implementation22 Jun 2021 Sourav Garg, Michael Milford

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.

Autonomous Driving Visual Place Recognition

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

1 code implementation15 Mar 2021 Udit Singh Parihar, Aniket Gujarathi, Kinal Mehta, Satyajit Tourani, Sourav Garg, Michael Milford, K. Madhava Krishna

The use of local detectors and descriptors in typical computer vision pipelines work well until variations in viewpoint and appearance change become extreme.

Pose Estimation Visual Place Recognition

Where is your place, Visual Place Recognition?

no code implementations11 Mar 2021 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.

Visual Place Recognition

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

3 code implementations CVPR 2021 Stephen Hausler, Sourav Garg, Ming Xu, Michael Milford, Tobias Fischer

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.

Computational Efficiency Visual Localization +1

SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition

1 code implementation23 Feb 2021 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.

Autonomous Driving Image Retrieval +6

Semantics for Robotic Mapping, Perception and Interaction: A Survey

no code implementations2 Jan 2021 Sourav Garg, Niko Sünderhauf, Feras Dayoub, Douglas Morrison, Akansel Cosgun, Gustavo Carneiro, Qi Wu, Tat-Jun Chin, Ian Reid, Stephen Gould, Peter Corke, Michael Milford

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.

Autonomous Driving Navigate

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

1 code implementation ECCV 2020 Madhu Vankadari, Sourav Garg, Anima Majumder, Swagat Kumar, Ardhendu Behera

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.

Depth Prediction Domain Adaptation +3

Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments

no code implementations3 Oct 2020 Satyajit Tourani, Dhagash Desai, Udit Singh Parihar, Sourav Garg, Ravi Kiran Sarvadevabhatla, Michael Milford, K. Madhava Krishna

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.

Visual Place Recognition

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

1 code implementation10 Jun 2020 Sourav Garg, Ben Harwood, Gaurangi Anand, Michael Milford

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.

Autonomous Driving Image Retrieval +4

VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change

1 code implementation17 May 2020 Mubariz Zaffar, Sourav Garg, Michael Milford, Julian Kooij, David Flynn, Klaus McDonald-Maier, Shoaib Ehsan

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.

Autonomous Navigation Image Retrieval +2

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

1 code implementation23 Jan 2020 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.

Image Compression Quantization +2

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

1 code implementation20 Feb 2019 Sourav Garg, Madhu Babu V, Thanuja Dharmasiri, Stephen Hausler, Niko Suenderhauf, Swagat Kumar, Tom Drummond, Michael Milford

Visual place recognition (VPR) - the act of recognizing a familiar visual place - becomes difficult when there is extreme environmental appearance change or viewpoint change.

Robotics

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

1 code implementation16 Apr 2018 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.

Navigate Scene Understanding +2

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

no code implementations6 Apr 2018 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.

Visual Place Recognition

An Occlusion Reasoning Scheme for Monocular Pedestrian Tracking in Dynamic Scenes

no code implementations25 Jan 2015 Sourav Garg, Swagat Kumar, Rajesh Ratnakaram, Prithwijit Guha

This paper looks into the problem of pedestrian tracking using a monocular, potentially moving, uncalibrated camera.

Cannot find the paper you are looking for? You can Submit a new open access paper.