no code implementations • 6 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.
1 code implementation • 1 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.
Ranked #1 on Visual Place Recognition on Nardo-Air R
no code implementations • 12 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.
no code implementations • 30 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.
no code implementations • 30 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.
1 code implementation • 19 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.
1 code implementation • 6 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.
1 code implementation • 29 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.
no code implementations • 28 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.
no code implementations • 28 Jun 2022 • Stephen Hausler, Ming Xu, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, Michael Milford
6-DoF visual localization systems utilize principled approaches rooted in 3D geometry to perform accurate camera pose estimation of images to a map.
no code implementations • 27 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.
no code implementations • 10 Mar 2022 • Abhishek Peri, Kinal Mehta, Avneesh Mishra, Michael Milford, Sourav Garg, K. Madhava Krishna
Sparse local feature matching is pivotal for many computer vision and robotics tasks.
1 code implementation • 18 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.
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.
Ranked #2 on Image Retrieval on 24/7 Tokyo
1 code implementation • 6 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.
Ranked #1 on Visual Place Recognition on Berlin Kudamm
1 code implementation • 22 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.
1 code implementation • 15 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.
no code implementations • 11 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.
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.
Ranked #1 on Visual Localization on RobotCar Seasons v2
1 code implementation • 23 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.
no code implementations • 2 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.
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.
no code implementations • 3 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.
1 code implementation • 10 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.
1 code implementation • 17 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.
1 code implementation • 23 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.
1 code implementation • 20 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
1 code implementation • 16 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.
no code implementations • 6 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.
no code implementations • 25 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.