no code implementations • ECCV 2020 • Sizhuo Ma, Mohit Gupta
We present inertial safety maps (ISM), a novel scene representation designed for fast detection of obstacles in scenarios involving camera or scene motion, such as robot navigation and human-robot interaction.
no code implementations • 2 Jun 2024 • Tianyi Zhang, Matthew Dutson, Vivek Boominathan, Mohit Gupta, Ashok Veeraraghavan
To the best of our knowledge, our approach is the first to achieve online, real-time image reconstruction on QIS.
no code implementations • 22 Apr 2024 • Avinash Anand, Kritarth Prasad, Ujjwal Goel, Mohit Gupta, Naman Lal, Astha Verma, Rajiv Ratn Shah
This research underscores the potential of harnessing LLMs for citation generation, opening a compelling avenue for exploring the intricate connections between scientific documents.
1 code implementation • 19 Apr 2024 • Avinash Anand, Mohit Gupta, Kritarth Prasad, Navya Singla, Sanjana Sanjeev, Jatin Kumar, Adarsh Raj Shivam, Rajiv Ratn Shah
Our experiments reveal that among the three models, MAmmoTH-13B emerges as the most proficient, achieving the highest level of competence in solving the presented mathematical problems.
no code implementations • 17 Apr 2024 • Vansh Gupta, Mohit Gupta, Jai Garg, Nitesh Garg
Existing solution uses similarity of strings, and edit distance algorithms to find out the similar addresses from the address database, but these algorithms could not work effectively with redundant, unstructured, or incomplete address data.
no code implementations • 17 Apr 2024 • Mohit Gupta, Nitesh Garg, Jai Garg, Vansh Gupta, Devraj Gautam
Parcels delivery is a critical activity in railways.
no code implementations • 16 Apr 2024 • Avinash Anand, Raj Jaiswal, Pijush Bhuyan, Mohit Gupta, Siddhesh Bangar, Md. Modassir Imam, Rajiv Ratn Shah, Shin'ichi Satoh
Our proposed approach achieves an IOU of 0. 96 and an OCR Accuracy of 78%, showcasing a remarkable improvement of approximately 25% in the OCR Accuracy compared to the previous Table Transformer approach.
1 code implementation • 15 Apr 2024 • Avinash Anand, Raj Jaiswal, Mohit Gupta, Siddhesh S Bangar, Pijush Bhuyan, Naman Lal, Rajeev Singh, Ritika Jha, Rajiv Ratn Shah, Shin'ichi Satoh
To solve this problem, domain adaptation approaches have been developed that use a small quantity of labeled data to adjust the model to the target domain.
no code implementations • 15 Apr 2024 • Avinash Anand, Mohit Gupta, Kritarth Prasad, Ujjwal Goel, Naman Lal, Astha Verma, Rajiv Ratn Shah
Citation Text Generation (CTG) is a task in natural language processing (NLP) that aims to produce text that accurately cites or references a cited document within a source document.
no code implementations • 26 Mar 2024 • Fangzhou Mu, Carter Sifferman, Sacha Jungerman, Yiquan Li, Mark Han, Michael Gleicher, Mohit Gupta, Yin Li
We present a method for reconstructing 3D shape of arbitrary Lambertian objects based on measurements by miniature, energy-efficient, low-cost single-photon cameras.
no code implementations • ICCV 2023 • Sacha Jungerman, Atul Ingle, Mohit Gupta
Here we present a method capable of estimating extreme scene motion under challenging conditions, such as low light or high dynamic range, from a sequence of high-speed image frames such as those captured by a single-photon camera.
no code implementations • ICCV 2023 • Varun Sundar, Andrei Ardelean, Tristan Swedish, Claudio Bruschini, Edoardo Charbon, Mohit Gupta
As an added benefit, our projections provide camera-dependent compression of photon-cubes, which we demonstrate using an implementation of our projections on a novel compute architecture that is designed for single-photon imaging.
1 code implementation • ICCV 2023 • Matthew Dutson, Yin Li, Mohit Gupta
In this work, we exploit temporal redundancy between subsequent inputs to reduce the cost of Transformers for video processing.
no code implementations • 25 Aug 2023 • Carter Sifferman, Yeping Wang, Mohit Gupta, Michael Gleicher
To validate our methods, we capture 3, 800 measurements of eight planar surfaces from a wide range of viewpoints, and show that our method outperforms the proprietary-distance-estimate baseline by an order of magnitude in most scenarios.
no code implementations • 23 May 2023 • Harman Singh, Poorva Garg, Mohit Gupta, Kevin Shah, Ashish Goswami, Satyam Modi, Arnab Kumar Mondal, Dinesh Khandelwal, Dinesh Garg, Parag Singla
We are interested in image manipulation via natural language text -- a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces.
no code implementations • ICCV 2023 • Jeremy Klotz, Mohit Gupta, Aswin C. Sankaranarayanan
We present a structured light system based on position sensing diodes (PSDs), an unconventional sensing modality that directly measures the centroid of the spatial distribution of incident light, thus enabling high-resolution 3D laser scanning with a minimal amount of sensor data.
no code implementations • ICCV 2023 • Felipe Gutierrez-Barragan, Fangzhou Mu, Andrei Ardelean, Atul Ingle, Claudio Bruschini, Edoardo Charbon, Yin Li, Mohit Gupta, Andreas Velten
Single-photon 3D cameras can record the time-of-arrival of billions of photons per second with picosecond accuracy.
no code implementations • ICCV 2023 • Shantanu Gupta, Mohit Gupta
Previous work has largely focused on solving the image reconstruction problem first and then using off-the-shelf methods for downstream tasks, but the most general solutions that account for motion are costly and not scalable to large data volumes produced by single-photon sensors.
no code implementations • 9 Nov 2022 • Sacha Jungerman, Atul Ingle, Yin Li, Mohit Gupta
Time-resolved image sensors that capture light at pico-to-nanosecond timescales were once limited to niche applications but are now rapidly becoming mainstream in consumer devices.
no code implementations • 24 Jul 2022 • Bhavya Goyal, Jean-François Lalonde, Yin Li, Mohit Gupta
This creates a trade-off between these two kinds of image degradations: motion blur (due to long exposure) vs. noise (due to short exposure), also referred as a dual image corruption pair in this paper.
no code implementations • CVPR 2022 • Varun Sundar, Sizhuo Ma, Aswin C. Sankaranarayanan, Mohit Gupta
We present a novel structured light technique that uses Single Photon Avalanche Diode (SPAD) arrays to enable 3D scanning at high-frame rates and low-light levels.
no code implementations • 6 Apr 2022 • Narayana Darapaneni, Arjun Tanndalam, Mohit Gupta, Neeta Taneja, Prabu Purushothaman, Swati Eswar, Anwesh Reddy Paduri, Thangaselvi Arichandrapandian
India is the second largest producer of fruits and vegetables in the world, and one of the largest consumers of fruits like Banana, Papaya and Mangoes through retail and ecommerce giants like BigBasket, Grofers and Amazon Fresh.
no code implementations • CVPR 2022 • Felipe Gutierrez-Barragan, Atul Ingle, Trevor Seets, Mohit Gupta, Andreas Velten
CSPHs are a per-pixel compressive representation of the high-resolution histogram, that is built on-the-fly, as each photon is detected.
2 code implementations • 2 Dec 2021 • Matthew Dutson, Yin Li, Mohit Gupta
Video data is often repetitive; for example, the contents of adjacent frames are usually strongly correlated.
1 code implementation • ICCV 2021 • Bhavya Goyal, Mohit Gupta
The key idea is that having a spectrum of different brightness levels during training enables effective guidance, and increases robustness to shot noise even in extreme noise cases.
no code implementations • CVPR 2021 • Jongho Lee, Mohit Gupta
For several vision and robotics applications, 3D geometry of man-made environments such as indoor scenes can be represented with a small number of dominant planes.
no code implementations • 19 May 2021 • Vaishali Ingale, Anush Mohan, Divit Adlakha, Krishan Kumar, Mohit Gupta
This paper explores the idea of utilising Long Short-Term Memory neural networks (LSTMNN) for the generation of musical sequences in ABC notation.
no code implementations • CVPR 2021 • Atul Ingle, Trevor Seets, Mauro Buttafava, Shantanu Gupta, Alberto Tosi, Mohit Gupta, Andreas Velten
Digital camera pixels measure image intensities by converting incident light energy into an analog electrical current, and then digitizing it into a fixed-width binary representation.
no code implementations • 12 Mar 2021 • Felipe Gutierrez-Barragan, Huaijin Chen, Mohit Gupta, Andreas Velten, Jinwei Gu
Recently, data-driven methods that jointly denoise and mitigate MPI have become state-of-the-art without using the intermediate transient representation.
2 code implementations • CVPR 2021 • Athena Sayles, Ashish Hooda, Mohit Gupta, Rahul Chatterjee, Earlence Fernandes
By contrast, we contribute a procedure to generate, for the first time, physical adversarial examples that are invisible to human eyes.
no code implementations • 21 Jun 2020 • Sizhuo Ma, Shantanu Gupta, Arin C. Ulku, Claudio Bruschini, Edoardo Charbon, Mohit Gupta
These single-photon cameras (SPCs) are capable of capturing high-speed sequences of binary single-photon images with no read noise.
no code implementations • ICCV 2019 • Anant Gupta, Atul Ingle, Mohit Gupta
Single-photon avalanche diodes (SPADs) are becoming popular in time-of-flight depth-ranging due to their unique ability to capture individual photons with picosecond timing resolution.
no code implementations • 26 Jul 2019 • Sizhuo Ma, Brandon M. Smith, Mohit Gupta
The key enabling result is a per-ray linear equation, called the ray flow equation, that relates 3D scene flow to 4D light field gradients.
no code implementations • CVPR 2019 • Anant Gupta, Atul Ingle, Andreas Velten, Mohit Gupta
Single photon avalanche diodes (SPADs) are starting to play a pivotal role in the development of photon-efficient, long-range LiDAR systems.
no code implementations • CVPR 2019 • Atul Ingle, Andreas Velten, Mohit Gupta
Our key observation is that the precise inter-photon timing measured by a SPAD can be used for estimating scene brightness under ambient lighting conditions, even for very bright scenes.
no code implementations • ECCV 2018 • Mohit Gupta, Nikhil Nakhate
We present a mathematical framework for analysis and design of high performance structured light (SL) coding schemes.
no code implementations • ECCV 2018 • Sizhuo Ma, Brandon M. Smith, Mohit Gupta
The key enabling result is a per-ray linear equation, called the ray flow equation, that relates 3D scene flow to 4D light field gradients.
no code implementations • CVPR 2018 • Brandon M. Smith, Matthew O'Toole, Mohit Gupta
However, when imaging multiple NLOS objects, the speckle components due to different objects are superimposed on the virtual bare sensor image, and cannot be analyzed separately for recovering the motion of individual objects.
no code implementations • CVPR 2018 • Ruilin Xu, Mohit Gupta, Shree K. Nayar
We propose a novel imaging method for near-complete, surround, 3D reconstruction of geometrically complex objects, in a single shot.
no code implementations • ICCV 2015 • Kensei Jo, Mohit Gupta, Shree K. Nayar
We develop a theoretical model for speckle flow (motion of speckle as a function of sensor motion), and show that it is quasi-invariant to surrounding scene's properties.
1 code implementation • 14 Mar 2015 • Jian Wang, Mohit Gupta, Aswin C. Sankaranarayanan
The measurement rate of cameras that take spatially multiplexed measurements by using spatial light modulators (SLM) is often limited by the switching speed of the SLMs.