AGAshutosh Gupta

Ashutosh Gupta

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ashutosh Gupta has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • DeepMURE: Deep Self-Supervised Despeckling via Monte Carlo Multiplicative Unbiased Risk Estimation

    by Ashutosh Gupta, Chandra Sekhar Seelamantula, Thierry Blu, Tanish Yelgoe, Nitant Dube, Shanmuganathan Raman

  • C-LiSA: A Hierarchical Hybrid Transformer Model Using Orthogonal Cross Attention for Satellite Image Cloud Segmentation

    by Subhajit Paul, Ashutosh Gupta, S. Manthira Moorthi, Debajyoti Dhar

    Clouds in optical satellite images are a major concern since their presence hinders the ability to carry out accurate analysis as well as processing. Therefore, deriving accurate pixel-wise cloud masks is a key task in optical remote sensing. Several traditional as well as deep-learning algorithms have emerged to address this problem. However, the task of deriving accurate cloud masks from a variety of satellite images remains elusive due to the presence of confusing spectral signatures and changes in the properties of imaging sensors. In this article, we introduce a deep-learning model based on a hybrid transformer architecture for effective cloud mask generation named C-LiSA - cloud segmentation via the Lipschitz stable attention network. We propose two key attention mechanisms - dual orthogonal self-attention (DOSA) for handling confusing spectral signatures, and the hierarchical cross-channel attention (HC2A) model for effectively highlighting cloud-specific features during the cloud segmentation process. To validate the effectiveness of these mechanisms, we carry out theoretical and empirical Lipschitz stability analysis. We design the whole setup under an adversarial setting in the presence of Lovász-Softmax loss. We demonstrate both qualitative and quantitative outcomes for multiple satellite image datasets including Landsat-8, Sentinel-2, and Cartosat-2S. Our comparative study shows that the proposed model performs better compared to other state-of-the-art methods while providing better generalization across different datasets. We also showcase ablation studies to endorse our choices corresponding to different architectural elements and objective functions.


  • DEM Generation From Mono-Multispectral Images via Uncalibrated Epipolar Rectification and 3D Registration

    by Ashutosh Gupta, Hemant K. Lalwani, Subhajit Paul, Debajyoti Dhar

    Generation of Digital Elevation Models (DEM) typically requires fine image matching between set of images acquired with a wide-baseline and appropriate B/H ratio. Wide baseline stereo imaging is an expensive process since it requires two or more acquisitions at the cost of nominal mono-imaging operations. Due to the wide-baseline, angular separation in views is required, which results in increased occlusion problems leading to holes in the generated DEM. Multiview images taken with wide baselines also have lower overlap area compared to images taken from narrow-baseline systems. Moreover, while making orthorectified maps, large tilts need to be corrected using processing techniques to obtain a top-down view. To alleviate these issues, we propose a novel DEM generation pipeline that utilizes the narrow-baseline information between bands of a single multispectral image. Our method can generate sub-pixel accurate disparity maps while tackling spectral information change. Final DEM is generated from the disparity by using reference Ground Control Points (GCPs) and an iterative control point registration procedure. We demonstrate the effectiveness of our DEM generation pipeline on Resourcesat-2 LISS- IV multispectral image with a BIH ratio as low as 0.018. Our results show that sub pixel disparity of the order of 1/50th of a pixel can be computed. A visual and quantitative comparison of the generated DEM with the wide-baseline DEM from Cartosat-l shows that the elevation information is estimated with good overall agreement even for a hilly region. Our technique makes it possible to extract elevation information from mono-multispectral images with unusually low B/H ratios, potentially enabling the generation of DEMs from multispectral images that would not normall be considered viable for this purpose.

  • Open Access

    A distribution-independent risk estimator for image denoising

    by Babu Kishore Subramanian, Ashutosh Gupta, Chandra Sekhar Seelamantula

    We address the problem of image denoising for an additive white noise model without placing any restrictions on the statistical distribution of noise. We assume knowledge of only the first-and second-order noise statistics. In the recent mean-square error (MSE) minimization approaches for image denoising, one considers a particular noise distribution and derives an expression for the unbiased risk estimate of the MSE. For additive white Gaussian noise, an unbiased estimate of the MSE is Stein's unbiased risk estimate (SURE), which relies on Stein's lemma. We derive an unbiased risk estimate without using Stein's lemma or its counterparts for additive white noise model irrespective of the noise distribution. We refer to the MSE estimate as the generic risk estimate (GenRE). We demonstrate the effectiveness of GenRE using shrinkage in the undecimated Haar wavelet transform domain as the denoising function. The estimated peak-signal-to-noise-ratio (PSNR) using GenRE is typically within 1% of the PSNR obtained when optimizing with the oracle MSE. The performance of the proposed method is on par with SURE for Gaussian noise distribution, and better than SURE-based methods for other noise distributions such as uniform and Laplacian distribution in terms of both PSNR and structural similarity (SSIM)