scispace - formally typeset
Search or ask a question
Author

Mansi Sharma

Bio: Mansi Sharma is an academic researcher from Indian Institute of Technology Madras. The author has contributed to research in topics: Computer science & Rendering (computer graphics). The author has an hindex of 6, co-authored 37 publications receiving 190 citations. Previous affiliations of Mansi Sharma include Indian Institutes of Technology & Indian Institute of Technology Delhi.

Papers published on a yearly basis

Papers
More filters
Proceedings ArticleDOI
15 Dec 2020
TL;DR: Wang et al. as discussed by the authors proposed a novel Bilateral grid based 3D convolutional neural network, dubbed as 3DBG-UNet, that parameterize high dimensional feature space by encoding compact 3D bilateral grids with UNets and infers sharp geometric layout of the scene.
Abstract: The task of predicting smooth and edge-consistent depth maps is notoriously difficult for single image depth estimation. This paper proposes a novel Bilateral Grid based 3D convolutional neural network, dubbed as 3DBG-UNet, that parameterize high dimensional feature space by encoding compact 3D bilateral grids with UNets and infers sharp geometric layout of the scene. Further, an another novel 3DBGES-UNet model is introduced that integrate 3DBG-UNet for inferring an accurate depth map given a single color view. The 3DBGES-UNet concatenate 3DBG-UNet geometry map with the inception network edge accentuation map and a spatial object's boundary map obtained by leveraging semantic segmentation and train the UNet model with ResNet backbone. Both models are designed with a particular attention to explicitly account for edges or minute details. Preserving sharp discontinuities at depth edges is critical for many applications such as realistic integration of virtual objects in AR video or occlusion-aware view synthesis for 3D display applications. The proposed depth prediction network achieves state-of-the-art performance in both qualitative and quantitative evaluations on the challenging NYUv2-Depth data. The code and corresponding pre-trained weights will be made publicly available.

6 citations

Dissertation
01 Jan 2017
TL;DR: For creating a truly immersive experience, it is essential to support advanced functionalities like free-viewpoint viewing of natural video, and multi-media features which increase user interactivity with television content, like editing or mixing of scene components, virtual panning, tilting or zoom-in.
Abstract: The demand for 3D TV systems is going high and technology is rapidly improving. High quality 3D content production is crucial for working on novel ways to show glasses-free 3D. For creating a truly immersive experience, it is essential to support advanced functionalities like free-viewpoint viewing of natural video. Other multi-media features which increase user interactivity with television content, like editing or mixing of scene components, virtual panning, tilting or zoom-in, a video featuring visual 3D effects as frozen movement, etc., must also be realized. It is also desirable for users to enjoy 3D vision with an increased

6 citations

Journal ArticleDOI
04 Jul 2021-Sensors
TL;DR: In this article, the authors proposed a novel flexible scheme for efficient layer-based representation and lossy compression of light fields on layered displays, which learns stacked multiplicative layers optimized using a convolutional neural network.
Abstract: To create a realistic 3D perception on glasses-free displays, it is critical to support continuous motion parallax, greater depths of field, and wider fields of view. A new type of Layered or Tensor light field 3D display has attracted greater attention these days. Using only a few light-attenuating pixelized layers (e.g., LCD panels), it supports many views from different viewing directions that can be displayed simultaneously with a high resolution. This paper presents a novel flexible scheme for efficient layer-based representation and lossy compression of light fields on layered displays. The proposed scheme learns stacked multiplicative layers optimized using a convolutional neural network (CNN). The intrinsic redundancy in light field data is efficiently removed by analyzing the hidden low-rank structure of multiplicative layers on a Krylov subspace. Factorization derived from Block Krylov singular value decomposition (BK-SVD) exploits the spatial correlation in layer patterns for multiplicative layers with varying low ranks. Further, encoding with HEVC eliminates inter-frame and intra-frame redundancies in the low-rank approximated representation of layers and improves the compression efficiency. The scheme is flexible to realize multiple bitrates at the decoder by adjusting the ranks of BK-SVD representation and HEVC quantization. Thus, it would complement the generality and flexibility of a data-driven CNN-based method for coding with multiple bitrates within a single training framework for practical display applications. Extensive experiments demonstrate that the proposed coding scheme achieves substantial bitrate savings compared with pseudo-sequence-based light field compression approaches and state-of-the-art JPEG and HEVC coders.

5 citations

Proceedings ArticleDOI
01 Dec 2019
TL;DR: A novel deep learning based solution to predict robust depth maps of a face, one forward facing and the other backward facing, from a single image from the wild, by training a fully convolutional neural network to learn the dual depth maps.
Abstract: Cheap and fast 3D asset creation to enable AR/VR applications is a fast growing domain. This paper addresses a significant problem of reconstructing complete 3D information of a face in near real-time speed on a mobile phone. We propose a novel deep learning based solution to predict robust depth maps of a face, one forward facing and the other backward facing, from a single image from the wild. A critical contribution is that the proposed network is capable of learning the depths of the occluded part of the face too. This is achieved by training a fully convolutional neural network to learn the dual (forward and backward) depth maps, with a common encoder and two separate decoders. The 300W-LP, a cloud point dataset, is used to compute the required dual depth maps from the training data. The code and results will be made available at project page.

5 citations

Proceedings ArticleDOI
16 Dec 2012
TL;DR: A novel rendering algorithm based on depth image warping to support virtual pan-tilt-zoom (PTZ) functionalities during 3D view generation and a novel selective warping scheme is presented to reduce the computational cost by as much as 40% while maintaining an acceptable quality of rendering results.
Abstract: This paper presents a novel rendering algorithm based on depth image warping to support virtual pan-tilt-zoom (PTZ) functionalities during 3D view generation. A method based on "3D-ness" knob is proposed for automatically specifying the virtual camera positions along a path, to model the PTZ mechanism in projective framework. Two novel quality enhancing techniques based on segmentation cues are proposed to add pan, tilt and zoom capabilities during arbitrary view synthesis. In addition to reduce the computational load that results in providing such functionalities, a novel selective warping scheme is presented to reduce the computational cost by as much as 40% while maintaining an acceptable quality of rendering results. Experiments are performed using standard "Breakdancers" and "Ballet" video sequences to demonstrate the effectiveness of the proposed methods as compared to currently published results.

4 citations


Cited by
More filters
01 Jan 2004
TL;DR: Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance and describes numerous important application areas such as image based rendering and digital libraries.
Abstract: From the Publisher: The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

3,627 citations

Proceedings Article
01 Jan 1999

2,010 citations

Journal ArticleDOI
TL;DR: In this article, the structural basis of potential inhibitors targeting SARS-CoV-2 Mpro, identifies gaps, and provides future directions, highlighting compounds with potential Mpro based antiviral activity.
Abstract: The Coronavirus disease-19 (COVID-19) pandemic is still devastating the world causing significant social, economic, and political chaos. Corresponding to the absence of globally approved antiviral drugs for treatment and vaccines for controlling the pandemic, the number of cases and/or mortalities are still rising. Current patient management relies on supportive treatment and the use of repurposed drugs as an indispensable option. Of a crucial role in the viral life cycle, ongoing studies are looking for potential inhibitors to the main protease (Mpro) of severe acute respiratory syndrome Coronavirus -2 (SARS-CoV-2) to tackle the pandemic. Although promising results have been achieved in searching for drugs inhibiting the Mpro, work remains to be done on designing structure-based improved drugs. This review discusses the structural basis of potential inhibitors targeting SARS-CoV-2 Mpro, identifies gaps, and provides future directions. Further, compounds with potential Mpro based antiviral activity are highlighted.

165 citations

Journal ArticleDOI
TL;DR: Novel natural metabolites namely, ursolic acid, carvacrol and oleanolic acid are reported as the potential inhibitors against main protease (Mpro) of COVID-19 by using integrated molecular modeling approaches.
Abstract: Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) is a novel corona virus that causes corona virus disease 2019 (COVID-19). The COVID-19 rapidly spread across the nations with high mortality rate even as very little is known to contain the virus at present. In the current study, we report novel natural metabolites namely, ursolic acid, carvacrol and oleanolic acid as the potential inhibitors against main protease (Mpro) of COVID-19 by using integrated molecular modeling approaches. From a combination of molecular docking and molecular dynamic (MD) simulations, we found three ligands bound to protease during 50 ns of MD simulations. Furthermore, the molecular mechanic/generalized/Born/Poisson-Boltzmann surface area (MM/G/P/BSA) free energy calculations showed that these chemical molecules have stable and favourable energies causing strong binding with binding site of Mpro protein. All these three molecules, namely, ursolic acid, carvacrol and oleanolic acid, have passed the ADME (Absorption, Distribution, Metabolism, and Excretion) property as well as Lipinski's rule of five. The study provides a basic foundation and suggests that the three phytochemicals, viz. ursolic acid, carvacrol and oleanolic acid could serve as potential inhibitors in regulating the Mpro protein's function and controlling viral replication. Communicated by Ramaswamy H. Sarma.

134 citations

Journal ArticleDOI
TL;DR: Role of EOs in the prevention and treatment of COVID-19 is discussed, and a chemo-herbal (EOs) combination of the drugs could be a more feasible and effective approach to combat this viral pandemic.
Abstract: Coronavirus disease of 2019 (COVID-19) has emerged as a global health threat. Unfortunately, there are very limited approved drugs available with established efficacy against the SARs-CoV-2 virus and its inflammatory complications. Vaccine development is actively being researched, but it may take over a year to become available to general public. Certain medications, for example, dexamethasone, antimalarials (chloroquine/hydroxychloroquine), antiviral (remdesivir), and IL-6 receptor blocking monoclonal antibodies (tocilizumab), are used in various combinations as off-label medications to treat COVID-19. Essential oils (EOs) have long been known to have anti-inflammatory, immunomodulatory, bronchodilatory, and antiviral properties and are being proposed to have activity against SARC-CoV-2 virus. Owing to their lipophilic nature, EOs are advocated to penetrate viral membranes easily leading to membrane disruption. Moreover, EOs contain multiple active phytochemicals that can act synergistically on multiple stages of viral replication and also induce positive effects on host respiratory system including bronchodilation and mucus lysis. At present, only computer-aided docking and few in vitro studies are available which show anti-SARC-CoV-2 activities of EOs. In this review, role of EOs in the prevention and treatment of COVID-19 is discussed. A discussion on possible side effects associated with EOs as well as anti-corona virus claims made by EOs manufacturers are also highlighted. Based on the current knowledge a chemo-herbal (EOs) combination of the drugs could be a more feasible and effective approach to combat this viral pandemic.

132 citations