Zobrazeno 1 - 10
of 306
pro vyhledávání: '"Patil, Akshay"'
We present a volume rendering-based neural surface reconstruction method that takes as few as three disparate RGB images as input. Our key idea is to regularize the reconstruction, which is severely ill-posed and leaving significant gaps between the
Externí odkaz:
http://arxiv.org/abs/2306.04699
The dominant majority of 3D models that appear in gaming, VR/AR, and those we use to train geometric deep learning algorithms are incomplete, since they are modeled as surface meshes and missing their interior structures. We present a learning framew
Externí odkaz:
http://arxiv.org/abs/2304.06342
Autor:
Patil, Akshay Gadi, Patil, Supriya Gadi, Li, Manyi, Fisher, Matthew, Savva, Manolis, Zhang, Hao
This report surveys advances in deep learning-based modeling techniques that address four different 3D indoor scene analysis tasks, as well as synthesis of 3D indoor scenes. We describe different kinds of representations for indoor scenes, various in
Externí odkaz:
http://arxiv.org/abs/2304.03188
We introduce the first active learning (AL) model for high-accuracy instance segmentation of moveable parts from RGB images of real indoor scenes. Specifically, our goal is to obtain fully validated segmentation results by humans while minimizing man
Externí odkaz:
http://arxiv.org/abs/2303.11530
Autor:
Singler, Marius, Patil, Akshay, Ney, Linda, Lorenz, Andreas, Tepner, Sebastian, Clement, Florian
Publikováno v:
In Energy and AI September 2024 17
Autor:
Nille, Omkar S., Patil, Akshay S., Vibhute, Anuja A., Shendage, Shital S., Tiwari, Arpita P., Anbhule, Prashant V., Sohn, Daewon, Gore, Anil H., Kolekar, Govind B.
Publikováno v:
In International Journal of Biological Macromolecules February 2024 257 Part 1
Autor:
Kolekar, Akanksha G., Nille, Omkar S., Koparde, Sneha V., Patil, Akshay S., Waghmare, Ravindra D., Sohn, Daewon, Anbhule, Prashant V., Kolekar, Govind B., Gokavi, Gavisiddappa S., More, Vishalkumar R.
Publikováno v:
In Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 5 January 2024 304
We present a deep neural network to predict structural similarity between 2D layouts by leveraging Graph Matching Networks (GMN). Our network, coined LayoutGMN, learns the layout metric via neural graph matching, using an attention-based GMN designed
Externí odkaz:
http://arxiv.org/abs/2012.06547
We introduce a differential visual similarity metric to train deep neural networks for 3D reconstruction, aimed at improving reconstruction quality. The metric compares two 3D shapes by measuring distances between multi-view images differentiably ren
Externí odkaz:
http://arxiv.org/abs/1911.09204
Autor:
K, Naveenkumar, Ravindra, Patil Akshay, B, Archana, Kannan, Neppoliyan, G, Pavithran, Sinha, Arup
Publikováno v:
In Journal of Molecular Structure 15 December 2023 1294 Part 1