no code implementations • 31 May 2024 • Xiao Zhang, William Gao, Seemandhar Jain, Michael Maire, David. A. Forsyth, Anand Bhattad
Image relighting is the task of showing what a scene from a source image would look like if illuminated differently.
no code implementations • 29 May 2024 • Vaibhav Vavilala, Florian Kluger, Seemandhar Jain, Bodo Rosenhahn, David Forsyth
Describing a scene in terms of primitives -- geometrically simple shapes that offer a parsimonious but accurate abstraction of structure -- is an established vision problem.
no code implementations • 7 Jul 2023 • Vaibhav Vavilala, Seemandhar Jain, Rahul Vasanth, Anand Bhattad, David Forsyth
We present Blocks2World, a novel method for 3D scene rendering and editing that leverages a two-step process: convex decomposition of images and conditioned synthesis.
no code implementations • 5 Oct 2021 • Seemandhar Jain, Prarthi Jain, Abhishek Srivastava
In this work, we extend our previous work by proposed an efficient iForest based approach for anomaly detection using cube sampling that is effective on streaming data.
no code implementations • 27 Sep 2021 • Seemandhar Jain, Prarthi Jain, Prabhat K. Upadhyay, Jules M. Moualeu, Abhishek Srivastava
In addition to being able to handle streaming data, the model works within the resource-constrained environments of an LPU and eliminates the need of transmitting the data to a back-end cloud, ensuring further energy savings.
no code implementations • 23 Aug 2021 • Seemandhar Jain, Aditya A. Shastri, Kapil Ahuja, Yann Busnel, Navneet Pratap Singh
Due to the large sizes of data, clustering algorithm often take too much time.