no code implementations • 20 Sep 2023 • David Li, Brandon Y. Feng, Amitabh Varshney
Furthermore, we use saliency-based importance sampling which enables our light field networks to distribute their capacity, particularly limited at lower LODs, towards representing the details viewers are most likely to focus on.
no code implementations • 1 Nov 2022 • Brandon Yushan Feng, Susmija Jabbireddy, Amitabh Varshney
We present VIINTER, a method for view interpolation by interpolating the implicit neural representation (INR) of the captured images.
no code implementations • 13 Aug 2022 • David Li, Amitabh Varshney
Our progressive multi-scale light field network addresses aliasing by encoding smaller anti-aliased representations at its lower levels of detail.
no code implementations • 12 Aug 2022 • Brandon Yushan Feng, yinda zhang, Danhang Tang, Ruofei Du, Amitabh Varshney
We introduce a new implicit shape representation called Primary Ray-based Implicit Function (PRIF).
no code implementations • 17 Feb 2022 • David Li, yinda zhang, Christian Häne, Danhang Tang, Amitabh Varshney, Ruofei Du
Immersive maps such as Google Street View and Bing Streetside provide true-to-life views with a massive collection of panoramas.
no code implementations • 17 Sep 2021 • Tahseen Rabbani, Brandon Feng, Marco Bornstein, Kyle Rui Sang, Yifan Yang, Arjun Rajkumar, Amitabh Varshney, Furong Huang
Federated learning (FL) is a popular paradigm for private and collaborative model training on the edge.
no code implementations • ICCV 2021 • Brandon Yushan Feng, Amitabh Varshney
We present a novel neural representation for light field content that enables compact storage and easy local reconstruction with high fidelity.