Search Results for author: Nima Khademi Kalantari

Found 12 papers, 6 papers with code

ReShader: View-Dependent Highlights for Single Image View-Synthesis

no code implementations19 Sep 2023 Avinash Paliwal, Brandon Nguyen, Andrii Tsarov, Nima Khademi Kalantari

To address this major problem, we make a key observation that the process of synthesizing novel views requires changing the shading of the pixels based on the novel camera, and moving them to appropriate locations.

Image Inpainting Novel View Synthesis

PhotoMat: A Material Generator Learned from Single Flash Photos

no code implementations20 May 2023 Xilong Zhou, Miloš Hašan, Valentin Deschaintre, Paul Guerrero, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Nima Khademi Kalantari

Instead, we train a generator for a neural material representation that is rendered with a learned relighting module to create arbitrarily lit RGB images; these are compared against real photos using a discriminator.

Frame Interpolation for Dynamic Scenes with Implicit Flow Encoding

1 code implementation27 Sep 2022 Pedro Figueirêdo, Avinash Paliwal, Nima Khademi Kalantari

To do this, we propose to encode the bidirectional flows into a coordinate-based network, powered by a hypernetwork, to obtain a continuous representation of the flow across time.

Video Frame Interpolation

Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask

1 code implementation4 Mar 2021 Avinash Paliwal, Libing Zeng, Nima Khademi Kalantari

We propose to do this by first explicitly aligning the neighboring frames to the current frame using a convolutional neural network (CNN).

Denoising Optical Flow Estimation +1

Deep Slow Motion Video Reconstruction with Hybrid Imaging System

1 code implementation27 Feb 2020 Avinash Paliwal, Nima Khademi Kalantari

In this paper, we address this problem using two video streams as input; an auxiliary video with high frame rate and low spatial resolution, providing temporal information, in addition to the standard main video with low frame rate and high spatial resolution.

Optical Flow Estimation valid +3

Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines

1 code implementation2 May 2019 Ben Mildenhall, Pratul P. Srinivasan, Rodrigo Ortiz-Cayon, Nima Khademi Kalantari, Ravi Ramamoorthi, Ren Ng, Abhishek Kar

We present a practical and robust deep learning solution for capturing and rendering novel views of complex real world scenes for virtual exploration.

Novel View Synthesis

Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition

no code implementations30 Jul 2018 Sai Bi, Nima Khademi Kalantari, Ravi Ramamoorthi

Experimental results show that our approach produces better results than the state-of-the-art DL and non-DL methods on various synthetic and real datasets both visually and numerically.

Intrinsic Image Decomposition Test

Light Field Video Capture Using a Learning-Based Hybrid Imaging System

1 code implementation8 May 2017 Ting-Chun Wang, Jun-Yan Zhu, Nima Khademi Kalantari, Alexei A. Efros, Ravi Ramamoorthi

Given a 3 fps light field sequence and a standard 30 fps 2D video, our system can then generate a full light field video at 30 fps.

Learning-Based View Synthesis for Light Field Cameras

no code implementations9 Sep 2016 Nima Khademi Kalantari, Ting-Chun Wang, Ravi Ramamoorthi

Specifically, we propose a novel learning-based approach to synthesize new views from a sparse set of input views.

Cannot find the paper you are looking for? You can Submit a new open access paper.