VIINTER: View Interpolation with Implicit Neural Representations of Images

TL;DR

VIINTER introduces a novel view interpolation method using implicit neural representations of images, interpolating learned code vectors to achieve viewpoint changes without explicit 3D modeling or pixel correspondence, validated across diverse multi-view scenes.

Contribution

The paper presents a new view interpolation technique leveraging INR code interpolation, eliminating the need for 3D structure, camera pose estimation, or pixel correspondence.

Findings

Effective view interpolation demonstrated on various multi-view scenes.

Significant enhancement in interpolation quality with proposed techniques.

Shows potential of INR for image manipulation tasks beyond fitting and super-resolution.

Abstract

We present VIINTER, a method for view interpolation by interpolating the implicit neural representation (INR) of the captured images. We leverage the learned code vector associated with each image and interpolate between these codes to achieve viewpoint transitions. We propose several techniques that significantly enhance the interpolation quality. VIINTER signifies a new way to achieve view interpolation without constructing 3D structure, estimating camera poses, or computing pixel correspondence. We validate the effectiveness of VIINTER on several multi-view scenes with different types of camera layout and scene composition. As the development of INR of images (as opposed to surface or volume) has centered around tasks like image fitting and super-resolution, with VIINTER, we show its capability for view interpolation and offer a promising outlook on using INR for image manipulation tasks.