# Neural Image Representations for Multi-Image Fusion and Layer Separation

Source: [Neural Image Representations for Multi-Image Fusion and Layer Separation](<https://www.sota2.com/research/paper/68fa6d191e209131cea37bd1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:25:36.384Z

Authors: Seonghyeon Nam, Marcus A. Brubaker, Michael S. Brown

Published: 2021-08-02T22:29:35.000Z

## Abstract

We propose a framework for aligning and fusing multiple images into a single view using neural image representations (NIRs), also known as implicit or coordinate-based neural representations. Our framework targets burst images that exhibit camera ego motion and potential changes in the scene. We describe different strategies for alignment depending on the nature of the scene motion -- namely, perspective planar (i.e., homography), optical flow with minimal scene change, and optical flow with notable occlusion and disocclusion. With the neural image representation, our framework effectively combines multiple inputs into a single canonical view without the need for selecting one of the images as a reference frame. We demonstrate how to use this multi-frame fusion framework for various layer separation tasks. The code and results are available at https://shnnam.github.io/research/nir.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-Image Super-Resolution on SatSynthBurst (test)](<https://www.sota2.com/research/sota/multi-image-super-resolution-on-satsynthburst-test.md>): Multi-image Super-resolution; SatSynthBurst (test); PSNR: 24.99.

- [Multi-Image Super-Resolution on SyntheticBurst (test)](<https://www.sota2.com/research/sota/multi-image-super-resolution-on-syntheticburst-test.md>): Multi-image Super-resolution; SyntheticBurst (test); PSNR: 23.39.

- [Multi-image super-resolution on SatSynthBurst](<https://www.sota2.com/research/sota/multi-image-super-resolution-on-satsynthburst.md>): Multi-image Super-resolution; SatSynthBurst; PSNR: 26.26.

- [Multi-image super-resolution on SyntheticBurst](<https://www.sota2.com/research/sota/multi-image-super-resolution-on-syntheticburst.md>): Multi-image Super-resolution; SyntheticBurst; PSNR: 24.46.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2108.01199>)

[PDF](<https://arxiv.org/pdf/2108.01199.pdf>)