# BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling

## TL;DR

This paper introduces BLiRF, a novel framework that combines classical non-rigid structure-from-motion priors with neural radiance fields by modeling scenes as bandlimited signals, improving dynamic scene modeling from a single camera.

## Contribution

It proposes a new scene representation that factorizes space and time using bandlimited signals, bridging NRSfM and NeRF for better dynamic scene modeling.

## Key findings

- Effective modeling of complex dynamic scenes with lighting and texture changes
- Improved motion localization and scene expressiveness
- Demonstrated results on diverse dynamic scenes

## Abstract

Reasoning the 3D structure of a non-rigid dynamic scene from a single moving camera is an under-constrained problem. Inspired by the remarkable progress of neural radiance fields (NeRFs) in photo-realistic novel view synthesis of static scenes, extensions have been proposed for dynamic settings. These methods heavily rely on neural priors in order to regularize the problem. In this work, we take a step back and reinvestigate how current implementations may entail deleterious effects, including limited expressiveness, entanglement of light and density fields, and sub-optimal motion localization. As a remedy, we advocate for a bridge between classic non-rigid-structure-from-motion (\nrsfm) and NeRF, enabling the well-studied priors of the former to constrain the latter. To this end, we propose a framework that factorizes time and space by formulating a scene as a composition of bandlimited, high-dimensional signals. We demonstrate compelling results across complex dynamic scenes that involve changes in lighting, texture and long-range dynamics.