DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video

TL;DR

DyBluRF introduces a novel method for synthesizing sharp, high-quality views from monocular videos with motion blur by modeling camera and scene dynamics, outperforming existing techniques.

Contribution

The paper presents DyBluRF, a dynamic neural radiance field approach that handles motion blur by capturing camera and scene trajectories and ensuring temporal coherence.

Findings

Outperforms existing methods in generating sharp views from blurred inputs

Maintains spatial-temporal consistency across scenes

Demonstrates effectiveness on a new diverse dataset

Abstract

Recent advancements in dynamic neural radiance field methods have yielded remarkable outcomes. However, these approaches rely on the assumption of sharp input images. When faced with motion blur, existing dynamic NeRF methods often struggle to generate high-quality novel views. In this paper, we propose DyBluRF, a dynamic radiance field approach that synthesizes sharp novel views from a monocular video affected by motion blur. To account for motion blur in input images, we simultaneously capture the camera trajectory and object Discrete Cosine Transform (DCT) trajectories within the scene. Additionally, we employ a global cross-time rendering approach to ensure consistent temporal coherence across the entire scene. We curate a dataset comprising diverse dynamic scenes that are specifically tailored for our task. Experimental results on our dataset demonstrate that our method outperforms existing approaches in generating sharp novel views from motion-blurred inputs while maintaining spatial-temporal consistency of the scene.