DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields

TL;DR

DynaMoN introduces a motion-aware camera localization method that enhances dynamic scene reconstruction with neural radiance fields, achieving faster training and improved accuracy in trajectory estimation and scene quality.

Contribution

The paper presents a novel iterative learning scheme combining semantic segmentation, motion masks, and statics-focused sampling for robust camera pose estimation in dynamic scenes.

Findings

Significantly accelerates training process.

Outperforms state-of-the-art in reconstruction quality.

Improves trajectory accuracy on real-world datasets.

Abstract

The accurate reconstruction of dynamic scenes with neural radiance fields is significantly dependent on the estimation of camera poses. Widely used structure-from-motion pipelines encounter difficulties in accurately tracking the camera trajectory when faced with separate dynamics of the scene content and the camera movement. To address this challenge, we propose Dynamic Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields (DynaMoN). DynaMoN utilizes semantic segmentation and generic motion masks to handle dynamic content for initial camera pose estimation and statics-focused ray sampling for fast and accurate novel-view synthesis. Our novel iterative learning scheme switches between training the NeRF and updating the pose parameters for an improved reconstruction and trajectory estimation quality. The proposed pipeline shows significant acceleration of the training process. We extensively evaluate our approach on two real-world dynamic datasets, the TUM RGB-D dataset and the BONN RGB-D Dynamic dataset. DynaMoN improves over the state-of-the-art both in terms of reconstruction quality and trajectory accuracy. We plan to make our code public to enhance research in this area.