CVFeb 21, 2024

SealD-NeRF: Interactive Pixel-Level Editing for Dynamic Scenes by Neural Radiance Fields

arXiv:2402.13510v16 citationsh-index: 40Proceedings of the 21st Conference on Robots and Vision
Originality Incremental advance
AI Analysis

This work addresses the need for flexible editing in implicit 3D models for tasks like scene post-processing and 3D content creation, but it is incremental as it extends prior methods to dynamic settings.

The paper tackles the problem of enabling pixel-level editing in dynamic scenes using Neural Radiance Fields (NeRF), which is limited in existing methods, and introduces SealD-NeRF to allow consistent edits across sequences by mapping actions to timeframes and using a teacher-student approach.

The widespread adoption of implicit neural representations, especially Neural Radiance Fields (NeRF), highlights a growing need for editing capabilities in implicit 3D models, essential for tasks like scene post-processing and 3D content creation. Despite previous efforts in NeRF editing, challenges remain due to limitations in editing flexibility and quality. The key issue is developing a neural representation that supports local edits for real-time updates. Current NeRF editing methods, offering pixel-level adjustments or detailed geometry and color modifications, are mostly limited to static scenes. This paper introduces SealD-NeRF, an extension of Seal-3D for pixel-level editing in dynamic settings, specifically targeting the D-NeRF network. It allows for consistent edits across sequences by mapping editing actions to a specific timeframe, freezing the deformation network responsible for dynamic scene representation, and using a teacher-student approach to integrate changes.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes