# Neural Video Fields Editing

arXiv: https://arxiv.org/abs/2312.08882 · HTML: https://mlsanity.com/paper/2312.08882/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- First posted on arXiv 12 Dec 2023.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Built on by (most cited first, 6 of 6)

- [Video Editing via Factorized Diffusion Distillation](https://mlsanity.com/paper/2403.09334/) (2024)
- [Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splatting](https://mlsanity.com/paper/2404.01168/) (2024)
- [GenCompositor: Generative Video Compositing with Diffusion Transformer](https://mlsanity.com/paper/2509.02460/) (2025)
- [Evolution of Video Generative Foundations](https://mlsanity.com/paper/2604.06339/) (2026)
- [VIA: Unified Spatiotemporal Video Adaptation Framework for Global and Local Video Editing](https://mlsanity.com/paper/2406.12831/) (2024)
- [Searching Priors Makes Text-to-Video Synthesis Better](https://mlsanity.com/paper/2406.03215/) (2024)

## Abstract (arXiv)

Diffusion models have revolutionized text-driven video editing. However, applying these methods to real-world editing encounters two significant challenges: (1) the rapid increase in GPU memory demand as the number of frames grows, and (2) the inter-frame inconsistency in edited videos. To this end, we propose NVEdit, a novel text-driven video editing framework designed to mitigate memory overhead and improve consistent editing for real-world long videos. Specifically, we construct a neural video field, powered by tri-plane and sparse grid, to enable encoding long videos with hundreds of frames in a memory-efficient manner. Next, we update the video field through off-the-shelf Text-to-Image (T2I) models to impart text-driven editing effects. A progressive optimization strategy is developed to preserve original temporal priors. Importantly, both the neural video field and T2I model are adaptable and replaceable, thus inspiring future research. Experiments demonstrate the ability of our approach to edit hundreds of frames with impressive inter-frame consistency. Our project is available at: https://nvedit.github.io/.