Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer

arXiv Code

Source 4D Rendering
"Sear Steak"

"Change his clothes into a
red shirt"

Source 4D Rendering
"Flame Salmon"

"Make the salmon
glow with a magical blue light"

Source 4D Rendering
"Coffee Martini"

"Change his cap into a
yellow cap"

Source 4D Rendering
"Cut Roasted Beef"

Change the scene into a
charcoal drawing"

Dynamic-eDiTor demonstrates its capability for high-quality 4D scene editing, ensuring both multi-view and temporal consistency.

Overview

Teaser — **Dynamic-eDiTor Overview.** We represent the multi-view video as a unified camera-time grid. Dynamic-eDiTor combines **Spatio-Temporal Sub-Grid Attention (STGA)**, which performs locally coherent cross-view and temporal fusion within each sub-grid, with **Context Token Propagation (CTP)**, which globally propagates the aggregated features across the grid via Full Token Inheritance and Flow-guided Token Replacement for robust spatio-temporal consistency enforcement. Together, these modules enable seamless, globally consistent multi-view video editing without additional training, while directly optimizing the pre-trained 4DGS.

Abstract

Recent progress in 4D representations, such as Dynamic NeRF and 4D Gaussian Splatting (4DGS), has enabled dynamic 4D scene reconstruction. However, text-driven 4D scene editing remains under-explored due to the challenge of ensuring both multi-view and temporal consistency across space and time during editing. Existing studies rely on 2D diffusion models that edit frames independently, often causing motion distortion, geometric drift, and incomplete editing. We introduce Dynamic-eDiTor, a training-free text-driven 4D editing framework leveraging Multimodal Diffusion Transformer (MM-DiT) and 4DGS. This mechanism consists of Spatio-Temporal Sub-Grid Attention (STGA) for locally consistent cross-view and temporal fusion, and Context Token Propagation (CTP) for global propagation via token inheritance and optical-flow-guided token replacement. Together, these components allow Dynamic-eDiTor to perform seamless, globally consistent multi-view video without additional training and directly optimize pre-trained source 4DGS. Extensive experiments on multi-view video dataset DyNeRF demonstrate that our method achieves superior editing fidelity and both multi-view and temporal consistency prior approaches.

4D Rendering Results

on DyNeRF and Hypernerf dataset

Qualitative comparison

Qualitative comparison1. Dynamic-eDiTor enables more robust non-rigid content manipulation and achieves more complete edits of the 4D scene. The top-row displays the original rendered frames, while the following rows show the edited 4DGS renderings produced by each baseline. Our method (bottom-row) outperforms all baselines in both text alignment and overall editing fidelity, while maintaining strong temporal and spatial consistency.

Qualitative comparison2. Dynamic-eDiTor enables more robust non-rigid content manipulation and achieves more complete edits of the 4D scene. The top-row displays the original rendered frames, while the following rows show the edited 4DGS renderings produced by each baseline. Our method (bottom-row) outperforms all baselines in both text alignment and overall editing fidelity, while maintaining strong temporal and spatial consistency.

Citation

If you find this work useful, please cite:

@InProceedings{Lee_2026_CVPR,
    author    = {Lee, Dong In and Doh, Hyungjun and Chi, Seunggeun and Duan, Runlin and Kim, Sangpil and Ramani, Karthik},
    title     = {Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2026},
    pages     = {1187-1197}
}