# Realistic and Controllable 3D Gaussian-Guided Object Editing for Driving Video Generation

## TL;DR

G^2Editor is a novel framework that enables photorealistic, controllable 3D object editing in driving videos, improving pose accuracy and visual fidelity for autonomous driving data augmentation.

## Contribution

The paper introduces G^2Editor, a new method that combines 3D Gaussian representations with hierarchical features for precise, realistic object editing in driving videos.

## Key findings

- Outperforms existing methods in pose control and visual quality.
- Supports object repositioning, insertion, and deletion.
- Enhances downstream autonomous driving tasks.

## Abstract

Corner cases are crucial for training and validating autonomous driving systems, yet collecting them from the real world is often costly and hazardous. Editing objects within captured sensor data offers an effective alternative for generating diverse scenarios, commonly achieved through 3D Gaussian Splatting or image generative models. However, these approaches often suffer from limited visual fidelity or imprecise pose control. To address these issues, we propose G^2Editor, a framework designed for photorealistic and precise object editing in driving videos. Our method leverages a 3D Gaussian representation of the edited object as a dense prior, injected into the denoising process to ensure accurate pose control and spatial consistency. A scene-level 3D bounding box layout is employed to reconstruct occluded areas of non-target objects. Furthermore, to guide the appearance details of the edited object, we incorporate hierarchical fine-grained features as additional conditions during generation. Experiments on the Waymo Open Dataset demonstrate that G^2Editor effectively supports object repositioning, insertion, and deletion within a unified framework, outperforming existing methods in both pose controllability and visual quality, while also benefiting downstream data-driven tasks.