ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing

TL;DR

ConsistDreamer introduces a 3D-aware diffusion framework that ensures high-fidelity, consistent scene editing by augmenting 2D diffusion models with 3D context and enforcing 3D consistency during training.

Contribution

It presents a novel method to incorporate 3D awareness into 2D diffusion models, enabling high-quality, instruction-guided scene editing with 3D consistency.

Findings

Achieves state-of-the-art performance in scene editing.

Effectively handles complex large-scale indoor scenes.

Successfully edits intricate patterns like plaid/checkered textures.

Abstract

This paper proposes ConsistDreamer - a novel framework that lifts 2D diffusion models with 3D awareness and 3D consistency, thus enabling high-fidelity instruction-guided scene editing. To overcome the fundamental limitation of missing 3D consistency in 2D diffusion models, our key insight is to introduce three synergetic strategies that augment the input of the 2D diffusion model to become 3D-aware and to explicitly enforce 3D consistency during the training process. Specifically, we design surrounding views as context-rich input for the 2D diffusion model, and generate 3D-consistent, structured noise instead of image-independent noise. Moreover, we introduce self-supervised consistency-enforcing training within the per-scene editing procedure. Extensive evaluation shows that our ConsistDreamer achieves state-of-the-art performance for instruction-guided scene editing across various scenes and editing instructions, particularly in complicated large-scale indoor scenes from ScanNet++, with significantly improved sharpness and fine-grained textures. Notably, ConsistDreamer stands as the first work capable of successfully editing complex (e.g., plaid/checkered) patterns. Our project page is at immortalco.github.io/ConsistDreamer.