X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation

TL;DR

X-Dreamer introduces a novel method that bridges the domain gap between 2D and 3D generation, improving the quality and accuracy of text-to-3D content by incorporating camera guidance and attention-mask alignment.

Contribution

The paper proposes two innovative components, CG-LoRA and AMA loss, to enhance 3D content creation by effectively aligning 2D diffusion models with 3D representations.

Findings

Outperforms existing text-to-3D methods in quality and accuracy.

Effectively incorporates camera information into diffusion models.

Focuses on foreground object detail and alignment.

Abstract

In recent times, automatic text-to-3D content creation has made significant progress, driven by the development of pretrained 2D diffusion models. Existing text-to-3D methods typically optimize the 3D representation to ensure that the rendered image aligns well with the given text, as evaluated by the pretrained 2D diffusion model. Nevertheless, a substantial domain gap exists between 2D images and 3D assets, primarily attributed to variations in camera-related attributes and the exclusive presence of foreground objects. Consequently, employing 2D diffusion models directly for optimizing 3D representations may lead to suboptimal outcomes. To address this issue, we present X-Dreamer, a novel approach for high-quality text-to-3D content creation that effectively bridges the gap between text-to-2D and text-to-3D synthesis. The key components of X-Dreamer are two innovative designs: Camera-Guided Low-Rank Adaptation (CG-LoRA) and Attention-Mask Alignment (AMA) Loss. CG-LoRA dynamically incorporates camera information into the pretrained diffusion models by employing camera-dependent generation for trainable parameters. This integration enhances the alignment between the generated 3D assets and the camera's perspective. AMA loss guides the attention map of the pretrained diffusion model using the binary mask of the 3D object, prioritizing the creation of the foreground object. This module ensures that the model focuses on generating accurate and detailed foreground objects. Extensive evaluations demonstrate the effectiveness of our proposed method compared to existing text-to-3D approaches. Our project webpage: https://xmu-xiaoma666.github.io/Projects/X-Dreamer/ .