MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration

• URL: http://arxiv.org/abs/2408.10605v4
• Date: Thu, 10 Oct 2024 03:02:10 GMT
• Title: MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration
• Authors: Yanbo Ding, Shaobin Zhuang, Kunchang Li, Zhengrong Yue, Yu Qiao, Yali Wang,
• Abstract summary: We introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries. By mimicking the collaboration of human professionals, this multi-modal agent pipeline facilitates the effective and automatic creation of images with 3D-controllable objects. We construct a new benchmark of T2I-3DisBench (3D image scene), which describes diverse 3D image scenes with 50 detailed prompts.
• Score: 29.657854912416038
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries. Specifically, our MUSES addresses this challenging task by developing a progressive workflow with three key components, including (1) Layout Manager for 2D-to-3D layout lifting, (2) Model Engineer for 3D object acquisition and calibration, (3) Image Artist for 3D-to-2D image rendering. By mimicking the collaboration of human professionals, this multi-modal agent pipeline facilitates the effective and automatic creation of images with 3D-controllable objects, through an explainable integration of top-down planning and bottom-up generation. Additionally, we find that existing benchmarks lack detailed descriptions of complex 3D spatial relationships of multiple objects. To fill this gap, we further construct a new benchmark of T2I-3DisBench (3D image scene), which describes diverse 3D image scenes with 50 detailed prompts. Extensive experiments show the state-of-the-art performance of MUSES on both T2I-CompBench and T2I-3DisBench, outperforming recent strong competitors such as DALL-E 3 and Stable Diffusion 3. These results demonstrate a significant step of MUSES forward in bridging natural language, 2D image generation, and 3D world. Our codes are available at the following link: https://github.com/DINGYANB/MUSES.

Related papers

• Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation [2.3213238782019316]
  GIMDiffusion is a novel Text-to-3D model that utilizes geometry images to efficiently represent 3D shapes using 2D images. We exploit the rich 2D priors of existing Text-to-Image models such as Stable Diffusion. In short, GIMDiffusion enables the generation of 3D assets at speeds comparable to current Text-to-Image models.
  arXiv  Detail & Related papers  (2024-09-05T17:21:54Z)
• IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation [96.32684334038278]
  In this paper, we explore the design space of text-to-3D models. We significantly improve multi-view generation by considering video instead of image generators. Our new method, IM-3D, reduces the number of evaluations of the 2D generator network 10-100x.
  arXiv  Detail & Related papers  (2024-02-13T18:59:51Z)
• IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts [90.49024750432139]
  We present IPDreamer, a novel method that captures intricate appearance features from complex $textbfI$mage $textbfP$rompts and aligns the synthesized 3D object with these extracted features. Our experiments demonstrate that IPDreamer consistently generates high-quality 3D objects that align with both the textual and complex image prompts.
  arXiv  Detail & Related papers  (2023-10-09T03:11:08Z)
• Guide3D: Create 3D Avatars from Text and Image Guidance [55.71306021041785]
  Guide3D is a text-and-image-guided generative model for 3D avatar generation based on diffusion models. Our framework produces topologically and structurally correct geometry and high-resolution textures.
  arXiv  Detail & Related papers  (2023-08-18T17:55:47Z)
• 3D-Aware Multi-Class Image-to-Image Translation with NeRFs [82.27932197385748]
  We investigate 3D-aware GANs for 3D consistent multi-class image-to-image (3D-aware I2I) translation. We decouple this learning process into a multi-class 3D-aware GAN step and a 3D-aware I2I translation step. In extensive experiments on two datasets, we successfully perform 3D-aware I2I translation with multi-view consistency.
  arXiv  Detail & Related papers  (2023-03-27T08:54:51Z)
• CC3D: Layout-Conditioned Generation of Compositional 3D Scenes [49.281006972028194]
  We introduce CC3D, a conditional generative model that synthesizes complex 3D scenes conditioned on 2D semantic scene layouts. Our evaluations on synthetic 3D-FRONT and real-world KITTI-360 datasets demonstrate that our model generates scenes of improved visual and geometric quality.
  arXiv  Detail & Related papers  (2023-03-21T17:59:02Z)
• XDGAN: Multi-Modal 3D Shape Generation in 2D Space [60.46777591995821]
  We propose a novel method to convert 3D shapes into compact 1-channel geometry images and leverage StyleGAN3 and image-to-image translation networks to generate 3D objects in 2D space. The generated geometry images are quick to convert to 3D meshes, enabling real-time 3D object synthesis, visualization and interactive editing. We show both quantitatively and qualitatively that our method is highly effective at various tasks such as 3D shape generation, single view reconstruction and shape manipulation, while being significantly faster and more flexible compared to recent 3D generative models.
  arXiv  Detail & Related papers  (2022-10-06T15:54:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.