Towards Multi-View Consistent Style Transfer with One-Step Diffusion via Vision Conditioning

• URL: http://arxiv.org/abs/2411.10130v1
• Date: Fri, 15 Nov 2024 12:02:07 GMT
• Title: Towards Multi-View Consistent Style Transfer with One-Step Diffusion via Vision Conditioning
• Authors: Yushen Zuo, Jun Xiao, Kin-Chung Chan, Rongkang Dong, Cuixin Yang, Zongqi He, Hao Xie, Kin-Man Lam,
• Abstract summary: Stylized images from different viewpoints generated by our method achieve superior visual quality, with better structural integrity and less distortion. Our method effectively preserves the structural information and multi-view consistency in stylized images without any 3D information.
• Score: 12.43848969320173
• License:
• Abstract: The stylization of 3D scenes is an increasingly attractive topic in 3D vision. Although image style transfer has been extensively researched with promising results, directly applying 2D style transfer methods to 3D scenes often fails to preserve the structural and multi-view properties of 3D environments, resulting in unpleasant distortions in images from different viewpoints. To address these issues, we leverage the remarkable generative prior of diffusion-based models and propose a novel style transfer method, OSDiffST, based on a pre-trained one-step diffusion model (i.e., SD-Turbo) for rendering diverse styles in multi-view images of 3D scenes. To efficiently adapt the pre-trained model for multi-view style transfer on small datasets, we introduce a vision condition module to extract style information from the reference style image to serve as conditional input for the diffusion model and employ LoRA in diffusion model for adaptation. Additionally, we consider color distribution alignment and structural similarity between the stylized and content images using two specific loss functions. As a result, our method effectively preserves the structural information and multi-view consistency in stylized images without any 3D information. Experiments show that our method surpasses other promising style transfer methods in synthesizing various styles for multi-view images of 3D scenes. Stylized images from different viewpoints generated by our method achieve superior visual quality, with better structural integrity and less distortion. The source code is available at https://github.com/YushenZuo/OSDiffST.

Related papers

• Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion [63.81544586407943]
  Single-image 3D portrait generation methods typically employ 2D diffusion models to provide multi-view knowledge, which is then distilled into 3D representations. We propose a Hybrid Priors Diffsion model, which explicitly and implicitly incorporates multi-view priors as conditions to enhance the status consistency of the generated multi-view portraits. Experiments demonstrate that our method can produce 3D portraits with accurate geometry and rich details from a single image.
  arXiv  Detail & Related papers  (2024-11-15T17:19:18Z)
• G3DST: Generalizing 3D Style Transfer with Neural Radiance Fields across Scenes and Styles [45.92812062685523]
  Existing methods for 3D style transfer need extensive per-scene optimization for single or multiple styles. In this work, we overcome the limitations of existing methods by rendering stylized novel views from a NeRF without the need for per-scene or per-style optimization. Our findings demonstrate that this approach achieves a good visual quality comparable to that of per-scene methods.
  arXiv  Detail & Related papers  (2024-08-24T08:04:19Z)
• Ada-adapter:Fast Few-shot Style Personlization of Diffusion Model with Pre-trained Image Encoder [57.574544285878794]
  Ada-Adapter is a novel framework for few-shot style personalization of diffusion models. Our method enables efficient zero-shot style transfer utilizing a single reference image. We demonstrate the effectiveness of our approach on various artistic styles, including flat art, 3D rendering, and logo design.
  arXiv  Detail & Related papers  (2024-07-08T02:00:17Z)
• Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images [54.56070204172398]
  We propose a simple yet effective pipeline for stylizing a 3D scene. We perform 3D style transfer by refining the source NeRF model using stylized images generated by a style-aligned image-to-image diffusion model. We demonstrate that our method can transfer diverse artistic styles to real-world 3D scenes with competitive quality.
  arXiv  Detail & Related papers  (2024-06-19T09:36:18Z)
• Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data [80.92268916571712]
  A critical bottleneck is the scarcity of high-quality 3D objects with detailed captions. We propose Bootstrap3D, a novel framework that automatically generates an arbitrary quantity of multi-view images. We have generated 1 million high-quality synthetic multi-view images with dense descriptive captions.
  arXiv  Detail & Related papers  (2024-05-31T17:59:56Z)
• Envision3D: One Image to 3D with Anchor Views Interpolation [18.31796952040799]
  We present Envision3D, a novel method for efficiently generating high-quality 3D content from a single image. It is capable of generating high-quality 3D content in terms of texture and geometry, surpassing previous image-to-3D baseline methods.
  arXiv  Detail & Related papers  (2024-03-13T18:46:33Z)
• Gaussian Splatting in Style [32.41970914897462]
  3D sceneization extends the work of neural style transfer to 3D. A vital challenge in this problem is to maintain the uniformity of the stylized appearance across multiple views. We propose a novel architecture trained on a collection of style images that, at test time, produces real time high-quality stylized novel views.
  arXiv  Detail & Related papers  (2024-03-13T13:06:31Z)
• IT3D: Improved Text-to-3D Generation with Explicit View Synthesis [71.68595192524843]
  This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues. Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images. For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data.
  arXiv  Detail & Related papers  (2023-08-22T14:39:17Z)
• 3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer [66.48720190245616]
  We propose a learning-based approach for style transfer between 3D objects. The proposed method can synthesize new 3D shapes both in the form of point clouds and meshes. We extend our technique to implicitly learn the multimodal style distribution of the chosen domains.
  arXiv  Detail & Related papers  (2020-11-26T16:59:12Z)

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.