ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2503.00746
31
0

DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting

2 March 2025
Liao Shen
T. Liu
Huiqiang Sun
Jiaqi Li
Z. Cao
Wei Li
Chen Change Loy
    3DGS
ArXivPDFHTML
Abstract

Recent advances in 3D Gaussian Splatting (3D-GS) have shown remarkable success in representing 3D scenes and generating high-quality, novel views in real-time. However, 3D-GS and its variants assume that input images are captured based on pinhole imaging and are fully in focus. This assumption limits their applicability, as real-world images often feature shallow depth-of-field (DoF). In this paper, we introduce DoF-Gaussian, a controllable depth-of-field method for 3D-GS. We develop a lens-based imaging model based on geometric optics principles to control DoF effects. To ensure accurate scene geometry, we incorporate depth priors adjusted per scene, and we apply defocus-to-focus adaptation to minimize the gap in the circle of confusion. We also introduce a synthetic dataset to assess refocusing capabilities and the model's ability to learn precise lens parameters. Our framework is customizable and supports various interactive applications. Extensive experiments confirm the effectiveness of our method. Our project is available atthis https URL.

View on arXiv
@article{shen2025_2503.00746,
  title={ DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting },
  author={ Liao Shen and Tianqi Liu and Huiqiang Sun and Jiaqi Li and Zhiguo Cao and Wei Li and Chen Change Loy },
  journal={arXiv preprint arXiv:2503.00746},
  year={ 2025 }
}
Comments on this paper