DOF-GS: Adjustable Depth-of-Field 3D Gaussian Splatting for Post-Capture Refocusing, Defocus Rendering and Blur Removal
Yujie Wang, Praneeth Chakravarthula, Baoquan Chen
摘要
Input Images with Defocus Blur Mip-Splatting Ours Ours (DOF Rendering) (a) (b) (c) (d) Novel View Synthesis Aperture Focal Distance Figure 1. Our method enhances 3DGS with a finite-aperture camera model and differentiable depth-of-field (DOF) rendering, enabling post-capture DOF control after training and capturing natural defocus cues from multi-view defocused images. Differentiable DOF rendering also mitigates reconstruction artifacts caused by multi-view inconsistent defocus blur. Insets (a)-(d), with in-focus areas in pink, show images rendered under various settings: (a)-(c) share aperture but differ in focal distance; (d) matches (b)'s focal distance but has a larger aperture.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- Benchmarking PhD-Level Coding in 3D Geometric Computer VisionWenyi Li, Renkai Luo, Yue Yu, Huan-ang Gao 等CVPR 2026 · 被引用 2 次
- Unblur-SLAM: Dense Neural SLAM for Blurry InputsQi Zhang, Denis Rozumny, Francesco Girlanda, Sezer Karaoglu 等CVPR 2026 · 被引用 1 次
它引用的顶会 Paper12
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen 等CVPR 2022 · 被引用 1,237 次
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian SplattingZeyu Yang, Hongye Yang, Zijie Pan, Li ZhangICLR 2024 · 被引用 529 次
- NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw ImagesBen Mildenhall, Peter Hedman, Ricardo Martin-Brualla, Pratul P. Srinivasan 等CVPR 2022 · 被引用 307 次
相关 Paper
- DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian SplattingLiao Shen, Tianqi Liu, Huiqiang Sun, Jiaqi Li 等CVPR 2025
- DC2: Dual-Camera Defocus Control by Learning to RefocusHadi Alzayer, Abdullah Abuolaim, Leung Chun Chan, Yang Yang 等CVPR 2023
- DoF-NeRF: Depth-of-Field Meets Neural Radiance FieldsZijin Wu, Xingyi Li, Juewen Peng, Hao Lu 等ACM MM 2022 · 被引用 34 次
- Mip-Splatting: Alias-Free 3D Gaussian SplattingZehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler 等CVPR 2024 · 被引用 360 次
- Multi-Focus Image Fusion via Explicit Defocus Blur ModellingYuhui Quan, Xi Wan, Zitao Tang, Jinxiu Liang 等AAAI 2025 · 被引用 12 次
