Research map / 3D vision / NeRF and radiance fields
MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects
Juewen Peng, Jianming Zhang, Xianrui Luo, Hao Lu, Ke Xian, Zhiguo Cao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase MPI planes from 8 to 32 (ablation) | MPIB · Synthesized bokeh (varying disparity) | LPIPS: 0.090 -> 0.019 | Improved |
| increase MPI planes from 16 to 32 (ablation) | MPIB · Synthesized bokeh (varying disparity) | LPIPS: 0.044 -> 0.019 | Improved |
| increase MPI planes from 32 to 64 (ablation) | MPIB · Synthesized bokeh (varying disparity) | LPIPS: 0.019 -> 0.018 | No clear effect |
| add weight normalization (ablation) | MPIB · Synthesized bokeh (constant disparity) | PSNR: 36.2 -> 36.7 | Improved |
| add weight normalization (ablation) | MPIB · Synthesized bokeh (varying disparity) | PSNR: 36.2 -> 36.8 | Improved |
| swap LaMa for EC inpainting (ablation) | MPIB · Synthesized bokeh (varying disparity) | LPIPS: 0.019 -> 0.019 | No clear effect |
| swap LaMa for MADF inpainting (ablation) | MPIB · Synthesized bokeh (varying disparity) | LPIPS: 0.019 -> 0.020 | No clear effect |
| use 3 inpainted background images instead of 1 (ablation) | MPIB · Synthesized bokeh (constant disparity) | PSNR: 36.7 -> 39.3 | Improved |
| use 3 inpainted background images instead of 1 (ablation) | MPIB · Synthesized bokeh (varying disparity) | LPIPS: 0.019 -> 0.017 | Improved |
| use MPIB instead of Scatter | MPIB · Synthesized bokeh (constant disparity) | PSNR: 33.9 -> 36.7 | Improved |
| use MPIB instead of Scatter in user study | MPIB · User study (refocus on foreground) | preference: 89.4% | Improved |
| use MPIB instead of SteReFo in user study | MPIB · User study (refocus on foreground) | preference: 72.7% | Improved |
Closest papers by meaning
- Dr. Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering (CVPR 2024 · similarity 0.90)
- Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model (ICLR 2026 · similarity 0.88)
- BokehCrafter: Taming Video Diffusion Models for Controllable Bokeh Rendering (AAAI 2026 · similarity 0.88)
- BokehMe++: Harmonious Fusion of Classical and Neural Rendering for Versatile Bokeh Creation (TPAMI 2024 · similarity 0.88)
- Stereo Vision Conversion from Planar Videos Based on Temporal Multiplane Images (AAAI 2024 · similarity 0.84)
- AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
