Research map / 3D vision / NeRF and radiance fields
Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures
Tim Seizinger, Florin-Alexandru Vasluianu, Marcos V. Conde, Zongwei Wu, Radu Timofte
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 |
|---|---|---|---|
| add spatial Manhattan decay mask to attention (ablation) | Bokehlicious attention · RealBokeh (all f-stops) | PSNR: 31.271 -> 32.708 | Improved |
| use per-head decay mask scales instead of one shared mask (ablation) | Bokehlicious attention · RealBokeh (all f-stops) | PSNR: 32.708 -> 33.224 | Improved |
| make decay masks aperture-aware (f-aware) (ablation) | Bokehlicious attention · RealBokeh (all f-stops) | PSNR: 33.224 -> 33.300 | Improved |
| make decay masks aperture-aware (f-aware), f/2.8 (ablation) | Bokehlicious attention · RealBokeh (f/2.8) | PSNR: 30.665 -> 31.101 | Improved |
| use AAA instead of Swin attention (ablation) | Bokehlicious · RealBokeh (all f-stops) | PSNR: 32.242 -> 33.300 | Improved |
| use AAA instead of NAT attention (ablation) | Bokehlicious · RealBokeh (all f-stops) | PSNR: 32.940 -> 33.300 | Improved |
| scale model from M to L | Bokehlicious · RealBokeh-bin | PSNR: 30.358 -> 31.250 | Improved |
| Bokehlicious-M vs best prior (DMSHN) | Bokehlicious-M · RealBokeh-bin | PSNR: 29.311 -> 30.358 | Improved |
| Bokehlicious-M vs BoMe with aperture control | Bokehlicious-M · RealBokeh (all f-stops) | PSNR: 29.125 -> 33.300 | Improved |
| Bokehlicious-M vs BoMe | Bokehlicious-M · EBB400 | PSNR: 23.85 -> 24.47 | Improved |
| Bokehlicious-M vs AMPN | Bokehlicious-M · EBB! Val294 | LPIPS: 0.1718 -> 0.1638 | Improved |
| train Bokehlicious-L on RealDefocus for deblurring vs DRBNet | Bokehlicious-L · RealDOF (zero-shot) | PSNR: 25.745 -> 25.858 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Dr.Bokeh — Dr. Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering (CVPR 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Dr. Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering (CVPR 2024 · similarity 0.92)
- BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching (AAAI 2026 · similarity 0.92)
- Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework (CVPR 2026 · similarity 0.92)
- AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer (NeurIPS 2026 · similarity 0.89)
- BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model (NeurIPS 2024 · similarity 0.83)
- DiffuseHigh: Training-Free Progressive High-Resolution Image Synthesis Through Structure Guidance (AAAI 2025 · 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.
