AI Paper Atlas

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

ICCV 2025 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 8 citations (OpenAlex)

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 changedWhereMeasuredEffect
add spatial Manhattan decay mask to attention (ablation)Bokehlicious attention · RealBokeh (all f-stops)PSNR: 31.271 -> 32.708Improved
use per-head decay mask scales instead of one shared mask (ablation)Bokehlicious attention · RealBokeh (all f-stops)PSNR: 32.708 -> 33.224Improved
make decay masks aperture-aware (f-aware) (ablation)Bokehlicious attention · RealBokeh (all f-stops)PSNR: 33.224 -> 33.300Improved
make decay masks aperture-aware (f-aware), f/2.8 (ablation)Bokehlicious attention · RealBokeh (f/2.8)PSNR: 30.665 -> 31.101Improved
use AAA instead of Swin attention (ablation)Bokehlicious · RealBokeh (all f-stops)PSNR: 32.242 -> 33.300Improved
use AAA instead of NAT attention (ablation)Bokehlicious · RealBokeh (all f-stops)PSNR: 32.940 -> 33.300Improved
scale model from M to LBokehlicious · RealBokeh-binPSNR: 30.358 -> 31.250Improved
Bokehlicious-M vs best prior (DMSHN)Bokehlicious-M · RealBokeh-binPSNR: 29.311 -> 30.358Improved
Bokehlicious-M vs BoMe with aperture controlBokehlicious-M · RealBokeh (all f-stops)PSNR: 29.125 -> 33.300Improved
Bokehlicious-M vs BoMeBokehlicious-M · EBB400PSNR: 23.85 -> 24.47Improved
Bokehlicious-M vs AMPNBokehlicious-M · EBB! Val294LPIPS: 0.1718 -> 0.1638Improved
train Bokehlicious-L on RealDefocus for deblurring vs DRBNetBokehlicious-L · RealDOF (zero-shot)PSNR: 25.745 -> 25.858Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy