CVMay 6

The First Controllable Bokeh Rendering Challenge at NTIRE 2026

arXiv:2605.0551081.47 citationsh-index: 16
Predicted impact top 25% in CV · last 90 daysOriginality Synthesis-oriented
AI Analysis

This work establishes a benchmark for controllable bokeh rendering, providing a standardized evaluation framework for the computer vision community.

The paper presents the first Controllable Bokeh Rendering Challenge at NTIRE 2026, with 8 teams submitting valid solutions. The challenge evaluated methods on unseen images using both quantitative metrics and qualitative user studies, with most participants refining the Bokehlicious baseline.

This study presents the outcomes of the first Controllable Bokeh Rendering Challenge at NTIRE and highlights the most effective submitted methodologies. In total, 44 participants registered for the competition, of which 8 teams submitted valid solutions after the conclusion of the final test phase. All submissions were evaluated on unseen images, focusing on portraits and intricate subjects with complex and visually appealing bokeh phenomena. In addition to the first track focusing on established quantitative fidelity metrics, we conducted a qualitative user study with a panel of experts for a second track focusing on perceptual assessment. As this was the inaugural challenge on this topic, most of the participants focused on refining and extending the Bokehlicious baseline method.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes