視覚デザイン探索のためのヒューマンコンピュテーションを用いたパラメタ空間解析

視覚デザイン探索のための
ヒューマンコンピュテーションを用いたパラメタ空間解析

Two interfaces for visual design exploration that are realized by our analysis technique. (Top) Smart Suggestion: The user can obtain appropriate parameter sets as suggestions. (Bottom) VisOpt Slider: The user can adjust each parameter effectively by the visualization (Vis) near the slider and the optimization (Opt) that gently guides the current parameters to the optimal direction.

Two interfaces for visual design exploration that are realized by our analysis technique. (Left) Smart Suggestion: The user can obtain appropriate parameter sets as suggestions. (Right) VisOpt Slider: The user can adjust each parameter effectively by the visualization (Vis) near the slider and the optimization (Opt) that gently guides the current parameters to the optimal direction.

概要

Parameter tweaking is one of the fundamental tasks in the editing of visual digital contents, such as correcting photo color or executing blendshape facial expression control. A problem with parameter tweaking is that it often requires much time and effort to explore a high-dimensional parameter space. We present a new technique to analyze such high-dimensional parameter space to obtain a distribution of human preference. Our method uses crowdsourcing to gather pairwise comparisons between various parameter sets. As a result of analysis, the user obtains a goodness function that computes the goodness value of a given parameter set. This goodness function enables two interfaces for exploration: Smart Suggestion, which provides suggestions of preferable parameter sets, and VisOpt Slider, which interactively visualizes the distribution of goodness values on sliders and gently optimizes slider values while the user is editing. We created four applications with different design parameter spaces. As a result, the system could facilitate the user's design exploration.

本研究では，パラメタ空間を解析しデザインの「良し悪し」の空間分布を推定することで，パラメタ調整に基づく視覚デザイン探索を支援する手法を提案する．まず，クラウドソーシングを用いたヒューマンコンピュテーションによって，様々なパラメタによるデザインの比較結果を集め，それをもとにパラメタ空間の解析を行う手法を提案する．次に，その解析結果を利用して視覚デザインの探索を支援するための2つの新しいユーザインタフェースを提案する．(1) Smart Suggestionは比較的「良い」と考えられるデザインを選択的に提示する機能である．(2) VisOpt Sliderは「良し悪し」の分布をヒートマップによって対話的に可視化 (Vis: visualization) する機能を有するスライダであり，更にユーザが値を編集している最中に「良い」パラメタへと対話的に最適化 (Opt: optimization) する機能も有する．

動画

論文添付動画 (3:31)

プレビュー動画 (0:30)

ギャラリー

Overview of our method. Our goal is to facilitate design exploration, which often requires to tweak many design parameters. Our method analyzes the design parameter space and obtains a so-called goodness function that can evaluate the goodness of each design. To do this, we use crowdsourced human computation. Finally, we provide two interfaces utilizing this goodness function.

Application to color correction of photos. The user can easily tweak parameters such as brightness, contrast, etc.

Application to shader. Even non-expert can easily achieve realistic stainless teapot using complex shader.

Application to camera and light control in 3D scene. Our analysis successfully captures the non-linear relationship between camera and light.

Application to facial expression modeling (blendshape). Even when there are over 50 parameters, our analysis is still powerful.

スライド @ WISS 2014

ダウンロード

発表文献

Yuki Koyama, Daisuke Sakamoto, and Takeo Igarashi. 2014. Crowd-powered parameter analysis for visual design exploration. In Proceedings of the 27th annual ACM symposium on User interface software and technology (UIST '14). ACM, New York, NY, USA, 65-74. [doi]

小山裕己, 坂本大介, 五十嵐健夫. ヒューマンコンピュテーションによるパラメタ空間解析を用いた視覚デザイン探索. コンピュータソフトウェア, vol.33, no.1, pp.1_63-1_77. (研究論文賞)
Yuki Koyama, Daisuke Sakamoto, and Takeo Igarashi. 2015. Crowd-powered parameter analysis for computational design exploration. In ACM SIGGRAPH 2015 Posters (SIGGRAPH '15). ACM, New York, NY, USA, Article 2, 1 pages. [doi]
小山裕己, 坂本大介, 五十嵐健夫. 視覚デザイン探索のためのクラウドソーシングを活用したパラメタ空間解析. 22th Workshop on Interactive Systems and Software (WISS 2014). 2014年11月. (優秀論文賞)
小山裕己, 坂本大介, 五十嵐健夫. デジタルコンテンツ生成のためのクラウドソーシングによるパラメタ最適化. 21th Workshop on Interactive Systems and Software (WISS 2013). 2013年12月.
小山裕己. コンピュータグラフィクスのためのクラウドソーシングによるパラメタ調整支援. ビジュアル情報処理合宿, 2013年9月.

謝辞

Yuki Koyama is funded by JSPS research fellowship. This work was supported by JSPS KAKENHI Grant Number 26-8574, 26240027. The face model is provided by faceshift AG under CC BY 3.0. The dragon and bunny models are provided by The Stanford 3D Scanning Repository.

小山 裕己

概要

動画