Princeton > CS Dept > PIXL > Graphics > Publications Local Access 

Composition-Aware Scene Optimization for Product Images
Computer Graphics Forum (Proc. Eurographics), May 2015

Tianqiang Liu, Jim McCann, Wilmot Li,
Thomas Funkhouser


Detail images generated from overview. From an overview image of a living room (a), we automatically generate detail images that highlight the speaker (b) and shelf (c). Notice how the chair moves to the right in (b) and to the left in (c) to provide an unobstructed view of the focus object.

Abstract

Increasingly, companies are creating product advertisements and catalog images using computer renderings of 3D scenes. A common goal for these companies is to create aesthetically appealing compositions that highlight objects of interest within the context of a scene. Unfortunately, this goal is challenging, not only due to the need to balance the trade-off among aesthetic principles and design constraints, but also because of the huge search space induced by possible camera parameters, object placement, material choices, etc. Previous methods have investigated only optimization of camera parameters. In this paper, we develop a tool that starts from an initial scene description and a set of high-level constraints provided by a stylist and then automatically generates an optimized scene whose 2D composition is improved. It does so by locally adjusting the 3D object transformations, surface materials, and camera parameters. The value of this tool is demonstrated in a variety of applications motivated by product catalogs, including rough layout refinement, detail image creation, home planning, cultural customization, and text inlay placement. Results of a perceptual study indicate that our system produces images preferable for product advertisement compared to a more traditional camera-only optimization.

Citation (BibTeX)

Tianqiang Liu, Jim McCann, Wilmot Li, and Thomas Funkhouser. Composition-Aware Scene Optimization for Product Images. Computer Graphics Forum (Proc. Eurographics) 34(2), May 2015.

Paper
  24.1M
  0.5M

Links
  Supplemental material
  Video

Talk
  PDF
  PPTX