Playing with Puffball: simple scale-invariant inflation for use in vision and graphics

By Nathaniel R. Twarog, Marshall F. Tappen, Edward H. Adelson. 2012

18 citations recorded by the source corpus.

We describe how inflation, the act of mapping a 2D silhouette to a 3D region, can be applied in two disparate problems to offer insight and improvement: silhouette part segmentation and image-based material transfer. To demonstrate this, we introduce Puffball, a novel inflation technique, which achieves similar results to existing inflation approaches -- including smoothness, robustness, and scale and shift-invariance -- through an exceedingly simple and accessible formulation. The part segmentation algorithm avoids many of the pitfalls of previous approaches by finding part boundaries on a canonical 3-D shape rather than in the contour of the 2-D shape; the algorithm gives reliable and intuitive boundaries, even in cases where traditional approaches based on the 2D Minima Rule are misled. To demonstrate its effectiveness, we present data in which subjects prefer Puffball's segmentations to more traditional Minima Rule-based segmentations across several categories of silhouettes. The texture transfer algorithm utilizes Puffball's estimated shape information to produce visually pleasing and realistically synthesized surface textures with no explicit knowledge of either underlying shape.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Lifting Object Detection Datasets into 3D (2015, methodology): “…from detection data, which has been a difﬁcult obstacle to research in joint object recognition and reconstruction. show results of our method and two baselines, Puffball [46] and a convex hull approach which generates a mesh directly from the output of our rigid structure-from-motion component.”
Category-specific object reconstruction from a single image (2014, methodology): “Category-agnostic methods – Puffball[42] and SIRFS[5] – consistently perform worse on the benchmark by themselves.”
Reconstructing PASCAL VOC (2014, methodology): “Since no other existing class reconstruction technique scales to such a large and diverse dataset using simple 2D annotations we compare to two simple baselines: an inflation technique originally proposed for silhouette based single-view reconstruction [25] and a multi-view baseline based on our rig”
Learning Category-Specific Deformable 3D Models for Object Reconstruction (2017, methodology): “the art intrinsic image decomposition method and ‘Puffball’l [63] denotes a shape-inflation method for reconstruction.”