Fit and diverse

Abstract

Figure 1: Set evolution starting from a small input set of lamps (left). With the set evolution "fit and diverse", new generations of shapes are not only fit to be lamps but also exhibit significant and potentially inspiring variations. AbstractWe introduce set evolution as a means for creative 3D shape modeling, where an initial population of 3D models is evolved to produce generations of novel shapes. Part of the evolving set is presented to a user as a shape gallery to offer modeling suggestions. User preferences define the fitness for the evolution so that over time, the shape population will mainly consist of individuals with good fitness. However, to inspire the user's creativity, we must also keep the evolving set diverse. Hence the evolution is "fit and diverse", drawing motivation from evolution theory. We introduce a novel part crossover operator which works at the finer-level part structures of the shapes, leading to significant variations and thus increased diversity in the evolved shape structures. Diversity is also achieved by explicitly compromising the fitness scores on a portion of the evolving population. We demonstrate the effectiveness of set evolution on man-made shapes. We show that selecting only models with high fitness leads to an elite population with low diversity. By keeping the population fit and diverse, the evolution can generate inspiring, and sometimes unexpected, shapes. Links:DL PDF WEB VIDEO DATA

Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation

“…Naturally, generating creative content can be tackled in many different ways. Xu et al [52] propose a set-evolution method for creative 3D shape modeling which aims to offer the user creative shapes that fit his preferences while still offering diversity. Elgammal et al [12] explore creative generation in the context of GANs [17] and learn new styles by maximizing the deviation from existing artistic styles using discriminators.…”

“…The quest for creative generation in computer graphics has sparked the study of computational creativity [8,19,41,42,52], which involves algorithms that simulate creative behaviors or try to enhance and augment the human creative pro-cess. Thanks to the rapid advancements in powerful text-toimage generative models, we now have an unprecedented ability to transform language into incredible, diverse images [4,11,27,33,35,37,39], opening up new possibilities for generating creative content.…”

Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation

“…Proxies usually retain a lower dimensional representation of the original model, which serve as a model reduction process and can be used to accelerate the rendering process or provide a more intuitive interface for users to manipulate the model. For example, in geometric modeling and shape manipulation, proxies reduces the complexity of original models, therefore enables structure preserving shape manipulation [ZFCO*11], shape collection synthesis [XZCOC12] and image‐based geometric modeling [XZZ*11]. Bounding volumes, which are one of the simplest form of proxies, are widely used in collision detection [GLM96,KHM*98], ray tracing [MOB*21] and shape approximation [CB17].…”

A Motion‐guided Interface for Modeling 3D Multi‐functional Furniture

“…Modeling by Example [FKS*04] is another way to help novice users to create models efficiently. To combine the parts of different shapes, shape deformations [XZCOC12] or predefined parameterized primitives [SSL*14] are needed. Our work also uses the concept of modeling with parameterized primitives, where our primitives can be static or dynamic furniture components.…”