ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
This work provides a novel method for generating 3D articulated objects, which is important for applications in computer graphics and robotics, though it appears incremental relative to existing generative approaches.
The paper tackles the problem of generating diverse 3D articulated objects with high-quality geometry, addressing flexibility-quality tradeoffs in existing methods. It introduces a transformer-based framework that parameterizes objects as token trees and uses SDF shape priors, achieving effective conditional generation from text descriptions.
This paper presents a novel framework for modeling and conditional generation of 3D articulated objects. Troubled by flexibility-quality tradeoffs, existing methods are often limited to using predefined structures or retrieving shapes from static datasets. To address these challenges, we parameterize an articulated object as a tree of tokens and employ a transformer to generate both the object's high-level geometry code and its kinematic relations. Subsequently, each sub-part's geometry is further decoded using a signed-distance-function (SDF) shape prior, facilitating the synthesis of high-quality 3D shapes. Our approach enables the generation of diverse objects with high-quality geometry and varying number of parts. Comprehensive experiments on conditional generation from text descriptions demonstrate the effectiveness and flexibility of our method.