Semantic aware 3D shape simplification using ellipsoids for better part editing
SemEllipsoid: Semantic-aware Shape Abstraction with Ellipsoid
GraphicsComputer Vision and Pattern Recognition
Summary
Making 3D objects simpler while keeping them accurate is important but tricky when the simple parts mix different shape pieces. The authors introduce a way to create simpler 3D models that keep each simple part matching exactly one meaningful section of the object, by using ellipsoid shapes and semantic information. Their method does not need training on lots of data and can work on many different object types. This helps in editing or manipulating specific parts of 3D objects without messing up other parts.
What this means in practice
- •For 3d modelers and animators: Create simplified 3D models that keep meaningful object parts separate for easier part-level editing and animation.
- •For game developers: Use semantically consistent shape approximations in games to improve performance and allow intuitive modification of object parts.
Authors
Kuankuan Cheng, Haocheng Yuan, Changjian Li
Abstract
Representing 3D shapes using a set of primitives - known as shape abstraction - is an actively studied problem in computer graphics with wide applications in shape understanding, analysis, and simulation due to the compactness and computational efficiency of the primitive-based representation. Prior work has primarily focused on geometry-aware shape abstraction, where the objective is to approximate the input shape with a minimal set of primitives while preserving geometric fidelity. However, these methods often overlook semantic consistency, inevitably leading to primitives that span across multiple semantic parts. Such inconsistency can cause undesirable artifacts in downstream tasks such as part-level shape editing or manipulation. In this paper, we introduce a new task - semantic-aware shape abstraction, where the goal is to produce abstractions that are both geometrically faithful and semantically consistent, ensuring that each primitive adheres strictly to a single semantic part without crossing semantic boundaries. We propose SemEllipsoid, a novel method to address this problem using ellipsoidal primitives. The core idea is to inject semantic constraints into the primitive optimization process leveraging the availability of semantic cues from large-scale foundation models. We design a fully differentiable projection-blending-evaluation scheme to measure semantic divergence against input semantic masks, and formulate an alternating optimization strategy to iteratively solve for optimal semantic assignment and primitive configurations. Our method is non-learning-based, requiring no data collection or network training, and generalizes well to shapes from arbitrary categories. It also supports different levels of abstraction according to user demand. Extensive experiments and evaluations validate the effectiveness of our approach across several 3D shape collections.