Скачать или смотреть [ICCV 2025] SuperDec: 3D Scene Decomposition with Superquadric Primitives

This is the oral presentation of “SuperDec: 3D Scene Decomposition with Superquadric Primitives”, presented at ICCV 2025.

Project page: super-dec.github.io

Authors: Elisabetta Fedele, Boyang Sun, Leonidas Guibas, Marc Pollefeys, Francis Engelmann

Abstract: We present SuperDec, an approach for compact 3D scene representations based on geometric primitives, namely superquadrics. While most recent works leverage geometric primitives to obtain photorealistic 3D scene representations, we propose to leverage them to obtain a compact yet expressive representation. We propose to solve the problem locally on individual objects and leverage the capabilities of instance segmentation methods to scale our solution to full 3D scenes. In doing that, we design a new architecture which efficiently decompose point clouds of arbitrary objects in a compact set of superquadrics. We train our architecture on ShapeNet and we prove its generalization capabilities on object instances extracted from the ScanNet++ dataset as well as on full Replica scenes. Finally, we show how a compact representation based on superquadrics can be useful for a diverse range of downstream applications, including robotic tasks and controllable visual content generation and editing.

© 2025 IEEE/CVF International Conference on Computer Vision (ICCV). Uploaded for research visibility and educational purposes.