paper-with-me

홈 › Papers

Rethinking 3D Shape Generation: Diffusion over Superquadrics

2026-06-08 · Zhiyang Liu, Wanze Li, Yuwei Wu, Chengran Yuan, Jiawei Sun, Rui Zheng, Marcelo H Ang arxiv

Diffusion models have advanced 3D shape generation, yet most methods still denoise in high-cardinality spaces (e.g., voxel/SDF grids, meshes, or point clouds), which is computationally and memory intensive and makes it difficult to scale in terms of both higher resolution and stronger controllability. We rethink the diffusion representation and propose to move diffusion from dense geometry to compact geometric primitives, representing each shape as a small set of superquadrics. Instead of operating on thousands to millions of geometric representation values, we leverage 7KB superquadric parameters (pose, size, and shape), drastically reducing diffusion-state dimensionality and per-step compute/memory. Our diffusion-over-superquadrics improves scalability by supporting broader capabilities (e.g., resolution-free point-cloud decoding, part-level editing, and constraint-based design) and achieving competitive surface-fidelity and distributional performance on standard benchmarks after point-cloud decoding, while enabling efficient generation within 0.6s per shape for most conditions.

📄 PDF Abstract BibTeX arXiv:2606.08957

Code (0)

등록된 구현이 없습니다.

Tasks

Point Clouds

Similar Papers 제목 키워드 기반

Supertoroid fitting of objects with holes for robotic grasping and scene generation

2024-12-05 · Joan Badia Torres, Eric Carmona, Abhijit Makhal, Omid Heidari 외

One of the strategies to detect the pose and shape of unknown objects is their geometric modeling, consisting on fitting known geometric entities. Classical geometric modeling fits simple shapes such as spheres or cylind…

Robotic GraspingScene Generation

Robust and Accurate Superquadric Recovery: a Probabilistic Approach

2021-11-29 · CVPR 2022 1 · Weixiao Liu, Yuwei Wu, Sipu Ruan, Gregory S. Chirikjian

Interpreting objects with basic geometric primitives has long been studied in computer vision. Among geometric primitives, superquadrics are well known for their ability to represent a wide range of shapes with few param…

Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids

2019-04-22 · CVPR 2019 6 · Despoina Paschalidou, Ali Osman Ulusoy, Andreas Geiger

Abstracting complex 3D shapes with parsimonious part-based representations has been a long standing goal in computer vision. This paper presents a learning-based solution to this problem which goes beyond the traditional…

Reinforcement Learning

Hierarchical Superquadric Decomposition with Implicit Space Separation

2022-09-15 · Jaka Šircelj, Peter Peer, Franc Solina, Vitomir Štruc

We introduce a new method to reconstruct 3D objects using a set of volumetric primitives, i.e., superquadrics. The method hierarchically decomposes a target 3D object into pairs of superquadrics recovering finer and fine…

Object

Sampling Superquadric Point Clouds with Normals

2018-02-14 · Paulo Ferreira

Superquadrics provide a compact representation of common shapes and have been used both for object/surface modelling in computer graphics and as object-part representation in computer vision and robotics. Superquadrics r…