Diffusion for 3D shapes is moved from dense geometry to compact superquadric parameter sets, cutting state size to roughly 7 KB per shape and enabling faster generation plus new editing capabilities.
arXiv preprint arXiv:2504.00992 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Introduces a clustering-based optimization technique for fitting superquadrics to point clouds that handles noise, outliers, and deformations with closed-form solutions and convergence proofs.
Prox-E is a training-free pipeline that abstracts 3D shapes into editable geometric primitives, uses a VLM to specify changes, and guides a generative model to apply precise local edits.
C3G creates compact 3D Gaussian representations with 2K points by guiding placement via learnable tokens that aggregate multi-view features through attention, yielding better efficiency and performance than dense methods.
Introduces dual pose-image representation, cross-modal alignment, and iterative construction to improve prompt alignment and diversity in multi-person text-to-image generation.
citing papers explorer
-
Rethinking 3D Shape Generation: Diffusion over Superquadrics
Diffusion for 3D shapes is moved from dense geometry to compact superquadric parameter sets, cutting state size to roughly 7 KB per shape and enabling faster generation plus new editing capabilities.
-
A Holistic Method for Superquadric Fitting Using Unsupervised Clustering Analysis
Introduces a clustering-based optimization technique for fitting superquadrics to point clouds that handles noise, outliers, and deformations with closed-form solutions and convergence proofs.
-
Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes
Introduces dual pose-image representation, cross-modal alignment, and iterative construction to improve prompt alignment and diversity in multi-person text-to-image generation.