paper-with-me

Papers

WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction

2025-05-07 · Richard Liu, Daniel Fu, Noah Tan, Itai Lang, Rana Hanocka

We present WIR3D, a technique for abstracting 3D shapes through a sparse set of visually meaningful curves in 3D. We optimize the parameters of Bezier curves such that they faithfully represent both the geometry and salient visual features (e.g. texture) of the shape from arbitrary viewpoints. We leverage the intermediate activations of a pre-trained foundation model (CLIP) to guide our optimization process. We divide our optimization into two phases: one for capturing the coarse geometry of the shape, and the other for representing fine-grained features. Our second phase supervision is spatially guided by a novel localized keypoint loss. This spatial guidance enables user control over abstracted features. We ensure fidelity to the original surface through a neural SDF loss, which allows the curves to be used as intuitive deformation handles. We successfully apply our method for shape abstraction over a broad dataset of shapes with varying complexity, geometric structure, and texture, and demonstrate downstream applications for feature control and shape deformation.

📄 PDF Abstract BibTeX arXiv:2505.04813

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes

2025-09-29 · Yuhan Wang, Weikai Chen, Zeyu Hu, Runze Zhang 외 arxiv

In user-generated-content (UGC) applications, non-expert users often rely on image-to-3D generative models to create 3D assets. In this context, primitive-based shape abstraction offers a promising solution for UGC scena…

Robust and Explainable 3D Mode Shape Recognition Using Region-Aware Graph Neural Networks

2026-07-01 · Tong Duy Son, Marc Brughmans, Andrey Hense, Kohta Sugiura 외 arxiv

Mode shape recognition is a fundamental task in automotive NVH development, yet it remains dependent on manual visual inspection by experienced engineers. Existing approaches based on engineering heuristics, Modal Assura…

Graph Learning

Geometry-Aware Face Completion and Editing

2018-09-09 · Linsen Song, Jie Cao, Linxiao Song, Yibo Hu 외

Face completion is a challenging generation task because it requires generating visually pleasing new pixels that are semantically consistent with the unmasked face region. This paper proposes a geometry-aware Face Compl…

DecoderFacial Inpainting

Geometry-Aware Physics-Informed PointNets for Modeling Flows Across Porous Structures

2026-02-15 · Luigi Ciceri, Corrado Mio, Jianyi Lin, Gabriele Gianini arxiv

Predicting flows that occur both through and around porous bodies is challenging due to coupled physics across fluid and porous regions and the need to generalize across diverse geometries and boundary conditions. We add…

Geometry-aware framework for deep energy method: an application to structural mechanics with hyperelastic materials

2024-05-06 · Thi Nguyen Khoa Nguyen, Thibault Dairay, Raphaël Meunier, Christophe Millet 외

Physics-Informed Neural Networks (PINNs) have gained considerable interest in diverse engineering domains thanks to their capacity to integrate physical laws into deep learning models. Recently, geometry-aware PINN-based…

Contact mechanicsForm