paper-with-me

Papers

ParSEL: Parameterized Shape Editing with Language

2024-05-30 · Aditya Ganeshan, Ryan Y. Huang, Xianghao Xu, R. Kenny Jones, Daniel Ritchie

The ability to edit 3D assets from natural language presents a compelling paradigm to aid in the democratization of 3D content creation. However, while natural language is often effective at communicating general intent, it is poorly suited for specifying precise manipulation. To address this gap, we introduce ParSEL, a system that enables controllable editing of high-quality 3D assets from natural language. Given a segmented 3D mesh and an editing request, ParSEL produces a parameterized editing program. Adjusting the program parameters allows users to explore shape variations with a precise control over the magnitudes of edits. To infer editing programs which align with an input edit request, we leverage the abilities of large-language models (LLMs). However, while we find that LLMs excel at identifying initial edit operations, they often fail to infer complete editing programs, and produce outputs that violate shape semantics. To overcome this issue, we introduce Analytical Edit Propagation (AEP), an algorithm which extends a seed edit with additional operations until a complete editing program has been formed. Unlike prior methods, AEP searches for analytical editing operations compatible with a range of possible user edits through the integration of computer algebra systems for geometric analysis. Experimentally we demonstrate ParSEL's effectiveness in enabling controllable editing of 3D objects through natural language requests over alternative system designs.

📄 PDF Abstract BibTeX arXiv:2405.20319

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Towards High-fidelity Artistic Image Vectorization via Texture-Encapsulated Shape Parameterization

2024-01-01 · CVPR 2024 1 · Ye Chen, Bingbing Ni, Jinfan Liu, Xiaoyang Huang 외

We develop a novel vectorized image representation scheme accommodating both shape/geometry and texture in a decoupled way particularly tailored for reconstruction and editing tasks of artistic/design images such as …

Image CompressionZero-Shot Learning

Easy-editable Image Vectorization with Multi-layer Multi-scale Distributed Visual Feature Embedding

2025-01-01 · CVPR 2025 1 · Ye Chen, Zhangli Hu, Zhongyin Zhao, Yupeng Zhu 외

Current parameterized image representations embed visual information along the semantic boundaries and struggle to express the internal detailed texture structures of image components, leading to a lack of content co…

ShapeWalk: Compositional Shape Editing Through Language-Guided Chains

2024-01-01 · CVPR 2024 1 · Habib Slim, Mohamed Elhoseiny

Editing 3D shapes through natural language instructions is a challenging task that requires the comprehension of both language semantics and fine-grained geometric details. To bridge this gap we introduce ShapeWalk a…

LADIS: Language Disentanglement for 3D Shape Editing

2022-12-09 · IAn Huang, Panos Achlioptas, Tianyi Zhang, Sergey Tulyakov 외

Natural language interaction is a promising direction for democratizing 3D shape design. However, existing methods for text-driven 3D shape editing face challenges in producing decoupled, local edits to 3D shapes. We add…

3D geometryDisentanglement

ShapeTalk: A Language Dataset and Framework for 3D Shape Edits and Deformations

2023-01-01 · CVPR 2023 1 · Panos Achlioptas, IAn Huang, Minhyuk Sung, Sergey Tulyakov 외

Editing 3D geometry is a challenging task requiring specialized skills. In this work, we aim to facilitate the task of editing the geometry of 3D models through the use of natural language. For example, we may want t…

3D geometryNeural Rendering