Decoder Generates Manufacturable Structures: A Framework for 3D-Printable Object Synthesis
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909988569481216 |
|---|---|
| author | Kumar, Abhishek |
| author_facet | Kumar, Abhishek |
| contents | This paper presents a novel decoder-based approach for generating manufacturable 3D structures optimized for additive manufacturing. We introduce a deep learning framework that decodes latent representations into geometrically valid, printable objects while respecting manufacturing constraints such as overhang angles, wall thickness, and structural integrity. The methodology demonstrates that neural decoders can learn complex mapping functions from abstract representations to valid 3D geometries, producing parts with significantly improved manufacturability compared to naive generation approaches. We validate the approach on diverse object categories and demonstrate practical 3D printing of decoder-generated structures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08015 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Decoder Generates Manufacturable Structures: A Framework for 3D-Printable Object Synthesis Kumar, Abhishek Computer Vision and Pattern Recognition 68T45, 68U05 I.2.6; I.4.8; I.3.5 This paper presents a novel decoder-based approach for generating manufacturable 3D structures optimized for additive manufacturing. We introduce a deep learning framework that decodes latent representations into geometrically valid, printable objects while respecting manufacturing constraints such as overhang angles, wall thickness, and structural integrity. The methodology demonstrates that neural decoders can learn complex mapping functions from abstract representations to valid 3D geometries, producing parts with significantly improved manufacturability compared to naive generation approaches. We validate the approach on diverse object categories and demonstrate practical 3D printing of decoder-generated structures. |
| title | Decoder Generates Manufacturable Structures: A Framework for 3D-Printable Object Synthesis |
| topic | Computer Vision and Pattern Recognition 68T45, 68U05 I.2.6; I.4.8; I.3.5 |
| url | https://arxiv.org/abs/2601.08015 |