# Deep3DSketch: 3D modeling from Free-hand Sketches with View- and Structural-Aware Adversarial Training

arXiv: https://arxiv.org/abs/2312.04435 · HTML: https://mlsanity.com/paper/2312.04435/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2023.

## Built on by (most cited first, 5 of 5)

- [Discrete Latent Perspective Learning for Segmentation and Detection](https://mlsanity.com/paper/2406.10475/) (2024)
- [From Air to Wear: Personalized 3D Digital Fashion with AR/VR Immersive 3D Sketching](https://mlsanity.com/paper/2505.09998/) (2025)
- [Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches](https://mlsanity.com/paper/2503.12191/) (2025)
- [Order Matters: 3D Shape Generation from Sequential VR Sketches](https://mlsanity.com/paper/2512.04761/) (2025)
- ["I Just Need GPT to Refine My Prompts": Rethinking Onboarding and Help-Seeking with Generative 3D Modeling Tools](https://mlsanity.com/paper/2603.29118/) (2026)

## Abstract (arXiv)

This work aims to investigate the problem of 3D modeling using single free-hand sketches, which is one of the most natural ways we humans express ideas. Although sketch-based 3D modeling can drastically make the 3D modeling process more accessible, the sparsity and ambiguity of sketches bring significant challenges for creating high-fidelity 3D models that reflect the creators' ideas. In this work, we propose a view- and structural-aware deep learning approach, textitDeep3DSketch, which tackles the ambiguity and fully uses sparse information of sketches, emphasizing the structural information. Specifically, we introduced random pose sampling on both 3D shapes and 2D silhouettes, and an adversarial training scheme with an effective progressive discriminator to facilitate learning of the shape structures. Extensive experiments demonstrated the effectiveness of our approach, which outperforms existing methods -- with state-of-the-art (SOTA) performance on both synthetic and real datasets.