Piecewise-smooth surface fitting onto unstructured 3D sketches
Emilie Yu, Rahul Arora, J. Andreas Bærentzen, Karan Singh, Adrien Bousseau
Abstract
We propose a method to transform unstructured 3D sketches into piecewise smooth surfaces that preserve sketched geometric features. Immersive 3D drawing and sketch-based 3D modeling applications increasingly produce imperfect and unstructured collections of 3D strokes as design output. These 3D sketches are readily perceived as piecewise smooth surfaces by viewers, but are poorly handled by existing 3D surface techniques tailored to well-connected curve networks or sparse point sets. Our algorithm is aligned with human tendency to imagine the strokes as a small set of simple smooth surfaces joined along stroke boundaries. Starting with an initial proxy surface, we iteratively segment the surface into smooth patches joined sharply along some strokes, and optimize these patches to fit surrounding strokes. Our evaluation is fourfold: we demonstrate the impact of various algorithmic parameters, we evaluate our method on synthetic sketches with known ground truth surfaces, we compare to prior art, and we show compelling results on more than 50 designs from a diverse set of 3D sketch sources.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 115ecc4f-0d60-4730-a667-c7b9785ce936Cited by top-tier papers8
- 3D VR Sketch Guided 3D Shape Prototyping and ExplorationLing Luo, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song et al.ICCV 2023 · 19 citations
- ViewCraft3D: High-fidelity and View-Consistent 3D Vector Graphics SynthesisChuang Wang, Haitao Zhou, Ling Luo, Qian YuNeurIPS 2025 · 5 citations
- It's All About Your Sketch: Democratising Sketch Control in Diffusion ModelsSubhadeep Koley, Ayan Kumar Bhunia, Deeptanshu Sekhri, Aneeshan Sain et al.CVPR 2024
- Recovering Dynamic 3D Sketches from VideosJaeah Lee, Changwoon Choi, Young Min Kim, Jaesik ParkCVPR 2025
- Rapid 3D Model Generation with Intuitive 3D InputTianrun Chen, Chaotao Ding, Shangzhan Zhang, Chunan Yu et al.CVPR 2024
Builds on1
Related papers
- NeuralSketch2Surf: Fast Neural Surfacing of Unoriented 3D SketchesHongsheng Ye, Anandhu Sureshkumar, Zhonghan Wang, Stefanie Hahmann et al.SIGGRAPH 2026
- Sketch2Mesh: Reconstructing and Editing 3D Shapes from SketchesBenoît Guillard, Edoardo Remelli, Pierre Yvernay, Pascal FuaICCV 2021 · 102 citations
- Learning Manifold Patch-Based Representations of Man-Made ShapesDmitriy Smirnov, Mikhail Bessmeltsev, Justin SolomonICLR 2021 · 5 citations
- Neural Strokes: Stylized Line Drawing of 3D ShapesDifan Liu, Matthew Fisher, Aaron Hertzmann, Evangelos KalogerakisICCV 2021 · 29 citations
- 3Doodle: Compact Abstraction of Objects with 3D StrokesChangwoon Choi, Jaeah Lee, Jaesik Park, Young Min KimSIGGRAPH 2024 · 12 citations
