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

arXiv: https://arxiv.org/abs/2505.04813 · HTML: https://mlsanity.com/paper/2505.04813/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 69 references that are in the map.
- First posted on arXiv 7 May 2025.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)
- [Learning Shape Abstractions by Assembling Volumetric Primitives](https://mlsanity.com/paper/1612.00404/) (2016)
- [CvxNet: Learnable Convex Decomposition](https://mlsanity.com/paper/1909.05736/) (2019)
- [Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception](https://mlsanity.com/paper/2306.06362/) (2023)
- [Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks](https://mlsanity.com/paper/2103.10429/) (2021)
- [Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models](https://mlsanity.com/paper/2207.11514/) (2022)
- [Photo-Sketching: Inferring Contour Drawings from Images](https://mlsanity.com/paper/1901.00542/) (2019)
- [SketchGen: Generating Constrained CAD Sketches](https://mlsanity.com/paper/2106.02711/) (2021)
- [CLIPascene: Scene Sketching with Different Types and Levels of Abstraction](https://mlsanity.com/paper/2211.17256/) (2022)
- [Breathing Life Into Sketches Using Text-to-Video Priors](https://mlsanity.com/paper/2311.13608/) (2023)
- [Learning to Sketch with Shortcut Cycle Consistency](https://mlsanity.com/paper/1805.00247/) (2018)
- [Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts](https://mlsanity.com/paper/2109.08857/) (2021)
- [Diffusion Feedback Helps CLIP See Better](https://mlsanity.com/paper/2407.20171/) (2024)
- [PointGMM: a Neural GMM Network for Point Clouds](https://mlsanity.com/paper/2003.13326/) (2020)
- [NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images](https://mlsanity.com/paper/2303.07653/) (2023)
- [3Doodle: Compact Abstraction of Objects with 3D Strokes](https://mlsanity.com/paper/2402.03690/) (2024)
- [SketchLattice: Latticed Representation for Sketch Manipulation](https://mlsanity.com/paper/2108.11636/) (2021)
- [Marching-Primitives: Shape Abstraction from Signed Distance Function](https://mlsanity.com/paper/2303.13190/) (2023)
- [Wired Perspectives: Multi-View Wire Art Embraces Generative AI](https://mlsanity.com/paper/2311.15421/) (2023)
- [Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features](https://mlsanity.com/paper/2311.18113/) (2023)
- [GeoCode: Interpretable Shape Programs](https://mlsanity.com/paper/2212.11715/) (2022)
- [Neural Contours: Learning to Draw Lines from 3D Shapes](https://mlsanity.com/paper/2003.10333/) (2020)
- [Primitive-based Shape Abstraction via Nonparametric Bayesian Inference](https://mlsanity.com/paper/2203.14714/) (2022)
- [Neural Strokes: Stylized Line Drawing of 3D Shapes](https://mlsanity.com/paper/2110.03900/) (2021)
- [3D Neural Edge Reconstruction](https://mlsanity.com/paper/2405.19295/) (2024)
- [Real-World Textured Things: a Repository of Textured Models Generated with Modern Photo-Reconstruction Tools](https://mlsanity.com/paper/2004.14753/) (2020)
- [Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering](https://mlsanity.com/paper/2405.15305/) (2024)

## Built on by (most cited first, 4 of 4)

- [Voxify3D: Pixel Art Meets Volumetric Rendering](https://mlsanity.com/paper/2512.07834/) (2025)
- [Fishbone: From One 3D Asset to a Million Controllable Edits](https://mlsanity.com/paper/2605.24805/) (2026)
- [Single-Line Drawing Generation via Semantics-Driven Optimization](https://mlsanity.com/paper/2606.01910/) (2026)
- [Organize Primitives into Semantic Parts: Reinforcement Reasoning for 3D Segmentation](https://mlsanity.com/paper/2610.04602/) (2026)

## Abstract (arXiv)

In this work 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.