# SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings

arXiv: https://arxiv.org/abs/2003.14034 · HTML: https://mlsanity.com/paper/2003.14034/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2020.

## Built on by (most cited first, 12 of 12)

- [Engineering Sketch Generation for Computer-Aided Design](https://mlsanity.com/paper/2104.09621/) (2021)
- [How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective](https://mlsanity.com/paper/2509.18905/) (2025)
- [Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning](https://mlsanity.com/paper/2110.15481/) (2021)
- [From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach](https://mlsanity.com/paper/2412.11892/) (2024)
- [Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings](https://mlsanity.com/paper/2508.18733/) (2025)
- [PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs](https://mlsanity.com/paper/2308.05744/) (2023)
- [Freehand Sketch Generation from Mechanical Components](https://mlsanity.com/paper/2408.05966/) (2024)
- ['CADSketchNet' -- An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks](https://mlsanity.com/paper/2107.06212/) (2021)
- [AI's Spatial Intelligence: Evaluating AI's Understanding of Spatial Transformations in PSVT:R and Augmented Reality](https://mlsanity.com/paper/2411.06269/) (2024)
- [Self-supervised Spatial Reasoning on Multi-View Line Drawings](https://mlsanity.com/paper/2104.13433/) (2021)
- [Agentic AI with Structured CoT for Enhancing AI's Spatial Intelligence: Visualization and Reasoning of Rotation](https://mlsanity.com/paper/2610.04188/) (2026)
- [Fine-Tuning VLM for Enhancing AI's Spatial Intelligence: Understanding 3D and 2D Rotations](https://mlsanity.com/paper/2610.04206/) (2026)

## Abstract (arXiv)

Spatial reasoning is an important component of human intelligence. We can imagine the shapes of 3D objects and reason about their spatial relations by merely looking at their three-view line drawings in 2D, with different levels of competence. Can deep networks be trained to perform spatial reasoning tasks? How can we measure their "spatial intelligence"? To answer these questions, we present the SPARE3D dataset. Based on cognitive science and psychometrics, SPARE3D contains three types of 2D-3D reasoning tasks on view consistency, camera pose, and shape generation, with increasing difficulty. We then design a method to automatically generate a large number of challenging questions with ground truth answers for each task. They are used to provide supervision for training our baseline models using state-of-the-art architectures like ResNet. Our experiments show that although convolutional networks have achieved superhuman performance in many visual learning tasks, their spatial reasoning performance on SPARE3D tasks is either lower than average human performance or even close to random guesses. We hope SPARE3D can stimulate new problem formulations and network designs for spatial reasoning to empower intelligent robots to operate effectively in the 3D world via 2D sensors. The dataset and code are available at https://ai4ce.github.io/SPARE3D.