# Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks

arXiv: https://arxiv.org/abs/1807.08485 · HTML: https://mlsanity.com/paper/1807.08485/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2018.

## Built on by (most cited first, 9 of 9)

- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion](https://mlsanity.com/paper/2111.10332/) (2021)
- [Exploiting GPT-4 Vision for Zero-shot Point Cloud Understanding](https://mlsanity.com/paper/2401.07572/) (2024)
- [VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understanding](https://mlsanity.com/paper/2409.09254/) (2024)
- [Physics Validation of Novel Convolutional 2D Architectures for Speeding Up High Energy Physics Simulations](https://mlsanity.com/paper/2105.08960/) (2021)
- [ViewFormer: View Set Attention for Multi-view 3D Shape Understanding](https://mlsanity.com/paper/2305.00161/) (2023)
- [InfoGNN: End-to-end deep learning on mesh via graph neural networks](https://mlsanity.com/paper/2503.02414/) (2025)
- [MeshCNN Fundamentals: Geometric Learning through a Reconstructable Representation](https://mlsanity.com/paper/2105.13277/) (2021)

## Abstract (arXiv)

We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs. We represent 3D shapes as multi-layered height-maps (MLH) where at each grid location, we store multiple instances of height maps, thereby representing 3D shape detail that is hidden behind several layers of occlusion. We provide a novel view merging method for combining view dependent information (Eg. MLH descriptors) from multiple views. Because of the ability of using 2D CNNs, our method is highly memory efficient in terms of input resolution compared to the voxel based input. Together with MLH descriptors and our multi view merging, we achieve the state-of-the-art result in classification on ModelNet dataset.