# Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation

arXiv: https://arxiv.org/abs/1802.09987 · HTML: https://mlsanity.com/paper/1802.09987/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2018.

## Built on by (most cited first, 7 of 7)

- [gradSim: Differentiable simulation for system identification and visuomotor control](https://mlsanity.com/paper/2104.02646/) (2021)
- [Active 3D Shape Reconstruction from Vision and Touch](https://mlsanity.com/paper/2107.09584/) (2021)
- [SuperGaussian: Repurposing Video Models for 3D Super Resolution](https://mlsanity.com/paper/2406.00609/) (2024)
- [Improved α-GAN architecture for generating 3D connected volumes with an application to radiosurgery treatment planning](https://mlsanity.com/paper/2207.11223/) (2022)
- [Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Images](https://mlsanity.com/paper/2109.11844/) (2021)
- [Machine Learning for Detection of 3D Features using sparse X-ray data](https://mlsanity.com/paper/2206.02564/) (2022)
- [Reconstructing vehicles from orthographic drawings using deep neural networks](https://mlsanity.com/paper/2206.08789/) (2022)

## Abstract (arXiv)

We consider the problem of scaling deep generative shape models to high-resolution. Drawing motivation from the canonical view representation of objects, we introduce a novel method for the fast up-sampling of 3D objects in voxel space through networks that perform super-resolution on the six orthographic depth projections. This allows us to generate high-resolution objects with more efficient scaling than methods which work directly in 3D. We decompose the problem of 2D depth super-resolution into silhouette and depth prediction to capture both structure and fine detail. This allows our method to generate sharp edges more easily than an individual network. We evaluate our work on multiple experiments concerning high-resolution 3D objects, and show our system is capable of accurately predicting novel objects at resolutions as large as 512×512×512 -- the highest resolution reported for this task. We achieve state-of-the-art performance on 3D object reconstruction from RGB images on the ShapeNet dataset, and further demonstrate the first effective 3D super-resolution method.