# 3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models

arXiv: https://arxiv.org/abs/2210.04265 · HTML: https://mlsanity.com/paper/2210.04265/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 9 Oct 2022.

## Builds on (most cited first, 30 of 33)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction](https://mlsanity.com/paper/2007.03858/) (2020)
- [STAR: Sparse Trained Articulated Human Body Regressor](https://mlsanity.com/paper/2008.08535/) (2020)
- [DeepHuman: 3D Human Reconstruction from a Single Image](https://mlsanity.com/paper/1903.06473/) (2019)
- [DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing](https://mlsanity.com/paper/1911.13225/) (2019)
- [Tex2Shape: Detailed Full Human Body Geometry From a Single Image](https://mlsanity.com/paper/1904.08645/) (2019)
- [SMPLicit: Topology-aware Generative Model for Clothed People](https://mlsanity.com/paper/2103.06871/) (2021)
- [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.08400/) (2017)
- [Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction](https://mlsanity.com/paper/2007.11432/) (2020)
- [Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing](https://mlsanity.com/paper/2204.08906/) (2022)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era](https://mlsanity.com/paper/1906.06543/) (2019)
- [AutoDIAL: Automatic DomaIn Alignment Layers](https://mlsanity.com/paper/1704.08082/) (2017)
- [Photo Wake-Up: 3D Character Animation from a Single Photo](https://mlsanity.com/paper/1812.02246/) (2018)
- [StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision](https://mlsanity.com/paper/2104.05289/) (2021)
- [Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation](https://mlsanity.com/paper/2103.04705/) (2021)
- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (2021)
- [Unsupervised Domain Adaptation: A Reality Check](https://mlsanity.com/paper/2111.15672/) (2021)
- [Deep Optimized Priors for 3D Shape Modeling and Reconstruction](https://mlsanity.com/paper/2012.07241/) (2020)
- [TetraTSDF: 3D human reconstruction from a single image with a tetrahedral outer shell](https://mlsanity.com/paper/2004.10534/) (2020)
- [An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection](https://mlsanity.com/paper/2204.00154/) (2022)
- [Domain-Adaptive Single-View 3D Reconstruction](https://mlsanity.com/paper/1812.01742/) (2018)
- [Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation](https://mlsanity.com/paper/2005.07839/) (2020)
- [DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction](https://mlsanity.com/paper/1911.09204/) (2019)

## Built on by (most cited first, 2 of 2)

- [Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers](https://mlsanity.com/paper/2308.14152/) (2023)
- [Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey](https://mlsanity.com/paper/2412.01450/) (2024)

## Abstract (arXiv)

Acquiring the virtual equivalent of exhibits, such as sculptures, in virtual reality (VR) museums, can be labour-intensive and sometimes infeasible. Deep learning based 3D reconstruction approaches allow us to recover 3D shapes from 2D observations, among which single-view-based approaches can reduce the need for human intervention and specialised equipment in acquiring 3D sculptures for VR museums. However, there exist two challenges when attempting to use the well-researched human reconstruction methods: limited data availability and domain shift. Considering sculptures are usually related to humans, we propose our unsupervised 3D domain adaptation method for adapting a single-view 3D implicit reconstruction model from the source (real-world humans) to the target (sculptures) domain. We have compared the generated shapes with other methods and conducted ablation studies as well as a user study to demonstrate the effectiveness of our adaptation method. We also deploy our results in a VR application.