mlsanityData to 7 Oct 2026

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

arXiv 2210.04265 ↗First posted 9 Oct 2022cs.CVcited by 2

Not on the map. Why?

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 9 Oct 2022.

Builds on

33 of 44 references.

References · 33

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  4. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  5. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  6. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  7. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  8. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  9. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  10. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  11. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  12. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
21 more
  1. 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 154
  2. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  3. 2020Combining Implicit Function Learning and Parametric Models for 3D Human Reconstructioncited by 133
  4. 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
  5. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  6. 2019Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Eracited by 87
  7. 2017AutoDIAL: Automatic DomaIn Alignment Layerscited by 75
  8. 2018Photo Wake-Up: 3D Character Animation from a Single Photocited by 60
  9. 2021StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Visioncited by 38
  10. 2021Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentationcited by 33
  11. 2021A Survey of Unsupervised Domain Adaptation for Visual Recognitioncited by 31
  12. 2021Unsupervised Domain Adaptation: A Reality Checkcited by 24
  13. 2020Deep Optimized Priors for 3D Shape Modeling and Reconstructioncited by 20
  14. 2020TetraTSDF: 3D human reconstruction from a single image with a tetrahedral outer shellcited by 18
  15. 2022An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detectioncited by 17
  16. 2018Domain-Adaptive Single-View 3D Reconstructioncited by 12
  17. 2020Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptationcited by 12
  18. 2019DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstructioncited by 7
  19. 2020Self-Supervised 2D Image to 3D Shape Translation with Disentangled Representationscited by 4
  20. 2020Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstructioncited by 4
  21. 2021DCL: Differential Contrastive Learning for Geometry-Aware Depth Synthesiscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformerscited by 7
  2. 2024Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Surveycited by 1