mlsanityData to 14 Oct 2026

One-to-many Reconstruction of 3D Geometry of cultural Artifacts using a synthetically trained Generative Model

arXiv 2402.08310 ↗First posted 13 Feb 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Estimating the 3D shape of an object using a single image is a difficult problem. Modern approaches achieve good results for general objects, based on real photographs, but worse results on less expressive representations such as historic sketches. Our automated approach generates a variety of detailed 3D representation from a single sketch, depicting a medieval statue, and can be guided by multi-modal inputs, such as text prompts. It relies solely on synthetic data for training, making it adoptable even in cases of only small numbers of training examples. Our solution allows domain experts such as a curators to interactively reconstruct potential appearances of lost artifacts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 20 references that are in the map. First posted on arXiv 13 Feb 2024.

Builds on

17 of 20 references.

References · 17

  1. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  2. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  3. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  4. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  5. 2022Pretraining is All You Need for Image-to-Image Translationcited by 160
  6. 2020Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizationscited by 102
  7. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  8. 2022Neural 3D Reconstruction in the Wildcited by 79
  9. 20173D Shape Reconstruction from Sketches via Multi-view Convolutional Networkscited by 45
  10. 2019Learning single-image 3D reconstruction by generative modelling of shape, pose and shadingcited by 43
  11. 2022MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpaintingcited by 35
  12. 2020RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloudcited by 26
5 more
  1. 2017Rethinking Reprojection: Closing the Loop for Pose-aware ShapeReconstruction from a Single Imagecited by 20
  2. 2020Style-transfer GANs for bridging the domain gap in synthetic pose estimator trainingcited by 7
  3. 2019Learning Manifold Patch-Based Representations of Man-Made Shapescited by 5
  4. 2020Self-Supervised 2D Image to 3D Shape Translation with Disentangled Representationscited by 4
  5. 2024A Concept for Reconstructing Stucco Statues from historic Sketches using synthetic Data onlycited by 1

Built on by

Not cited yet.