mlsanityData to 14 Oct 2026

Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images

arXiv 2109.02288 ↗First posted 6 Sep 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Recovering the 3D structure of an object from a single image is a challenging task due to its ill-posed nature. One approach is to utilize the plentiful photos of the same object category to learn a strong 3D shape prior for the object. This approach has successfully been demonstrated by a recent work of Wu et al. (2020), which obtained impressive 3D reconstruction networks with unsupervised learning. However, their algorithm is only applicable to symmetric objects. In this paper, we eliminate the symmetry requirement with a novel unsupervised algorithm that can learn a 3D reconstruction network from a multi-image dataset. Our algorithm is more general and covers the symmetry-required scenario as a special case. Besides, we employ a novel albedo loss that improves the reconstructed details and realisticity. Our method surpasses the previous work in both quality and robustness, as shown in experiments on datasets of various structures, including single-view, multi-view, image-collection, and video sets.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 29 of its 60 references that are in the map. First posted on arXiv 6 Sep 2021.

Builds on

29 of 60 references.

References · 29

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  2. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  3. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  4. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  6. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  7. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  8. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  9. 2014Learning Face Representation from Scratchcited by 453
  10. 2017Neural 3D Mesh Renderercited by 437
  11. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 268
  12. 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
17 more
  1. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 201
  2. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  3. 20193D Hand Shape and Pose from Images in the Wildcited by 190
  4. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  5. 20193D Hand Shape and Pose Estimation from a Single RGB Imagecited by 174
  6. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  7. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  8. 2018Nonlinear 3D Face Morphable Modelcited by 157
  9. 2017GANerated Hands for Real-time 3D Hand Tracking from Monocular RGBcited by 147
  10. 2017Morphable Face Models - An Open Frameworkcited by 138
  11. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  12. 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
  13. 2018Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimationcited by 78
  14. 20163D Face Reconstruction by Learning from Synthetic Datacited by 64
  15. 2017Rethinking Reprojection: Closing the Loop for Pose-aware ShapeReconstruction from a Single Imagecited by 20
  16. 2018Monocular Depth Estimation using Multi-Scale Continuous CRFs as Sequential Deep Networkscited by 19
  17. 20193D Dense Face Alignment via Graph Convolution Networkscited by 14

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2.

4 papers.

  1. 2022Improving 3D-aware Image Synthesis with A Geometry-aware Discriminatorcited by 16
  2. 2022Structural Causal 3D Reconstructioncited by 12
  3. 2023SimpSON: Simplifying Photo Cleanup with Single-Click Distracting Object Segmentation Networkcited by 5
  4. 2023Self-supervised Learning for Enhancing Geometrical Modeling in 3D-Aware Generative Adversarial Networkcited by 1