mlsanityData to 7 Oct 2026

Learning to Generate Chairs, Tables and Cars with Convolutional Networks

arXiv 1411.5928 ↗First posted 21 Nov 2014cs.CV cs.LG cs.NEcited by 26

Not on the map. Why?

Abstract (arXiv)

We train generative 'up-convolutional' neural networks which are able to generate images of objects given object style, viewpoint, and color. We train the networks on rendered 3D models of chairs, tables, and cars. Our experiments show that the networks do not merely learn all images by heart, but rather find a meaningful representation of 3D models allowing them to assess the similarity of different models, interpolate between given views to generate the missing ones, extrapolate views, and invent new objects not present in the training set by recombining training instances, or even two different object classes. Moreover, we show that such generative networks can be used to find correspondences between different objects from the dataset, outperforming existing approaches on this task.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Nov 2014.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 17; 2022: 5; 2023: 3; 2024: 1.

26 papers.

Sort:

  1. 2021Editing Conditional Radiance Fieldscited by 222
  2. 2021Neural Articulated Radiance Fieldcited by 196
  3. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 179
  4. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 99
  5. 2021CDFI: Compression-Driven Network Design for Frame Interpolationcited by 55
  6. 2021Video Autoencoder: self-supervised disentanglement of static 3D structure and motioncited by 34
  7. 2023RadEdit: stress-testing biomedical vision models via diffusion image editingcited by 28
  8. 2021Where and What? Examining Interpretable Disentangled Representationscited by 27
  9. 2021Commutative Lie Group VAE for Disentanglement Learningcited by 27
  10. 2023GINA-3D: Learning to Generate Implicit Neural Assets in the Wildcited by 25
  11. 2021Model reduction for the material point method via an implicit neural representation of the deformation mapcited by 11
  12. 2021Deep View Synthesis via Self-Consistent Generative Networkcited by 10
14 more
  1. 2022MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Posecited by 10
  2. 2021Unsupervised Novel View Synthesis from a Single Imagecited by 8
  3. 2021A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videoscited by 8
  4. 2022Sparsity-guided Network Design for Frame Interpolationcited by 6
  5. 2021Prediction of MGMT Methylation Status of Glioblastoma using Radiomics and Latent Space Shape Featurescited by 3
  6. 2022MorphPool: Efficient Non-linear Pooling & Unpooling in CNNscited by 3
  7. 2021ID-Unet: Iterative Soft and Hard Deformation for View Synthesiscited by 2
  8. 2021Learning the Precise Feature for Cluster Assignmentcited by 1
  9. 2021Novel View Synthesis from a Single Image via Unsupervised learningcited by 1
  10. 2021Grounding Psychological Shape Space in Convolutional Neural Networkscited by 1
  11. 2024Level of agreement between emotions generated by Artificial Intelligence and human evaluation: a methodological proposalcited by 1
  12. 2021Profile to Frontal Face Recognition in the Wild Using Coupled Conditional GANcited by 0
  13. 2022ContraFeat: Contrasting Deep Features for Semantic Discoverycited by 0
  14. 2023Controllability-Constrained Deep Network Models for Enhanced Control of Dynamical Systemscited by 0