Weakly Supervised Generative Adversarial Networks for 3D Reconstruction

29 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials (2018, methodology): “[9] use 2D silhouettes as supervision for 3D reconstruction from a single image.”
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era (2019, methodology): “…either by using multiple binary masks captured from multiple viewpoints [19], which can only reconstruct the visual hull and as such, they are limited in accuracy, or by using adversarial training [91], [97], which constrains the reconstructed 3D shapes to be within the manifold of valid classes.”
Image2Mesh: A Learning Framework for Single Image 3D Reconstruction (2017, methodology): “s, pooling, and other techniques that have been successfully applied to 2D images for the learning process. Volumetric autoencoders [6,24] and generative adversarial networks (GAN) have been proposed [7,15,32] to learn of the probabilistic latent space of object shapes. It has been used for object c”
3D Object Reconstruction from a Single Depth View with Adversarial Learning (2017, methodology): “Perspective Transformer Nets [62] and the recent WS-GAN [18] are introduced to learn 3D object structures up to a 32(3) resolution occupancy grid.”