Corpus ID: 214611956

Universal Differentiable Renderer for Implicit Neural Representations

@article{Yariv2020UniversalDR,
  title={Universal Differentiable Renderer for Implicit Neural Representations},
  author={Lior Yariv and Matan Atzmon and Y. Lipman},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.09852}
}
The goal of this work is to learn implicit 3D shape representation with 2D supervision (i.e., a collection of images). To that end we introduce the Universal Differentiable Renderer (UDR) a neural network architecture that can provably approximate reflected light from an implicit neural representation of a 3D surface, under a wide set of reflectance properties and lighting conditions. Experimenting with the task of multiview 3D reconstruction, we find our model to improve upon the baselines in… Expand
7 Citations
Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations
  • PDF
Learning Implicit Surface Light Fields
  • 13
  • PDF
D-NeRF: Neural Radiance Fields for Dynamic Scenes
  • 27
  • PDF
Differentiable Rendering: A Survey
  • 13
  • Highly Influenced
  • PDF
Dynamic View Synthesis from Dynamic Monocular Video
  • PDF
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
  • 51
  • PDF

References

SHOWING 1-10 OF 30 REFERENCES
Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision
  • 112
  • Highly Influential
  • PDF
Learning to Infer Implicit Surfaces without 3D Supervision
  • 62
  • PDF
Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer
  • 88
  • PDF
Soft Rasterizer: A Differentiable Renderer for Image-Based 3D Reasoning
  • 152
  • PDF
OpenDR: An Approximate Differentiable Renderer
  • 288
  • PDF
Occupancy Networks: Learning 3D Reconstruction in Function Space
  • 436
  • PDF
Unsupervised Training for 3D Morphable Model Regression
  • 130
  • PDF
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
  • 480
  • Highly Influential
  • PDF
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
  • 793
  • PDF
Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction
  • 56
  • PDF
...
1
2
3
...