Geometry-Aware Neural Rendering
Epipolar geometry
Deep Neural Networks
DOI:
10.48550/arxiv.1911.04554
Publication Date:
2019-01-01
AUTHORS (3)
ABSTRACT
Understanding the 3-dimensional structure of world is a core challenge in computer vision and robotics. Neural rendering approaches learn an implicit 3D model by predicting what camera would see from arbitrary viewpoint. We extend existing neural to more complex, higher dimensional scenes than previously possible. propose Epipolar Cross Attention (ECA), attention mechanism that leverages geometry scene perform efficient non-local operations, requiring only $O(n)$ comparisons per spatial dimension instead $O(n^2)$. introduce three new simulated datasets inspired real-world robotics demonstrate ECA significantly improves quantitative qualitative performance Generative Query Networks (GQN).
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES ()
CITATIONS ()
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....