Dictionary Fields: Learning a Neural Basis Decomposition
Open Access
- 26 July 2023
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (4) , 1-12
Abstract
We present Dictionary Fields, a novel neural representation which decomposes a signal into a product of factors, each represented by a classical or neural field representation, operating on transformed input coordinates. More specifically, we factorize a signal into a coefficient field and a basis field, and exploit periodic coordinate transformations to apply the same basis functions across multiple locations and scales. Our experiments show that Dictionary Fields lead to improvements in approximation quality, compactness, and training time when compared to previous fast reconstruction methods. Experimentally, our representation achieves better image approximation quality on 2D image regression tasks, higher geometric quality when reconstructing 3D signed distance fields, and higher compactness for radiance field reconstruction tasks. Furthermore, Dictionary Fields enable generalization to unseen images/3D scenes by sharing bases across signals during training which greatly benefits use cases such as image regression from partial observations and few-shot radiance field reconstruction.Keywords
Funding Information
- SNF (00021, 204840)
This publication has 25 references indexed in Scilit:
- Local Implicit Grid Representations for 3D Scenes2020
- Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision2020
- Deferred neural renderingACM Transactions on Graphics, 2019
- Neural volumesACM Transactions on Graphics, 2019
- Learning Implicit Fields for Generative Shape Modeling2019
- Stereo magnificationACM Transactions on Graphics, 2018
- Tanks and templesACM Transactions on Graphics, 2017
- Fast and flexible convolutional sparse coding2015
- Online dictionary learning for sparse coding2009
- Demo: Robust face recognition via sparse representation2008