Continuous Dynamic-NeRF: Spline-NeRF

03/25/2022
by   Julian Knodt, et al.
0

The problem of reconstructing continuous functions over time is important for problems such as reconstructing moving scenes, and interpolating between time steps. Previous approaches that use deep-learning rely on regularization to ensure that reconstructions are approximately continuous, which works well on short sequences. As sequence length grows, though, it becomes more difficult to regularize, and it becomes less feasible to learn only through regularization. We propose a new architecture for function reconstruction based on classical Bezier splines, which ensures C^0 and C^1-continuity, where C^0 continuity is that ∀ c:lim_x→ c f(x) = f(c), or more intuitively that there are no breaks at any point in the function. In order to demonstrate our architecture, we reconstruct dynamic scenes using Neural Radiance Fields, but hope it is clear that our approach is general and can be applied to a variety of problems. We recover a Bezier spline B(β, t∈[0,1]), parametrized by the control points β. Using Bezier splines ensures reconstructions have C^0 and C^1 continuity, allowing for guaranteed interpolation over time. We reconstruct β with a multi-layer perceptron (MLP), blending machine learning with classical animation techniques. All code is available at https://github.com/JulianKnodt/nerf_atlas, and datasets are from prior work.

READ FULL TEXT
research
01/06/2021

Regularization-Agnostic Compressed Sensing MRI Reconstruction with Hypernetworks

Reconstructing under-sampled k-space measurements in Compressed Sensing ...
research
03/15/2021

Spline quadrature and semi-classical orthogonal Jacobi polynomials

A theory of spline quadrature rules for arbitrary continuity class in a ...
research
03/30/2022

Iterative Deep Homography Estimation

We propose Iterative Homography Network, namely IHN, a new deep homograp...
research
05/30/2023

Template-free Articulated Neural Point Clouds for Reposable View Synthesis

Dynamic Neural Radiance Fields (NeRFs) achieve remarkable visual quality...
research
03/21/2021

KPI Method for Dynamic Surface Reconstruction With B-splines based on Sparse Data

High dimensional B-splines are catching tremendous attentions in fields ...
research
03/22/2023

𝒞^k-continuous Spline Approximation with TensorFlow Gradient Descent Optimizers

In this work we present an "out-of-the-box" application of Machine Learn...

Please sign up or login with your details

Forgot password? Click here to reset