Главная
Study mode:
on
1
Intro
2
Presentation
3
Sparse recovery
4
Deep nihilism
5
Problems with deep solutions
6
Novel view synthesis
7
Nerf papers
8
How is Nerf different
9
Rendering a scene
10
Volumetric formulation
11
Transmittance equation
12
Multiview synthesis
13
Neural Radiance
14
Problems with Neural Radiance
15
Planoxyls
16
Regularization
17
Resolution
18
Harmonic Basis
19
Results
20
TV regularization
21
Synthetic scenes
22
More scenes
23
The 360 view
Description:
Explore a lecture on the intersection of compressed sensing and deep learning in computational imaging. Delve into Ben Recht's presentation at IPAM's Multi-Modal Imaging Workshop, where he discusses novel approaches to inverse problems. Learn about the Plenoxels system for photorealistic view synthesis, which offers a faster alternative to Neural Radiance Fields. Discover how sparse 3D grids with spherical harmonics can be optimized using gradient methods and convex regularization. Examine the trade-offs between theoretical guarantees and flexibility in imaging techniques, and understand the potential for combining the strengths of compressed sensing and deep learning paradigms. Gain insights into the challenges and advancements in multidimensional image processing, nonlinear measurements, and complex forward models in computational imaging.

Splitting the Difference Between Deep and Shallow Solutions of Inverse Problems

Institute for Pure & Applied Mathematics (IPAM)
Add to list
00:00
-00:38