[4eyes] Fwd: [grads] Adam Schmidt MS Project Defense

[Adam Schmidt]

Hi all,

I'm giving my MS project defense talk today at 1pm, and I would be happy if
you would come!!

Best,
Adam

---------- Forwarded message ---------
From: Karen van Gool <kvangool at ucsb.edu>
Date: Thu, Jun 6, 2019 at 11:09 AM
Subject: [grads] Adam Schmidt MS Project Defense
To: <faculty at lists.cs.ucsb.edu>, <grads at lists.cs.ucsb.edu>, <
research at lists.cs.ucsb.edu>, <colloquia at lists.cs.ucsb.edu>


MS Project Defense

*Adam Schmidt*

Wednesday, June 12, 2019

1:00 PM – HFH 1132





*Committee: *Pradeep Sen (Chair), Lingqi Yan



*Title:* Fast Rendered Image Denoising Using Adaptive Blockwise Computation





*Abstract:*


This project looks at solutions for removing noise from rendered images in
real-time. Rendering is the process of creating an image from a model of a
scene or environment. Creating detailed renders can be an extremely costly
process, so a recent push in graphics has been to create noisy renders and
then estimate the detailed output. Given a rendered image, how can we
quickly denoise this result? Fast denoising would be useful when a game
company wants to denoise the scenes in their game in real-time, or when an
animation studio needs quick results to see how a scene will look in their
final animation. This project focuses on multiple concepts that can help
machine learning models approach denoising in real-time. The main novel
concept the project introduces is an optimization to allocate computation
based on region detail. We use a chain of multiple Convolutional Neural
Networks (CNNs) to estimate a detailed image at different levels of
refinement. After each refinement a binary-mask estimator is introduced to
decide which regions have reached sufficient levels of quality. The model
then continues on more complicated image regions. In my talk I will detail
the model's results and give a brief survey on the current state of the art.


*Everyone welcome!*

-- 
Karen van Gool
*she, her*
Graduate Student Advisor
Computer Sciences,UCSB
HFH 2104
805.893.4322
_______________________________________________
grads maillist  -  grads at lists.cs.ucsb.edu
https://lists.cs.ucsb.edu/mailman/listinfo/grads
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cs.ucsb.edu/pipermail/ilab-users/attachments/20190612/5013aedb/attachment.html>