Research paper highlights by @CasualEffects
Toronto, ON
Joined February 2009
- Tweets1.3K
- Following34
- Followers4.8K
- Likes261
Some of my best CS research students were athletes. They have been trained in teamwork, grit, discipline, time management, and work ethic. They know how to leverage constructive criticism. And the brain is part of the body--physical health is good for mental health & innovation!
In a footnote, @paulg makes an unusual defense of school sports for a tech guy — they are the thing in school that most resembles the actual adult activity. “pretending to do something serious, or seriously doing something pretend.”
Gargan & Neelamkavil, Approximating Reflectance Functions using Neural Networks, EGSR 1998
books.google.ca/books?id=OJS…
That's about 23 years ahead of its time. Just imagine what you could learn at online EGSR'21 this year...
Morgan McGuire retweeted
Reminder that registration is free for @nvidia #GTC21 April 12-16, featuring @GeoffreyHinton who will share his latest work in #neural networks; sessions on #AppliedAI; and more. nvda.ws/3sR0kDh
Morgan McGuire retweeted
The I3D 2021 Program is up and now includes calendar entries you can easily add to your own calendar, see i3dsymposium.github.io/2021/… - hope to see you there. Come for the rendering, stay for the Rocket League :) #I3D2021
Jonnalagadda et al. Robust Vision-Based Cheat Detection in Competitive
Gaming, I3D'21 uses AI to detect cheating at the final image. This protects the privacy and integrity of the player's computer while allowing games to be secured even at the display.
arxiv.org/pdf/2103.10031.pdf
Morgan McGuire retweeted
Join us at ow.ly/NTNQ50E5rY2 for an interview with Hayley Iben, who recently received a Technical Achievement Award for her work on @Pixar's Taz hair simulation system. Congratulations, Hayley! Follow us and stay tuned for the inside stories of cool graphics researchers!
Morgan McGuire retweeted
My team at #nvidia is hiring!
Get involved in #NVIDIAOmniverse efforts around #syntheticdata, collaborate with our Toronto AI research team around the Kaolin 3D #DeepLearning library and more!
Apply here nvidia.wd5.myworkdayjobs.com… to work at the intersection of graphics and AI!
Morgan McGuire retweeted
In an internal chat, @JustRogDigiTec made the point that "2 people talking in stereo from the same location is basically noise, but 2 people talking in some spatialized audio form allows transition". We still have a ways to go, but VR audio is going to be surprisingly impactful.
Morgan McGuire retweeted
Excited to share our latest Behind the Magic #VFX reel on #TheMandalorian season 2. Enjoy! #Watch bit.ly/2OETouu
Morgan McGuire retweeted
We are happy to announce that our CFP is now live!
highperformancegraphics.org/…
Morgan McGuire retweeted
The “simple idea” of Maximum Likelihood is anything but.
There’s an epic history of a turbulent past, of surviving numerous assaults on the core idea, culminating in a beautiful yet complicated theory.
This paper is highly entertaining and educational.
arxiv.org/abs/0804.2996
Majercik et al. 2020, Scaling Probe-Based Real-Time Dynamic Global Illumination for Production presents advances on the "DDGI" ray tracing algorithm for large worlds, art direction, glossy reflection, and higher performance on all platforms.
arxiv.org/abs/2009.10796
Morgan McGuire retweeted
At HPG'20, we showed new esports results eliminating most of the task performance penalty for added latency in a first person view using 2D warps & late-latched input. This could accelerate desktop gaming or enable cloud gaming and XR with low latency.
casual-effects.com/research/…
Morgan McGuire retweeted
Turner Whitted's new IEEE ray tracing retrospective:
ieeexplore.ieee.org/document…
Morgan McGuire retweeted
The Khronos Vulkan Ray Tracing extension is here!
We now have a cross-vendor solution for GPU accelerated ray tracing on Vulkan as well as on DirectX. It is very similar to the DirectX Raytracing and OptiX APIs to make it easy to learn and port to.
khronos.org/blog/ray-tracing…
Morgan McGuire retweeted
I got through some of my game backlog last weekend.
A Short Hike (store.steampowered.com/app/1…, free on Epic this week)
Minit (store.steampowered.com/app/6…)
Are both friendly, cute Zelda-likes that play very quickly and have great graphics. Perfect for stressed-out adults and for kids.
Lample and Charton's new neural network symbolic mathematics solver includes integration and differentiation, and can beat Mathematica:
arxiv.org/pdf/1912.01412.pdf
The cheap and cheerful alternative to EMWA and Kalman filters for noisy input at varying frequencies by Casiez et al. 2012:
cristal.univ-lille.fr/~casie…
cristal.univ-lille.fr/~casie…
Mitsuba 2: A Retargetable Forward and Inverse Renderer by Nimier-David, Vicini, et al. ToG 2019 describes a technique for building and compiling efficient, modular, and parallel renderers in C++ for both CPUs and GPUs. The full source will soon be public.
rgl.epfl.ch/publications/Nim…
Low-Discrepancy Blue Noise Sampling, Ahmed et al. 2016 projet.liris.cnrs.fr/ldbn/
gives low-discrepancy sample points which are good for quasi-Monte Carlo integration that also have blue-noise properties and are thus perceptually desirable for residual noise and direct visualization
