Morgan McGuire

@morgan3d

Research paper highlights by

Williams College and NVIDIA
Joined February 2009

Tweets

You blocked @morgan3d

Are you sure you want to view these Tweets? Viewing Tweets won't unblock @morgan3d

  1. Retweeted
    Apr 9

    Turner Whitted's new IEEE ray tracing retrospective:

    Undo
  2. Retweeted
    Mar 17

    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.

    Show this thread
    Undo
  3. Retweeted
    Mar 17

    I got through some of my game backlog last weekend. A Short Hike (, free on Epic this week) Minit () Are both friendly, cute Zelda-likes that play very quickly and have great graphics. Perfect for stressed-out adults and for kids.

    Show this thread
    Undo
  4. 17 Dec 2019

    Lample and Charton's new neural network symbolic mathematics solver includes integration and differentiation, and can beat Mathematica:

    Undo
  5. 30 Nov 2019

    The cheap and cheerful alternative to EMWA and Kalman filters for noisy input at varying frequencies by Casiez et al. 2012:

    Undo
  6. 4 Oct 2019

    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.

    Undo
  7. 22 Sep 2019

    Low-Discrepancy Blue Noise Sampling, Ahmed et al. 2016 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

    Undo
  8. 19 Sep 2019

    Non-linear sphere tracing for rendering deformed signed distance fields, Seyb et al. '19 Ray trace skinned SDFs by intersecting a bounding hull and then treating the gradient of the SDF as a flow field to traverse using an ODE solver--like a physics sim.

    Undo
  9. 9 Jul 2019

    González-Acuña & Chaparro-Romo, General formula for bi-aspheric singlet lens design free of spherical aberration, Applied Optics 2018

    Undo
  10. 18 Jun 2019

    Wang et al. Detecting Photoshopped Faces by Scripting Photoshop, 2019 (with code!) detects limited image manipulations using deep learning and attempts to undo them.

    Undo
  11. Retweeted
    18 Jun 2019

    In 2016, introduced the concept of distributing MC errors as a blue noise in screen space with Blue-noise Dithered Sampling. and I were inspired by the concept and we have been thinking about it for a while.

    Undo
  12. 18 Apr 2019

    Kim et al., NVGaze: An Anatomically-Informed Dataset for Low-Latency, Near-Eye Gaze Estimation, CH'2019 uses ray tracing and machine learning to build a fast gaze tracking system and shares their full high-res synthetic training dataset.

    Undo
  13. Retweeted
    5 Mar 2019

    I cobbled together an unofficial updated PDF of the book "Ray Tracing Gems," correcting all known errata (thanks, and others for your fixes!). Go get it, and see times & places for GDC/GTC signings and talks, here:

    Undo
  14. Retweeted
    6 Mar 2019

    Just uploaded a preprint of "Real-Time Continuous Level of Detail Rendering of Point Clouds": Essential source code samples here: Will follow up with videos/slides after the conference:

    Undo
  15. Retweeted
    25 Feb 2019

    Baseline Pupil Diameter Is Not a Reliable Biomarker of Subjective Sleepiness, because it has a circadian rhythm and it is sensitive to sleep pressure

    Undo
  16. Retweeted
    26 Feb 2019

    Enriching mesh vertices with filtered quadrics helps smoothing and clustering geometry at high speed, while preserving large salient structures. Find out more in our new paper, now online:

    Undo
  17. 6 Feb 2019

    Geirhos et al.'19 () show that image classification CNNs are remarkably similar to non-ML Bag of Feature models and largely focus on texture over relationships. Explained more clearly by

    Undo
  18. 6 Feb 2019

    Geirhos et al.'19 () show that image classification CNNs are remarkably similar to non-ML Bag of Feature models and largely focus on texture over relationships. Explained more clearly by

    Undo
  19. 7 Jan 2019

    Čadík, Perceptual Evaluation of Color-to-Grayscale Image Conversions, PG'08 has terrific evaluations of perceptual metrics for color -> luminance while preserving image content edges.

    Undo
  20. 5 Dec 2018

    Geirho et al. 2019, ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness Counters the overfitting to texture instead of shape of many classifiers by improving the training set.

    Undo

Loading seems to be taking a while.

Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

    You may also like

    ·