I recently found an easy setup to get into my slides. Compared to the standard zoom setup, it's fun, engaging, and allows me to interact with the slide contents directly.
Check out the thread below and set it up for your own presentation!
I mainly follow the excellent video tutorial by @cem_yuksel
but with a poor man's variant (i.e., without a white background or green screen).
Make sure to check out the videos for the best quality!
Step 1: Download Open Broadcaster Software (OBS) studio. obsproject.com
Why: We will use OBS to composite the slides and your camera video feed together and create a "virtual camera".
You can then use the virtual camera for your video conferencing presentation.
Step 2: Use Skype to create a FAKE digital green screen.
Specifically, choose a green image as your background effect. Now, leave this window there. We will use this camera preview on the screen as our video source in OBS (so that it won't reveal any background clutter).
Step 3: Use OBS to create the layered composition.
- Top: Your slides
- Middle: Window capture the skype (with crop and color key filters)
- Bottom: Your slides
The layering ensures that your face/hands appear BEHIND the slide contents.
Step 4: Set up the Virtual Camera.
In OBS, you will see the control panel on the bottom right. Just start the virtual camera.
Then, in the zoom video setting, you can select this "OBS Virtual Camera" as your video source.
Voilà! Now you can move into your slides, stream/record your presentation, and engage your students/audience better. No green screen or white background needed.
Try it out and let me know how it goes! Have fun!
Yet another solution is through the advanced zoom sharing feature. This approach, however, would
- limit yourself in the bottom right corner (cannot point to your content)
- occlude the slide contents.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
NeRF has shown incredible view synthesis results, but it requires multi-view captures for STATIC scenes.
How can we achieve view synthesis for DYNAMIC scenes from a single video? Here is what I learned from several recent efforts.
Instead of presenting Video-NeRF, Nerfie, NR-NeRF, D-NeRF, NeRFlow, NSFF (and many others!) as individual algorithms, here I try to view them from a unifying perspective and understand the pros/cons of various design choices.
Okay, here we go.
*Background*
NeRF represents the scene as a 5D continuous volumetric scene function that maps the spatial position and viewing direction to color and density. It then projects the colors/densities to form an image with volume rendering.
How do we get pseudo labels from unlabeled images?
Unlike classification, directly thresholding the network outputs for dense prediction doesn't work well.
Our idea: start with weakly sup. localization (Grad-CAM) and refine it with self-attention for propagating the scores.
Using two different prediction mechanisms is great bc they make errors in different ways. With our fusion strategy, we get WELL-CALIBRATED pseudo labels (see the expected calibration errors in E below) and IMPROVED accuracy under 1/4, 1/8, 1/16 of labeled examples.
Have you ever wondered why papers from top universities/research labs often appear in the top few positions in the daily email and web announcements from arXiv?
Why is that the case? Why should I care?
Wait a minute! Does the article position even matter?
The method achieves AWESOME results but requires precise camera poses as inputs.
Isn't SLAM/SfM a SOLVED problem? You might ask.
Yes, it works pretty well for static and controlled environments. For causal videos, existing methods usually fail to register all frames or produce outlier poses with large errors.
How can we learn NeRF from a SINGLE portrait image? Check out @gaochen315's recent work leverages new (meta-learning) and old (3D morphable model) tricks to make it work! This allows us to synthesize new views and manipulate FOV.
Training a NeRF from a single image from scratch won't work because it cannot recover the correct shape. The rendering results look fine at the original viewpoint but produce large errors at novel views.
Congratulations Jinwoo Choi for passing his Ph.D. thesis defense!
Special thanks to the thesis committee members (Lynn Abbott, @berty38, Harpreet Dhillon, and Gaurav Sharma) for valuable feedback and advices.
Jinwoo started his PhD in building an interactive system for home-based stroke rehabilitation. Published at ASSETS 17 and PETRA, 2018.
The preliminary efforts lay the foundation for a recent 1.1 million NSF Smart and Connected Health award!
He then looked into scene biases in action recognition datasets and presented debiasing methods that lead to improved generalization in downstream tasks [Choi NeurIPS 19]. chengao.vision/SDN/