Robin Huse retweeted
The Claude - Blender MCP connector is mind blowing. How would I have done this without it.
From DXF terrain data to final setup it cleaned up the scene, converted a proper point cloud and wrote a whole Delaunay triangulation mesher.
Robin Huse retweeted
🚀 Just added SPZ export to my 360° → 3DGS pipeline!
📊 8M splats → only 33MB (vs ~466MB PLY)
✨ New features: SPZ v3 format for 10x smaller files
Adaptive sampling - more Gaussians where detail matters
Quality presets: Low→Ultra (250K to 8M splats)
Transform any equirectangular panorama into a Gaussian splat VR scene
Painting:
Joakim Skovgaard. Christ in the Kingdom of the Dead
🌐
#GaussianSplatting #unity3d #GameDev #VR #3DGS #Voxels #Physics #madewithunity
1892
Robin Huse retweeted
First, the internet crawled so that AI can run.
Now, AR glasses will crawl so that robotics can run.
Robin Huse retweeted
That's beyond awesome! The future is here. Check out this paper thread on Radiance Fields applied to your favorite sitcom! 🧵
ShowMak3r: Compositional TV Show Reconstruction
TL;DR: We reconstruct dynamic radiance fields from TV shows, enabling editing of the scenes like how video clips are made in a production control room.
Contributions:
• We introduce ShowMak3r, a comprehensive pipeline that reconstructs the dynamic radiance field from TV shows, enabling viewpoint editing like a production control room.
• We propose 3DLocator, which accurately aligns actors on the stage. 3DLocator even aims to solve unseen poses due to occlusions.
• We present ShotMatcher, which enables continuous tracking of actors under shot changes. Our approach associates actors even when they are not visible in certain shots.
• We implement an implicit face-fitting network to recover and express dynamic facial expressions.
• Extensive experiments show the validity of our approach and demonstrate possible applications such as actor relocation, insertion, deletion, and pose manipulation.
Robin Huse retweeted
Hedra Studio and Character-3 is here. A new generation of AI-native video creation.
At its core is Character-3, the first omnimodal model in production, built to jointly reason across image, text, and audio for more intelligent video generation. This goes beyond multimodal—it’s the next evolution of AI-driven content creation.
With Hedra Studio, we’re making this technology easy to use. It brings together Character-3 and other leading AI tools in one platform, so creators can focus on ideas instead of complicated workflows.
With Hedra Studio, you can:
- Text-to-video and audio-to-video
- Character and general-purpose image and video creation
- Dynamic backgrounds, text-to-emotion, and top AI model integration
Character-3 sets a new standard for AI video. Hedra Studio makes it accessible. Both are available now.
Robin Huse retweeted
“We’ve added Experimental support for Apple Vision Pro’s Full and Mixed immersion styles, enabling creators to explore the full potential of augmented reality on Apple devices”
In the past, Unreal Engine hasn't been as fully featured on macOS as it has on Windows - we're making great strides, though 🛠️
We want your development to be cohesive across the platforms you work best on, after all!
Read up on this comprehensive progress report as we continue our journey to achieve feature parity on Apple platforms: epic.gm/ue-mac-progress-repo…
Robin Huse retweeted
Meta’s Controllable Human-Object
Interaction model is so accurate…
“Lift the chair, move and put down the chair”
Robin Huse retweeted
Simply Piano for Vision Pro just dropped!
Great music. Great design. You actually learn to read music, not just placement. AI-powered feedback. Play with or without a real piano. Oh, and it’s free!
There are plenty of piano learning apps in AR, but this one’s the best by far.
Robin Huse retweeted
Coming soon: new eye-hand interaction #XR research with direct & indirect gestures.
Before, a #2DUI teaser from 2015's "Gaze-Shifting" work:
Eye-hand coordination shifts pen mode btn.
1) direct drawing
2) precise cursor mode
Eyes stay on target.
bit.ly/3RUwigD – at Castellammare del Golfo, Sicily
Robin Huse retweeted
Day 7: Ever tried writing every day for a week? 7 Surprising Benefits of Writing Daily for a Week
Robin Huse retweeted
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
website: guanjunwu.github.io/4dgs/
abs: arxiv.org/abs/2310.08528
Trains a model to predict a deformation field of the 3D gaussian splatting representation to introduce dynamics to the scene
Robin Huse retweeted
TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis
pdf: arxiv.org/pdf/2109.15271.pdf
abs: arxiv.org/abs/2109.15271
project page: imaging.cs.cmu.edu/torf/
Robin Huse retweeted
📱 2021 Mobile AR Features V4
Now ∼50 features for 9 AR Providers!
🆕 Zappar added, credit @tomdefraine from @ZapparApp
👇 View, Suggest edits
docs.google.com/spreadsheets…
Robin Huse retweeted
Our method can reconstruct complex dynamic scenes from a monocular input video. Here is an example of a topological change caused by splitting a cookie in half. The video is played back from novel viewpoints. (6/N)
Robin Huse retweeted
I put up a list of #AR and #VR related paper presentations in #CHI2021 here: youtube.com/watch?v=bTdS8YCV… Please feel free to add more videos via shorturl.at/abwEX in case I missed one.
Robin Huse retweeted
Major WWDC preview: the new 3D Apple arrives.
scobleizer.blog/2021/05/15/t…
Will be doing a Twitter Space later this afternoon to talk with everyone about this.
If you are in VR or AR you MUST read this. It will change our industry deeply.
Robin Huse retweeted
Paper accepted to #ICML2021!
Sharf: Shape-conditioned Radiance Fields from a Single View
krematas.com/sharf/
arxiv.org/abs/2102.08860
We perform novel view synthesis by estimating the radiance field from a single image using a geometric scaffold
with @krematas, @rmbrualla
Robin Huse retweeted
Can get your coders to free my last name from icloud jail?
Been locked out for 6+ months because of an uncapitalized t in TRUE, my surname but also a computer command.
Now that I a layman have explained problem to you a giant computer company, could u fix?
@apple @AppleSupport
Robin Huse retweeted
I used to say I would help entrepreneurs for free. Now I do just that. That is what I do in between writing another book and chasing after the kids. Spatial Computing is about to have the rocket engines lit. Call me to tell me what you are building: +1-425-205-1921. All free.
Now that my career is over:
scobleizer.blog/2021/01/08/n…






























