Space and time reconstructed in 4D
Is this how higher dimensional beings see us - every moment at once?
Starting to understand what Vonnegut meant by humans being “great millipedes” - clearly it applies to our four legged friends too!
Geolocated 2d video → per frame 3d gaussians → each left precisely where & when it happened
Andrew Ng just dropped the best 2-hour course on Graph Engineering: from single agent to full automation
9:14 - your first agent
33:11 - loop engineering
1:02:46 - graph engineering
1:30:15 - agents that rewrite themselves
1:49:05 - full graph system
two hours, and it replaces every agent tutorial you bookmarked this year
Prompts → Agents → Loops → Graphs
most people will stop after the first agent and call it automation
he saves the last forty minutes for the graph that runs it without him
same model, same tokens, completely different week
watch it today
the step-by-step guide is below, save it while it is still early ↓
📸 Sharp Astra Photo Editor ✨
Built with #Astra and @Apple#SHARP, this @ThreeJS prototype turns a 2D photo into a 3D Gaussian splat scene .... blending 3D objects, like this typographic ring, that pass in front of and behind subjects using the inferred depth. ⭐
Fable 5 is nuts. I vibe coded terminator vision replays with no LiDAR or IMU, just 2D videos from Ray-Bans, GoPros, and iPhones -- all fused into a 4D reconstruction of my shooting range sessions.
Full pipeline in the video ft. audio-waveform sync, SAM3 masked colmap & pi3 solves, 3D gaussian splats, and gemini as the hit/miss judge.
Chapters:
0:00 Cold Open
0:39 Project IronSight
1:41 Origin Story
2:38 The Command Center
3:55 Inside the Machine — From 2D to 4D
5:54 Training the AI to See
8:18 The Payoff
9:28 Where This Goes
11:42 God's Eye View
I have been iterating on Carveout, my tool for extracting labeled 3D objects from existing Gaussian Splat captures.
Since last week, I have mostly been working on improving detection quality, making the pipeline more autonomous, and allowing for manual input at specific steps when it can improve the results.
The full process now runs from a single command: rendering synthetic views, segmentation, mask lifting, instance grouping, verification, and export.
#GaussianSplatting #3DGS #segmentation
Much debate over Genie vs 3D engines.
You can have both - the control of 3D scene graphs + the creativity of generative ai.
Wrote this in 2024 breaking down the vision. The models are almost there.
Now just imagine if Unreal / Unity productized this.
This will change the way we experience sports forever -- watching the game from a gods eye view.
Arcturus is building 4D gaussian splatting tech that can capture every angle of a sporting event and pushes the bar for volumetric video. I tested this in a headset and it makes 360 and 3D 180 video look ancient.
This puts you closer to the action than any stadium seat, and it’s genuinely mind blowing.
Watching sports from a god’s eye view. I don’t care what people say, this is how I want to experience sports - as full blown 4d gaussian splats or better. Makes 3d videos look ancient after you try this tech. It’s inevitable. Dare I say new media.
Just used claude fable (aka mythos) to create this city block simulator complete with multi-agent traffic, live detection boxes + tracks, and day to night cycle. And it just one shotted it. This is gonna be fun -- the gap between idea and execution just keeps collapsing.