This is Segment Anything for #GaussianSplatting running on the web... but it comes with a caveat.
This is SplatEdit, a powerful #3DGS editing software built on top of SuperSplat.
Last week, it added a segmentation selection feature powered by Segment Anything, running locally in the browser. Just upload a splat, click on the "mug" icon and select entire objects in the scene.
The problem is that everything after the object is also selected (as you can see in the video).
To fix that, just use the brush tool to subtract the unwanted portion of the scene (hold CTRL while brushing).
I feel we are getting closer and closer to having more editing control on these amazing fuzzy clouds 😉
Watch us land one of our drone-boats inside a moving US Navy warship during RIMPAC. This world-first resupply mission was performed completely autonomously using a Splash Industries Typhoon USV.
JUST IN: 🇩🇰🇺🇸 Danish reporter slammed NATO General Secretary Mark Rutte live on camera:
"You sit next to Donald Trump at moments when he talks about conquering Greenland, talks about lashing out at allies like Spain.
Does this have any affect on your self-respect when you sit there and say nothing?"
High intelligence often comes with heightened pattern recognition. You start noticing social masks, forced conversations, performative friendships, hidden motives, emotional immaturity, and energy that feels draining instead of nourishing. Many highly intelligent people also have more active nervous systems, deeper inner worlds, and lower tolerance for superficial stimulation, so solitude can feel safer than constantly shrinking themselves to fit environments that don’t feel aligned.
See the depth prediction for robot manipulation on the most challenging case: TRANSPARENT objects! A plastic bag pouring beans into glass jars, and the perceived depth stays consistent over time, with clean and sharp BOUNDARIES.
Why is the depth this good? The hero behind the LingBot-Depth 2.0 upgrade is LingBot-Vision, our new self-supervised vision pretraining that makes boundary geometry the learning signal of SSL. The model discovers its own boundary tokens from raw images (no labels, no edge detector, bottom-left panel) and forces exactly those into the mask, so the student must reconstruct boundary geometry from context. Bottom-right: a single frozen-feature query staying locked on the deforming bag.
@pacotabaresmx @TlatoaniAzteca Paco, los hombres débiles y simps como tú que justificáis todas las actitudes de mierda de las mujeres me dais mucho asco, sois patéticos.
@DearS_o_n Transcended into a higher state , locked so deep in the bag , armed to the teeth, laser focused for what is to become and practice deferred gratification.