3D Gaussian splatting relies on depth-sorting of splats, which is costly and prone to artifacts (e.g., "popping"). In our latest work, "StochasticSplats", we replace sorted alpha blending by stochastic transparency, an unbiased Monte Carlo estimator from the real-time rendering literature.

Make sure to check out Thomas' 3DV paper Gaussians-to-Life. He investigated how video diffusion models can be used to animate arbitrary scenes and make them come to life!

Thomas Wimmer@wimmerthomas.bsky.social · last yr.

Had the honor to present "Gaussians-to-Life" at #3DV2025 yesterday. In this work, we used video diffusion models to animate arbitrary 3D Gaussian Splatting scenes. This work was a great collaboration with @moechsle.bsky.social, @miniemeyer.bsky.social, and Federico Tombari. 🧵⬇️

On my way back from 3DV in Singapore. What a blast! Thanks to all the organizers of this year's @3dvconf.bsky.social as well as all the speakers and presenters, I had such a fantastic time!

Keynote2: Reconstructing Everything By Noah Snavely (@snavely.bsky.social ) from Cornell Tech & Google Deepmind Noah Snavely: cs.cornell.edu/~snavely/

Make sure to check out Stan's new work on fast 3D scene generation! Very impressive results, congrats to the entire team.

Jon Barron@jonbarron.bsky.social · last yr.

Here's Bolt3D: fast feed-forward 3D generation from one or many input images. Diffusion means that generated scenes contain lots of interesting structure in unobserved regions. ~6 seconds to generate, renders in real time. Project page: szymanowiczs.github.io/bolt3d Arxiv: arxiv.org/abs/2503.14445

Exciting news! MegaSAM code is out🔥 & the updated Shape of Motion results with MegaSAM are really impressive! A year ago I didn't think we could make any progress on these videos: shape-of-motion.github.io/results.html Huge congrats to everyone involved and the community 🎉

As someone who has reported on AI for 7 years and covered China tech as well, I think the biggest lesson to be drawn from DeepSeek is the huge cracks it illustrates with the current dominant paradigm of AI development. A long thread. 1/

Don't miss your chance to register for ELLIS Unit Amsterdam's Winter School on #AI #FoundationModels. The deadline is Jan 26. More info: ivi.fnwi.uva.nl/ellis/events...

GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting Andrew Bond, Jui-Hsien Wang, Long Mai, Erkut Erdem, @aykuterdem.bsky.social tl;dr: 3DGS+B-spline-based motion+Neural ODE-driven camera modeling+spatio-temporal hierarchical learning arxiv.org/abs/2501.04782

For other 3D vision newcomers to blue sky: I highly recommend joning @chrisoffner3d.bsky.social 's list to follow the right people ;): go.bsky.app/Cfm9XFe

I have switched from X and Facebook to Bluesky. I will delete both my X and Facebook accounts in a little bit.

hey everyone - I am now also active here and excited about computer vision and machine learning stuff. 🎉