our new model Atlas also happens to be a capable text-to-image generator, providing it with a strong…
@BenMildenhall1.2万 位关注者
105,205 次观看
36 条评论
评论来自 X (Twitter) 上的原帖

@keenanisalive
Question purely out of curiosity: can you recover an explicit 3D representation (say, a textured mesh) from Atlas, such that renderings of the explicit representation closely reproduce the video (say, for example “hard surface” models and relatively simple materials)? This kind of question often gets side stepped (e.g., “meshes are old news”), but for me it’s a scientific question rather than an application question: what information is the model predicting, and which variables are still underdetermined?
61 个赞

@trq212
Incredible, congrats Ben!
15 个赞

@mazeyar
Can you let me play GTA VI in Atlas 😌🙏🏼
8 个赞

@BenMildenhall
yes
53 个赞

@mazeyar
Hahaha thanks 🤣

@mtizard
Incredible work. If I have a variety of viewpoints of the same scene, can Atlas ingest all that ground truth and use it to synthesise the missing perspectives? Would this work with synchronised video frames too?
7 个赞

@BenMildenhall
exactly!
4 个赞

@peterom
Beautiful style adherence! The fabric on the octopus is amazing
4 个赞

@boneGPT
very cool, can you show it doing a couple 360s? would like to see if it keeps persistence
4 个赞

@XRarchitect
this one 🫠 so good
2 个赞

@NicholasBardy
nice work
1 个赞

@tkexpress11
Sick
1 个赞

@XGEN_labs
The move from image generation to controllable 3D worlds is especially exciting. Curious how far this kind of world knowledge can generalize across unseen environments and viewpoints.
1 个赞

@Dusanwriter
I was waiting for this. Marble etc were awesome but I can't wait to experiment. Working on history projects (London UK, really top people) and we have such deep ideas but needed something like Atlas to get us there. Storytelling has a new tool kit and you guys rocking it. EPIC
1 个赞

@yuceli
Very impressive. I wonder if one day, AI would read a novel and produce a cinematic version of it.
1 个赞

@itsnicholash
wow that 2D japanese scene though
1 个赞

@ritwik_raha
Takes one back to NeRF days

@AmaraWolfeeb
Claiming Atlas has 'world knowledge' from 2D text-to-image training is a massive stretch. How does it handle actual physical consistency and occlusion when you try to navigate those stylized scenes?

@IDGAFACCP
That world knowledge foundation generalizing across views is clever.

@outofcosmos
wf















