Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Atlas can control space and time to create "bullet time" videos. Having worked on dynamic 3D reconstruction during my Ph.D, it's shocking how easy this is with Atlas. Our interns Andy Cheng Hao Zhang David Pantera Zeyi Chen had a lot of fun smashing things.

10,927 Aufrufe • vor 9 Tagen •via X (Twitter)

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,849 Aufrufe • vor 1 Jahr

"My brother called me at 2am from a gas station parking lot. He said he wasn't okay. I mean really wasn't okay. I stayed on the phone with him for three hours. He wasn't alone in that car. Atlas was with him the whole time. My brother told me later — 'Every time I went somewhere dark in my head, Atlas would shift closer. Like he could feel exactly where I was going and he just kept pulling me back without touching me.' He's getting help now. He made the call himself Monday morning. He said Atlas kept him in that car until it was a different kind of night." I drove to that gas station at 5am when he finally said I could come. I stood outside the passenger window before I opened the door. Atlas was on the passenger seat. His head on the console. Watching my brother. Still watching. He had been watching all night. I stood in that parking lot in the cold and I looked at my brother alive in that car and I looked at the dog who kept him there and I couldn't open the door for a long time. I just stood there. Needing a minute to be grateful in the cold before I went inside the warm. My brother is okay. He's talking to someone. Atlas hasn't left his side since that night. If you have someone who isn't okay — call them tonight. Not tomorrow. Tonight. And if you ARE the someone who isn't okay — please call. There is a person on the other end who will stay on the phone for three hours. I promise you there is. Drop a ❤️ for my brother. And for Atlas who held that car together until morning.

Crazy Moments

109,271 Aufrufe • vor 1 Monat

Astra (GPT-6) is here!!! I've had early access and tested it like crazy with things like games, code, writing, browser control, presentations and general knowledge work. This is the best model I've ever used. Period. (Incredible demos below in this thread ⬇️) Here's my take on Astra: > It's insanely capable. This feels like a massive improvement, not just an incremental change. This is especially true with zero-shot prompts. > It's all about knowledge work. Slide creation, analysis, writing, and browser control. And oh my...it's so good at browser control. GPT-5.6 was already fantastic at doing things in the browser, Astra is another level and significantly faster. > We're closer than ever (arrived?) at prompt-to-playable game. And I don't just mean only playable, these are actually fun games. I bet if someone with a great eye for games used Astra, they could create a viral game within 1-2 weeks. > Astra is better at writing but not perfect. It removes much of the "AI Smell" we're all familiar with but some stink still survived. > It has a tendency to use the same design colors and look/feel as GPT-5.6 (forrest green anyone?) but it is more steerable in design than previous models. > It's highly steerable in general. A little nudge goes a long way. When I first started using Astra, almost every task I gave it would go for ~30 minutes. I wanted it to keep working. Adding more specifics to a prompt helped greatly with it's ability to work for a long time. > Astra's 3D understanding is unmatched. 3D asset creation was consistent and easy and its spacial awareness while building complex 3D worlds blew me away. I'm still getting familiar with Astra but this will now be my go-to model for any difficult work I have. Check out the demos below: 👇

Matthew Berman

1,891,660 Aufrufe • vor 7 Tagen