Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

byebye expensive motion tracking equipment 👋 ai makes motion capturing so easy now! nvidia presented GENMO last week, a new model that can generate and estimate human motion from text, audio, video, and 3D keyframes

73,693 Aufrufe • vor 1 Jahr •via X (Twitter)

10 Kommentare

Profilbild von PowerBeatsVR
PowerBeatsVRvor 3 Jahren

Get ready for a full-body VR workout that’s fun, fast, and intuitive — Play PowerBeatsVR (Now on Meta Quest) 🔥

Profilbild von Paliesk Debesį
Paliesk Debesįvor 1 Jahr

Is it real time? Would love to use something like this for VR chat.

Profilbild von Adrian Werner
Adrian Wernervor 1 Jahr

It's not going to replace expensive motion tracking for high end production because the fidelity is too low. But it is a cool stuff to have for indie studios. It's not anything new, plenty of such systems are already in use, for example inZOI has inhouse one.

Profilbild von NΞXUS STUDIO ⒶI
NΞXUS STUDIO ⒶIvor 1 Jahr

Awesome, is it possible to generate a tracking shot of a car too?

Profilbild von Atiko 💎
Atiko 💎vor 1 Jahr

Wow

Profilbild von BLENDER SUSHI 🫶 X - 24/7 Blenderian
BLENDER SUSHI 🫶 X - 24/7 Blenderianvor 1 Jahr

Fingers typing behind clothes :)

Profilbild von JSFILMZ
JSFILMZvor 1 Jahr

ai mocap been out for like 5 years

Profilbild von WaveSpeedAI
WaveSpeedAIvor 1 Jahr

Cool!

Profilbild von Jorge
Jorgevor 1 Jahr

some people might complain about "le ai is taking le work" but actually you still gotta know dem moves I've seen people doing mocaps at home and moving really weirdly, with like 3000€ equipment

Profilbild von rey
reyvor 1 Jahr

@grok buddy, wt the hell is going on, I thought this wasn't suppose to come till 2030 ,r we in the singularity already 😂

Ähnliche Videos

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,635 Aufrufe • vor 2 Jahren