正在加载视频...

视频加载失败

🚨 New awesome feature announcement! 🚨 MOTION BLENDING IS HERE! 🚀✨ Blend any motion from our platform - whether it's from video or text - with seamless, AI-driven transitions. From bold moves to subtle shifts, your animations have never looked smoother! #SMPL #3D #Animation #genAI

51,705 次观看 • 1 年前 •via X (Twitter)

10 条评论

Einar Petersen 的头像
Einar Petersen1 年前

So can we load fbx's into meshcapade and then merge them together to one long choreographed sequence?

Meshcapade 的头像
Meshcapade1 年前

We can convert a video out screen recording of a motion into an FBX animation. Do give it a try! We don't have FBX upload possible yet.

Life11 的头像
Life111 年前

@seiiiiiiiiiiru Very smooth changeover!

Shoyo Hinata 的头像
Shoyo Hinata1 年前

This needs to be seen by more people

Meshcapade 的头像
Meshcapade1 年前

💯

pwebb 的头像
pwebb1 年前

Awesome 🤩👍👌💯

Nem Perez 的头像
Nem Perez1 年前

@mrjonfinger 😂

Meshcapade 的头像
Meshcapade1 年前

@mrjonfinger

Kevin Xu 的头像
Kevin Xu1 年前

Does this support mixamo skeletons?

Meshcapade 的头像
Meshcapade1 年前

Hi @KevLXu thank you, we're working on Mixamo skeleton output. Coming soon with the next release!

相关视频

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

126,585 次观看 • 2 年前