正在加载视频...
视频加载失败
Check out Daoyi Gao's DiffCAD - introducing probabilistic CAD retrieval and alignment to an RGB image. We captures ambiguities in depth/scale, inexact CAD matches, and don't require any training on real data!
15,580 次观看 • 2 年前 •via X (Twitter)
1 条评论

Angela Dai2 年前
We formulate a conditional generative task, leveraging diffusion to learn implicit probabilistic models CAD shape and pose in an image. This enables multi-hypothesis CAD reconstructions from only synthetic training. Great work by @DaoyiGao with @david_roz_, @StefanLeuteneg1
相关视频
0:29
Sensitive content
What if your CAD tool could understand you? User: “Can you design a clamping device that's 30mm long and 20mm high?” CADAI Assistant: “Got it. Here’s the model.” ⚙️ Runs inside SolidWorks 📐 Trained on your own CAD data ⚡️ Real-time design generation Watch it happen
CADAICO
13,618 次观看 • 1 年前

