Loading video...

Video Failed to Load

Go Home

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!

angelaqdai's profile picture

Angela Dai

9,561 subscribers

15,586 views • 2 years ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

1 Comments

Angela Dai's profile picture
Angela Dai2 years ago

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

Related Videos

Testing image-to-CAD for SR Platform on a new set of GPUs 🔥 We are working with lium.io (SN51) to showcase the efficiency of decentralized compute for SR Platform — from CAD generation to RL training and sim-to-real validation What it means: > Flexible, on-demand rental for us. Pay with crypto. > Diverse GPU options, powered by Openτensor Foundaτion's incentive alignment. > Lower equipment cost → higher margin for the network. Onchain robots, onchain compute.
0:25

Testing image-to-CAD for SR Platform on a new set of GPUs 🔥 We are working with lium.io (SN51) to showcase the efficiency of decentralized compute for SR Platform — from CAD generation to RL training and sim-to-real validation What it means: > Flexible, on-demand rental for us. Pay with crypto. > Diverse GPU options, powered by Openτensor Foundaτion's incentive alignment. > Lower equipment cost → higher margin for the network. Onchain robots, onchain compute.

Strike Robot

18,134 views • 1 month ago

Generate an image of a product with ChatGPT Images 2.0 and convert to CAD with GPT-5.5 in Codex with ForgeCAD
0:30

Generate an image of a product with ChatGPT Images 2.0 and convert to CAD with GPT-5.5 in Codex with ForgeCAD

Ruben Kostandyan

244,833 views • 1 month ago

Something I'm working on Compressible flow solver for muzzle devices Take any random silencer CAD and check its muzzle gas dynamics
0:39

Something I'm working on Compressible flow solver for muzzle devices Take any random silencer CAD and check its muzzle gas dynamics

PoptartNoahh

115,146 views • 3 months ago

Introducing Modality Forcing, a recipe for post-training T2I models for SOTA RGB-Depth generation! Text-to-image (T2I) models learn rich representations of the spatial world. How do we build on this prior for high-quality depth generation? 🧵 [1/6]
0:25

Introducing Modality Forcing, a recipe for post-training T2I models for SOTA RGB-Depth generation! Text-to-image (T2I) models learn rich representations of the spatial world. How do we build on this prior for high-quality depth generation? 🧵 [1/6]

Bardienus Duisterhof

64,240 views • 27 days ago

Introducing Adam: The Future of CAD
0:53

Introducing Adam: The Future of CAD

Zach Dive

2,798,915 views • 1 year ago

Introducing Agentic Object Detection! Given a text prompt like “unripe strawberries” or “Kellogg’s branded cereal” and an image, we use an agentic workflow to reason at length and detect the specified objects. No need to label any training data. Watch the video for details.
2:09

Introducing Agentic Object Detection! Given a text prompt like “unripe strawberries” or “Kellogg’s branded cereal” and an image, we use an agentic workflow to reason at length and detect the specified objects. No need to label any training data. Watch the video for details.

Andrew Ng

397,780 views • 1 year ago

Here's a Problem: CAD SUCKS - High barrier of Education - Even higher barrier to cost So, my team and I in Gauntlet AI S25 built a Text-to-CAD tool with AI-First principles called MOORPH in the last 24 hours. Check it out.
4:15

Here's a Problem: CAD SUCKS - High barrier of Education - Even higher barrier to cost So, my team and I in Gauntlet AI S25 built a Text-to-CAD tool with AI-First principles called MOORPH in the last 24 hours. Check it out.

Patrick Skinner

22,849 views • 1 year ago

Introducing CAD Drawing generation with Background agents.
1:54

Introducing CAD Drawing generation with Background agents.

MecAgent

16,909 views • 20 days ago

Nano Banana 2, new state of the art in image generation and editing combined with Gemini’s real-world knowledge! You can simulate 3D CAD models purely through images. From sketch to real object!
0:22

Nano Banana 2, new state of the art in image generation and editing combined with Gemini’s real-world knowledge! You can simulate 3D CAD models purely through images. From sketch to real object!

koray kavukcuoglu

85,619 views • 4 months ago

I built a manufacturing-aware CAD interpretation engine that uses LLMs to query any step model's geometric data, saving $10k/Yr on analysis software. This web-based CAD analysis tool is a workbench for developing bespoke DFM tools for manufacturing services.
1:48

I built a manufacturing-aware CAD interpretation engine that uses LLMs to query any step model's geometric data, saving $10k/Yr on analysis software. This web-based CAD analysis tool is a workbench for developing bespoke DFM tools for manufacturing services.

Connor Kapoor

50,631 views • 6 months ago

Attach images and other files to Zookeeper with our 1.1.12 release. Enables functionality like Image-to-CAD, generating a full feature tree.
0:36

Attach images and other files to Zookeeper with our 1.1.12 release. Enables functionality like Image-to-CAD, generating a full feature tree.

Zoo

116,131 views • 4 months ago

New demo: collaborative AI CAD in the browser 🚀 Built with Electric + Durable Streams + TANSTACK DB+AI+Start - ElectricSQL + DB: data sync - Durable Streams: presence + AI + CAD (Yjs!) sync - TanStack AI: AI for cad modelling 🤯 - Coded with Cursor
0:30

New demo: collaborative AI CAD in the browser 🚀 Built with Electric + Durable Streams + TANSTACK DB+AI+Start - ElectricSQL + DB: data sync - Durable Streams: presence + AI + CAD (Yjs!) sync - TanStack AI: AI for cad modelling 🤯 - Coded with Cursor

Sam Willis

155,378 views • 6 months ago

I built an interactive tool to map the relationships in CAD modeling software, their underlying geometry kernels, and the companies that own them. try it out at
0:30

I built an interactive tool to map the relationships in CAD modeling software, their underlying geometry kernels, and the companies that own them. try it out at

Connor Kapoor

27,798 views • 4 months ago

A new way to watch Wimbledon! 😍 Introducing Signals, combining real-time data, fan interaction and insight. Check out the trial:
1:28

A new way to watch Wimbledon! 😍 Introducing Signals, combining real-time data, fan interaction and insight. Check out the trial:

BBC Sport

46,821 views • 1 day ago

Gauntlet AI drive-by! 8 hours of progress so far. Building in-browser CAD generation and UX for manipulation of CAD renderings. A full Cursor for CAD. MVP up and running, a lot of improvement from here. Excited to see what this will look like at the end of the week.
8:37

Gauntlet AI drive-by! 8 hours of progress so far. Building in-browser CAD generation and UX for manipulation of CAD renderings. A full Cursor for CAD. MVP up and running, a lot of improvement from here. Excited to see what this will look like at the end of the week.

Austen Allred

14,386 views • 1 year ago

We need to infuse the timeline with more CAD propaganda
0:24

We need to infuse the timeline with more CAD propaganda

wavefnx

2,807,218 views • 1 year ago

See Asajj Ventress and Cad Bane in Tales of the Underworld, available May 4 on Disney+.
0:33

See Asajj Ventress and Cad Bane in Tales of the Underworld, available May 4 on Disney+.

Star Wars

199,715 views • 1 year ago

🚨Product Update We have tested the new capabilities of the #CADAI Assistant in modifying complex CAD parts and assemblies, particularly those frequently used by our customers. Furthermore, in response to requests from our partners, we are testing features that will enable the CADAI assistant to find CAD models in the customer's database based on the context and semantics of search queries. 🤖
1:03

🚨Product Update We have tested the new capabilities of the #CADAI Assistant in modifying complex CAD parts and assemblies, particularly those frequently used by our customers. Furthermore, in response to requests from our partners, we are testing features that will enable the CADAI assistant to find CAD models in the customer's database based on the context and semantics of search queries. 🤖

CADAICO

14,365 views • 2 years ago

Very excited to share our first public release after I joined Robbyant! We present Lingbot-Depth 👀 — a state-of-the-art depth foundation model trained with RGB-D MAE on millions of real & simulated RGBD pairs. 🔹 Camera depths as natural masks for RGB-D MAE modeling 🔹 Large-scale real + sim RGBD data curation pipeline What surprised us most: ✨ Significant improvement on transparent, reflective surfaces, and thin structures — traditionally the hardest cases for depth models. 👇These are some of hard causal-capture images we tested on. The results are pretty good! #DepthEstimation #FoundationModels #EmbodiedAI #3DVision #Robotics #RobbyAnt
0:34

Very excited to share our first public release after I joined Robbyant! We present Lingbot-Depth 👀 — a state-of-the-art depth foundation model trained with RGB-D MAE on millions of real & simulated RGBD pairs. 🔹 Camera depths as natural masks for RGB-D MAE modeling 🔹 Large-scale real + sim RGBD data curation pipeline What surprised us most: ✨ Significant improvement on transparent, reflective surfaces, and thin structures — traditionally the hardest cases for depth models. 👇These are some of hard causal-capture images we tested on. The results are pretty good! #DepthEstimation #FoundationModels #EmbodiedAI #3DVision #Robotics #RobbyAnt

Yinghao Xu

22,574 views • 5 months ago