Learn how to combine a deep learning model for... pose estimation to perform a 3D reconstruction using two cameras 📸show more

hi all, excited to join! i'm building an expressive... mini "shoggoth" robot which will eventually be hooked up to gpt4o realtime voice. i'm currently working on the low-level policies, which are trained in a mujoco simulation with RL. to delay working on raw-pixels for now, i trained a pose-estimation model using deeplabcut and triangulate the position in 3d space using the stereo cameras. eventually, i'll use gpt4o's tool calling capabilities to activate several of these policies (closed and open loop) based on the dialog flow! captions: manual actuation of the tentacle / 3d pose estimation / target designshow more

How can we use test-time compute for spatial understanding?... 🤔 In InterPose, we propose to repeatedly sample generative video models to help two-view pose estimation and reconstruction, by leveraging the video models' keyframe interpolation abilities. A 🧵... (1/8)show more

I've started reading Dungeon Meshi and also been doing... a lot of 2D/3D mixed stuff in Blender recently, so of course I had to combine the two. Had a lot of fun learning how to combine vertex painting with pixel textures for this one. #dungeonmeshi #pixelart #Blender3dshow more

Try new poses and angles! 3D drawing figures are... ideal for when you have a pose in mind but can't find that perfect reference image. Learn how to apply poses and other fun additions like BVH files to your 3D model in this tutorial: #clipstudioshow more

ViTPose -- best open-source pose estimation model just landed... to Hugging Face transformers 🕺🏻💃🏻 See how to use on the next one ⤵️show more

Created a quick VFX to make Wimbledon more green🌱... Using Camera Pose Estimation, body & ball segmentation to incorporate the grass simulation 🙂show more

random model find; might be the best 3D multi-person... pose estimation I have ever seen; it's Apache-2.0 Multi-HMR: Regressing Whole-Body Human Meshes for Multiple Persons in a Single Shot; ECCV2024show more

just two 19$ cameras mounted to a 3d printed... bracket and depth anything v3show more

Ever had a perfect image in mind that a... text-to-image model just couldn't capture? Our new reinforcement learning agent, PASTA, turns image generation into a collaborative conversation, learning your style to bring your vision to life. Learn how it works:show more

Went to a bodybuilding gym, did some legs. Just... need to learn how to pose 🤪 #girlswholift #gymgirls #stronggirlsshow more

Create a 3D model from a single image, set... of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”show more

Recently, I've been working a lot on Gaussian Splatting.... I built a repo for camera pose estimation using Rerun, Gradio, and prefix.dev that merges GLOMAP with hloc! 🧵More info belowshow more

🌿 Introducing pesto~ for Max/MSP! A standalone wrapper for... real-time neural pitch estimation powered by Sony CSL's PESTO deep learning model. Get robust, timbre-agnostic, low-latency (&lt;5ms) pitch tracking with confidence &amp; amplitude outputs in your Max patches.show more

What If Your Warehouse Could Spot a Dangerous Situation... Before a Person Does? That's where computer vision gets really useful. Using YOLO11, cameras can detect and track forklifts, AGVs, workers, pallets and other hazards in real time. It can also use pose estimation to spot unsafe lifting or bending and tracking to monitor how people and vehicles move around each other. You can even combine it with IoT sensors and warehouse systems to react to hazards instead of simply recording them. Occlusion, blind spots, glare and poor lighting can still hurt detection accuracy. That's why good camera placement and sensor fusion matter.show more

Detect worker falls in real time with Ultralytics YOLO26!... 📦 Combine object detection and pose estimation to identify when a person carrying luggage boxes falls, helping logistics teams improve warehouse safety and respond faster to incidents. Get started ➡️ #Ultralytics #YOLO26 #AI #Logistics #WorkplaceSafetyshow more

pretty confident in the model being done now, all... thats left is rigging! learning how to set up a proper foot roll for this modelshow more

A lot of people mistake the frog pose to... dog pose Watch and learnshow more

📢We introduce “RefFusion”, a novel inpainting method for scenes... reconstructed using 3D Gaussian Splatting. 🔗 TLDR: we personalize an image diffusion model to a given reference image and distill its knowledge to 3D through score distillation sampling.show more