Luís Condados·Sep 22Marigold V2 at four bits: what quantizing a 20-billion-parameter depth model costsOriginally published at https://condados.ai/blog/marigold-v2-quantization-cost
Papers in 100 Lines of Code·Sep 18DUSt3R Made 3D Reconstruction Work Without Camera Poses. MASt3R Made It Accurate.Two unposed images in, dense 3D geometry out: how DUSt3R turned cameras into an output — and MASt3R added precise matching and metric…A response icon1A response icon1
Papers in 100 Lines of Code·Sep 4Depth Anything 3 Just Made VGGT Look OverengineeredA plain DINO transformer with one depth-and-ray prediction target beats VGGT on camera pose and geometry — and can even produce 3D…A response icon1A response icon1
Tanzir Mannan Turzo·Jun 6Introduction to Monocular Depthকোনো কিছু ঠিক ভাবে বুঝতে হলে আমাদের ৩ টা fundamental প্রশ্ন এর উত্তর জানতে হয়
BLED·Apr 8Depth ProIn the last post, we covered how MiDaS and Depth Anything pushed monocular depth estimation forward. But there are other models who pushed…
Agneya Pathare·Mar 2How to Build Monocular Depth Estimation in PythonA Step-by-Step MiDaS v2.1 Tutorial
Papers in 100 Lines of Code·Dec 22, 2025Extracting Depth From Any Pretrained 3DGS (No Retraining Needed)Extract depth maps from any pretrained 3D Gaussian Splatting without retraining, depth loss, or special…
Padmanabh Butala·Nov 6, 2025How Machines See Depth: The Fundamentals of Stereo VisionI remember standing out on the field one day, and a friend tossed a ball directly my way. In the fraction of a second that the ball was in…
Anton Maltsev·Jul 21, 2025Choosing AI Accelerators for Robots: What to KnowHi everyone! I’m Anton, and on my channel, I usually talk about different Edge AI boards. But today, I want to focus specifically on how…
