Dmytro Mishkin 🇺🇦#1505
Tired of 1B+ parameter VLMs that require massive GPUs and take 1s+ to process an image? Do you miss live demos? Come to the CVPR Meta booth Friday + Saturday 10am-12pm, I'll be giving a new live demo running on a LAPTOP of our egocentric 3DBB demo of our latest work, Boxer
Dmytro Mishkin 🇺🇦#1505Tired of 1B+ parameter VLMs that require massive GPUs and take 1s+ to process an image? Do you miss live demos? Come to the CVPR Meta booth Friday + Saturday 10am-12pm, I'll be giving a new live demo running on a LAPTOP of our egocentric 3DBB demo of our latest work, Boxer
Users praise Meta's lightweight egocentric 3D object detection running on a laptop as really cool, highlighting its promise even while noting needs like specialized sources for broader monocular video pipelines.
FoundationStereo works impressively well on calibrated stereo rigs such as Project Aria: We use it to power the Boxer live demo.
@ddetone Boxer is really cool. Still needs specialized sources. Is it workable to create a pipeline for monocular video, using SLAM and/or DA3 or something, instead of Aria glasses