It is 2026, we’ve basically solved AGI and conference wifi is still slower than dial up internet
Daniel DeTone
@ddetone
Deep Nets and Geometry — what could go wrong?
Long Beach, CA
Joined June 2009
- Giving two silent disco 🪩 style talks at the Meta booth today: @ 1:30pm Boxer -- lifting open world 2DBBs to 3D @ 4:30pm NymeriaPlus -- adding new annotations to Nymeria egocentric dataset Grab a headset and tune in 🕺💃 #CVPR2026
- 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
- The biggest impact of the Segment Anything line of work was not the actual image segmentation, but rather the flood of paper titles with the name “Any” in them. Cmon folks, let’s just call this generalization and move on!!
- New blog post about Boxer is live on the Project Aria websiteHow do you decompose a 2D image into accurate 3D object detections? You use🥊Boxer. A new model from Reality Labs Research enables robust 3D object detection by "lifting" 2D proposals from off-the-shelf detectors like OWL-ViT and SAM into metric 3D space. No more "flat"
