Tianwei Shen

📢Sonata: Self-Supervised Learning of Reliable Point Representations📢 Meet Sonata, our"3D-DINO" pre-trained with Point Transformer V3, accepted at #CVPR2025! 🌍: xywu.me/sonata 📦: github.com/facebookresear… 🚀: github.com/Pointcept/Poin… 🔹Semantic-aware and spatial reasoning representations learned with no label; 🔹3x linear probing accuracy (from 21.8% to 72.5%) on ScanNet; 🔹2x data efficiency performance with only 1% of the data compared to previous approaches; 🔹As always, establish new SOTA results across indoor and outdoor 3D perception tasks. Our author team: @HengshuangZhao, @jstraub6, @rapideRobot, @ddetone, @NinjaDuncan, @TianweiS, @Christopher_Xie, @NanYang719.

What is the right benchmark for a 3D Egocentric Foundation model? We recently open-sourced a small, high quality egocentric benchmark consisting of 1) 3D surfaces 2) 3D objects. We released a simple 3D CNN baseline model called EVL: projectaria.com/research/efm3d/ Try to beat our model!

📢 Today, our team is excited to announce 𝑺𝒄𝒆𝒏𝒆𝑺𝒄𝒓𝒊𝒑𝒕: an end-to-end method for scene reconstruction from @RealityLabs Research, which enables AI agents to understand and describe 3D spaces. projectaria.com/scenescript /🧵

Interested in 3D object detection and egocentric vision? We open sourced a small yet challenging dataset called Aria Everyday Objects (AEO). We use it as one of the tasks for benchmarking a new class of Egocentric 3D Foundation Models we are working on: arxiv.org/abs/2406.10224

We have launched our interactive web visualizer and sample datasets to the public! Try it here: paralleldomain.com/data-visualize… This data trains better computer vision and perception models, helping our cars, robots, and autonomous systems make our world safer and more efficient.