Introducing ๐ฆ๐ง๐ฟ๐ฒ๐ฎ๐บ๐ฏ๐ฅ, a new 3D geometric foundation model for efficient 3D reconstruction from streaming input. Similar to LLMs, STream3R uses casual attention during training and KVCache at inference.
No need to worry about post-alignment or reconstructing from scratch. You can easily add new frames and update the reconstruction incrementally. Great work by Yushi @GROS17121524 and Yihang @TheYihangLuo !
Project: https://nirvanalan.github.io/projects/stream3r/ arXiv: https://arxiv.org/abs/2508.10893 Code: https://github.com/NIRVANALAN/STream3R
See a streaming reconstruction of our S-Lab lobby below!
์ธ์ฉ ํธ์
Yushi LAN (@GROS17121524)
๐ฅStreaming-based 3D/4D Foundation Model๐ฅ
We present STream3R, which reformulates dense 3D/4D reconstruction into a sequential registration task with causal attention.
- Projects: https://t.co/zrLlvxJ0FJ
- Code: https://t.co/ONYaJDrjhF
- Model: https://t.co/geJmRMSg52