# Sim(3)-TurboReg: Robust and Efficient Scale-Aware Registration via Tri-Scale Consistency

**Authors:** Zijun Zhou, Shaocheng Yan, Zhenjun Zhao, Yutong Hu, Ke Yang, Yingdong Gu, Pengcheng Shi, Jiayuan Li  
**Published:** 10 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.14135) · [PDF](https://arxiv.org/pdf/2611.14135) · [Code](https://github.com/ivan-zzj/Sim3-TurboReg) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.14135.html)

## Key numbers

- **90%**: On controlled unknown-scale registration at 90% outliers
- **92.5%**: ours matches RANSAC accuracy with 92.5% lower median latency
- **22.2%**: ours improves mean ATE RMSE by 22.2% and reduces mean end-to-end time by 16.6%

## Abstract

Feed-forward 3D foundation models recover geometry at high fidelity, yet inference memory constraints keep them from processing long sequences natively. Current streaming systems work around this limit with sliding-window chunking, which introduces severe monocular scale ambiguity. Resolving this ambiguity requires Sim(3) registration that stays accurate and efficient under outlier contamination. We introduce Sim(3)-TurboReg, which reformulates the compatibility graph construction of TurboReg by replacing absolute distance constraints with a strict Tri-Scale Consistency (TSC) criterion. Our analysis shows that TSC suppresses both mismatching and coordinate-distortion outliers. We integrate the resulting solver into existing streaming systems and obtain high-fidelity, kilometer-scale reconstruction for feed-forward models. On controlled unknown-scale registration at 90% outliers, ours matches RANSAC accuracy with 92.5% lower median latency. In DA3-Streaming on KITTI, ours improves mean ATE RMSE by 22.2% and reduces mean end-to-end time by 16.6%. Code: https://github.com/ivan-zzj/Sim3-TurboReg

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.