Info3R: Information-Adaptive Test-Time Training for 3D Reconstruction

2026-09-18

AI Summary

本文提出Info3R方法，通过信息自适应的测试时训练解决长图像流中3D重建的问题，提高了模型处理新信息的能力和长期序列评估的性能。

Abstract

Transformer-based models have recently achieved strong performance on 3D reconstruction from images, and recent works extend them to process video streams in an online manner for real-world deployment. However, existing methods overlook two key signals when handling long image streams: the importance of each incoming frame and the information saturation of the model's internal state. In this paper, we propose Info3R, a novel information-adaptive test-time training method for the online 3D reconstruction. We introduce an information-aware state update that modulates the state update strength based on the redundancy and informativeness of each incoming frame. To restore the state's plasticity -- its capacity to incorporate new observations -- we propose a dynamic state reset, triggered by the cumulative magnitude of state updates and the model's prediction confidence and accompanied by an anchor-to-world alignment. Our method achieves consistent improvements on camera pose estimation, video depth estimation, and 3D reconstruction, while substantially mitigating the performance degradation in the long sequence evaluation. Notably, on KITTI Odometry, our method achieves on average 1.68x lower ATE than LongStream, demonstrating its robustness on extended outdoor sequences.

Problem

• 3D Reconstruction
• Test-Time Training
• Information-Adaptive
• Long Image Streams
• State Update

Innovation

• information-adaptive test-time training
• information-aware state update
• dynamic state reset