SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

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 ba

Read original source ↗ Open in workspace

recordType

paper

region

Global