ICLR 2026 Paper TTT3R: Enhancing 3D Reconstruction via Test-Time Training

rsasaki0109 · x · 2026-07-31

The ICLR 2026 paper project TTT3R (3D Reconstruction as Test-Time Training) is now open-source.

The method proposes a simple state update rule to enhance the length generalization of the CUT3R model when handling varying input lengths. By treating 3D reconstruction as a test-time training process, the model can dynamically adjust during inference, achieving better performance in 3D reconstruction tasks.

Related event: TTT3R: Enhancing 3D Reconstruction via Test-Time Training(2 posts)→

Original post →

More from Research

Research channel →