Test3R, a test-time learning technique for 3D reconstruction, enhances geometric accuracy by optimizing network consistency using self-supervised learning on image triplets.
Dense matching methods like DUSt3R regress pairwise pointmaps for 3D
reconstruction. However, the reliance on pairwise prediction and the limited
generalization capability inherently restrict the global geometric consistency.
In this work, we introduce Test3R, a surprisingly simple test-time learning
technique that significantly boosts geometric accuracy. Using image triplets
(I_1,I_2,I_3), Test3R generates reconstructions from pairs (I_1,I_2) and
(I_1,I_3). The core idea is to optimize the network at test time via a
self-supervised objective: maximizing the geometric consistency between these
two reconstructions relative to the common image I_1. This ensures the model
produces cross-pair consistent outputs, regardless of the inputs. Extensive
experiments demonstrate that our technique significantly outperforms previous
state-of-the-art methods on the 3D reconstruction and multi-view depth
estimation tasks. Moreover, it is universally applicable and nearly cost-free,
making it easily applied to other models and implemented with minimal test-time
training overhead and parameter footprint. Code is available at
https://github.com/nopQAQ/Test3R.
