Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R

ArXi:2605.19539v1 Announce Type: new Geometric foundation models hold promise for unconstrained dense geometry prediction from uncalibrated images. However, in current feed-forward designs, their predicted confidence scores are heuristic, lack probabilistic interpretation, and often fail to indicate where and how much the predicted geometry can be trusted. To address this gap, we present Trust3R, a lightweight evidential uncertainty framework for feed-forward 3D reconstruction.