SOURCE-LINKED INTELLIGENCE

Albedo Estimation via Latent Bridge Matching

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Recent advances in Intrinsic Image Decomposition (IID) have increasingly relied on generative models. However, progress remains limited by three key challenges: (a) insufficient physical consistency, (b) high computational cost at inference time, and (c) limited generalization capabilities. In this work, we show that latent bridge matching (LBM) effectively addresses these limitations for albedo estimation. We introduce a novel LBM-based architecture that enforces physical consistency through a pixel reconstruction loss, benefits from the inherent efficiency of LBM low-cost inference, and impr

Read original source ↗ Open in workspace

recordType

paper

region

Global