
CC
Claudia Cuttano, Tamy Boubekeur, Elena Garces, Giuseppe Vecchio
· 1 min read
ResearcharXiv cs.CV
RAID: Representation Autoencoder for Intrinsic Decomposition
arXiv:2611.24521v1 Announce Type: new
Abstract: Single-image intrinsic decomposition is an inherently ill-posed problem, requiring the disentanglement of strongly coupled appearance factors from a single RGB observation. Recent methods address this ambiguity with diffusion priors, at the cost of large, iterative, and often stochastic models. We show that accurate decomposition does not require a large generative model. Our key idea is to decouple reconstruction from decomposition on top of a strong pretrained representation. First, an $X \rightarrow X$ teacher learns to reconstruct each intrinsic map from DINOv3 features using a shared decoder, without paired RGB-to-intrinsic supervision. Then, a DINOv3-based student predicts the corresponding teacher representations from RGB through lightweight, modality-specific projections, enabling training on partially annotated datasets and predicting all intrinsics in a single forward pass. \textbf{RAID}, predicts intrinsic properties in the structured latent space, enabling a compact 165M-parameter model, 100x faster than diffusion-based methods. Despite its compact size, it achieves competitive or superior decomposition quality, with improved robustness to input resolution. Additionally, our learned projections yield interpretable, modality-specific feature spaces.
Original source
This story was published by arXiv cs.CV and written by Claudia Cuttano, Tamy Boubekeur, Elena Garces, Giuseppe Vecchio. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


