Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bae, Gwangbin, Davison, Andrew J.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.00712
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910349695909888
author Bae, Gwangbin
Davison, Andrew J.
author_facet Bae, Gwangbin
Davison, Andrew J.
contents Despite the growing demand for accurate surface normal estimation models, existing methods use general-purpose dense prediction models, adopting the same inductive biases as other tasks. In this paper, we discuss the inductive biases needed for surface normal estimation and propose to (1) utilize the per-pixel ray direction and (2) encode the relationship between neighboring surface normals by learning their relative rotation. The proposed method can generate crisp - yet, piecewise smooth - predictions for challenging in-the-wild images of arbitrary resolution and aspect ratio. Compared to a recent ViT-based state-of-the-art model, our method shows a stronger generalization ability, despite being trained on an orders of magnitude smaller dataset. The code is available at https://github.com/baegwangbin/DSINE.
format Preprint
id arxiv_https___arxiv_org_abs_2403_00712
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rethinking Inductive Biases for Surface Normal Estimation
Bae, Gwangbin
Davison, Andrew J.
Computer Vision and Pattern Recognition
Despite the growing demand for accurate surface normal estimation models, existing methods use general-purpose dense prediction models, adopting the same inductive biases as other tasks. In this paper, we discuss the inductive biases needed for surface normal estimation and propose to (1) utilize the per-pixel ray direction and (2) encode the relationship between neighboring surface normals by learning their relative rotation. The proposed method can generate crisp - yet, piecewise smooth - predictions for challenging in-the-wild images of arbitrary resolution and aspect ratio. Compared to a recent ViT-based state-of-the-art model, our method shows a stronger generalization ability, despite being trained on an orders of magnitude smaller dataset. The code is available at https://github.com/baegwangbin/DSINE.
title Rethinking Inductive Biases for Surface Normal Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.00712