Intrinsic Image Decomposition Using Point Cloud Representation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xing, Xiaoyan, Groh, Konrad, Karaoglu, Sezer, Gevers, Theo
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910387308331008
author Xing, Xiaoyan
Groh, Konrad
Karaoglu, Sezer
Gevers, Theo
author_facet Xing, Xiaoyan
Groh, Konrad
Karaoglu, Sezer
Gevers, Theo
contents The purpose of intrinsic decomposition is to separate an image into its albedo (reflective properties) and shading components (illumination properties). This is challenging because it's an ill-posed problem. Conventional approaches primarily concentrate on 2D imagery and fail to fully exploit the capabilities of 3D data representation. 3D point clouds offer a more comprehensive format for representing scenes, as they combine geometric and color information effectively. To this end, in this paper, we introduce Point Intrinsic Net (PoInt-Net), which leverages 3D point cloud data to concurrently estimate albedo and shading maps. The merits of PoInt-Net include the following aspects. First, the model is efficient, achieving consistent performance across point clouds of any size with training only required on small-scale point clouds. Second, it exhibits remarkable robustness; even when trained exclusively on datasets comprising individual objects, PoInt-Net demonstrates strong generalization to unseen objects and scenes. Third, it delivers superior accuracy over conventional 2D approaches, demonstrating enhanced performance across various metrics on different datasets. (Code Released)
format Preprint
id arxiv_https___arxiv_org_abs_2307_10924
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Intrinsic Image Decomposition Using Point Cloud Representation
Xing, Xiaoyan
Groh, Konrad
Karaoglu, Sezer
Gevers, Theo
Computer Vision and Pattern Recognition
The purpose of intrinsic decomposition is to separate an image into its albedo (reflective properties) and shading components (illumination properties). This is challenging because it's an ill-posed problem. Conventional approaches primarily concentrate on 2D imagery and fail to fully exploit the capabilities of 3D data representation. 3D point clouds offer a more comprehensive format for representing scenes, as they combine geometric and color information effectively. To this end, in this paper, we introduce Point Intrinsic Net (PoInt-Net), which leverages 3D point cloud data to concurrently estimate albedo and shading maps. The merits of PoInt-Net include the following aspects. First, the model is efficient, achieving consistent performance across point clouds of any size with training only required on small-scale point clouds. Second, it exhibits remarkable robustness; even when trained exclusively on datasets comprising individual objects, PoInt-Net demonstrates strong generalization to unseen objects and scenes. Third, it delivers superior accuracy over conventional 2D approaches, demonstrating enhanced performance across various metrics on different datasets. (Code Released)
title Intrinsic Image Decomposition Using Point Cloud Representation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.10924