InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular Depth

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Cho-Ying, Gao, Quankai, Hsu, Chin-Cheng, Wu, Te-Lin, Chen, Jing-Wen, Neumann, Ulrich
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929472976977920
author Wu, Cho-Ying
Gao, Quankai
Hsu, Chin-Cheng
Wu, Te-Lin
Chen, Jing-Wen
Neumann, Ulrich
author_facet Wu, Cho-Ying
Gao, Quankai
Hsu, Chin-Cheng
Wu, Te-Lin
Chen, Jing-Wen
Neumann, Ulrich
contents Indoor monocular depth estimation helps home automation, including robot navigation or AR/VR for surrounding perception. Most previous methods primarily experiment with the NYUv2 Dataset and concentrate on the overall performance in their evaluation. However, their robustness and generalization to diversely unseen types or categories for indoor spaces (spaces types) have yet to be discovered. Researchers may empirically find degraded performance in a released pretrained model on custom data or less-frequent types. This paper studies the common but easily overlooked factor-space type and realizes a model's performance variances across spaces. We present InSpaceType Dataset, a high-quality RGBD dataset for general indoor scenes, and benchmark 13 recent state-of-the-art methods on InSpaceType. Our examination shows that most of them suffer from performance imbalance between head and tailed types, and some top methods are even more severe. The work reveals and analyzes underlying bias in detail for transparency and robustness. We extend the analysis to a total of 4 datasets and discuss the best practice in synthetic data curation for training indoor monocular depth. Further, dataset ablation is conducted to find out the key factor in generalization. This work marks the first in-depth investigation of performance variances across space types and, more importantly, releases useful tools, including datasets and codes, to closely examine your pretrained depth models. Data and code: https://depthcomputation.github.io/DepthPublic/
format Preprint
id arxiv_https___arxiv_org_abs_2408_13708
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular Depth
Wu, Cho-Ying
Gao, Quankai
Hsu, Chin-Cheng
Wu, Te-Lin
Chen, Jing-Wen
Neumann, Ulrich
Computer Vision and Pattern Recognition
Machine Learning
Indoor monocular depth estimation helps home automation, including robot navigation or AR/VR for surrounding perception. Most previous methods primarily experiment with the NYUv2 Dataset and concentrate on the overall performance in their evaluation. However, their robustness and generalization to diversely unseen types or categories for indoor spaces (spaces types) have yet to be discovered. Researchers may empirically find degraded performance in a released pretrained model on custom data or less-frequent types. This paper studies the common but easily overlooked factor-space type and realizes a model's performance variances across spaces. We present InSpaceType Dataset, a high-quality RGBD dataset for general indoor scenes, and benchmark 13 recent state-of-the-art methods on InSpaceType. Our examination shows that most of them suffer from performance imbalance between head and tailed types, and some top methods are even more severe. The work reveals and analyzes underlying bias in detail for transparency and robustness. We extend the analysis to a total of 4 datasets and discuss the best practice in synthetic data curation for training indoor monocular depth. Further, dataset ablation is conducted to find out the key factor in generalization. This work marks the first in-depth investigation of performance variances across space types and, more importantly, releases useful tools, including datasets and codes, to closely examine your pretrained depth models. Data and code: https://depthcomputation.github.io/DepthPublic/
title InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular Depth
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2408.13708