Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Zhiqiang, Wang, Zhengxue, Wang, Kun, Li, Jun, Yang, Jian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915185898291200
author Yan, Zhiqiang
Wang, Zhengxue
Wang, Kun
Li, Jun
Yang, Jian
author_facet Yan, Zhiqiang
Wang, Zhengxue
Wang, Kun
Li, Jun
Yang, Jian
contents In this paper, we introduce the Selective Image Guided Network (SigNet), a novel degradation-aware framework that transforms depth completion into depth enhancement for the first time. Moving beyond direct completion using convolutional neural networks (CNNs), SigNet initially densifies sparse depth data through non-CNN densification tools to obtain coarse yet dense depth. This approach eliminates the mismatch and ambiguity caused by direct convolution over irregularly sampled sparse data. Subsequently, SigNet redefines completion as enhancement, establishing a self-supervised degradation bridge between the coarse depth and the targeted dense depth for effective RGB-D fusion. To achieve this, SigNet leverages the implicit degradation to adaptively select high-frequency components (e.g., edges) of RGB data to compensate for the coarse depth. This degradation is further integrated into a multi-modal conditional Mamba, dynamically generating the state parameters to enable efficient global high-frequency information interaction. We conduct extensive experiments on the NYUv2, DIML, SUN RGBD, and TOFDC datasets, demonstrating the state-of-the-art (SOTA) performance of SigNet.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19225
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion
Yan, Zhiqiang
Wang, Zhengxue
Wang, Kun
Li, Jun
Yang, Jian
Computer Vision and Pattern Recognition
Image and Video Processing
In this paper, we introduce the Selective Image Guided Network (SigNet), a novel degradation-aware framework that transforms depth completion into depth enhancement for the first time. Moving beyond direct completion using convolutional neural networks (CNNs), SigNet initially densifies sparse depth data through non-CNN densification tools to obtain coarse yet dense depth. This approach eliminates the mismatch and ambiguity caused by direct convolution over irregularly sampled sparse data. Subsequently, SigNet redefines completion as enhancement, establishing a self-supervised degradation bridge between the coarse depth and the targeted dense depth for effective RGB-D fusion. To achieve this, SigNet leverages the implicit degradation to adaptively select high-frequency components (e.g., edges) of RGB data to compensate for the coarse depth. This degradation is further integrated into a multi-modal conditional Mamba, dynamically generating the state parameters to enable efficient global high-frequency information interaction. We conduct extensive experiments on the NYUv2, DIML, SUN RGBD, and TOFDC datasets, demonstrating the state-of-the-art (SOTA) performance of SigNet.
title Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2412.19225