Depth map dynamic restoration method integrating quality perception

By integrating quality perception and dynamic repair technologies in depth map repair, depth map repair is used to use the reference residual network, and feature enhancement is combined with depth clues, the impact of depth map quality on information fusion is solved, and the quality of information fusion and generalization of feature enhancement is improved.

CN119693279AActive Publication Date: 2025-03-25TIANJIN UNIV
7 Cites 0 Cited by

Patent Information

Application Number
CN202411782439.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-05
Publication Date
2025-03-25
Estimated Expiration
2044-12-05

AI Technical Summary

Technical Problem

The prior art fails to effectively consider the depth map quality during the process of depth map repair and multimodal information fusion, resulting in the loss of geometric information in part of the space, affecting the quality of information fusion. The local feature enhancement algorithm lacks dynamic response to the depth map quality, resulting in insufficient generalization and robustness.

Method used

The dynamic repair method of depth maps with integrated quality perception is adopted, and a dynamic depth enhancement module is constructed using the reference residual network, dynamic repair is performed based on the quality score of the original depth map, and feature enhancement is performed by combining depth clues as masks.

Benefits of technology

By dynamically repairing the depth map, the spatial and geometric information of the original depth map is retained, the quality of multimodal information fusion is improved, and the generalization and robustness of local feature enhancement is enhanced.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a depth map dynamic restoration method integrated with quality perception. The method comprises the following steps: S1, generating an RGB prompt graph of an RGB image; s2, constructing a depth map quality perception algorithm model; s3, constructing a dynamic depth enhancement module by using a reference residual network, and carrying out dynamic depth image restoration according to the RGB prompt image Sh generated in the S1 and the original depth image quality score gp generated in the S2 to generate a restored depth image Dr; and S4, dynamically generating depth cues m1, m2, m3,..., mn according to the quality score gp of the original depth image in the step S2 and the repaired depth image Dr in the step S3, taking the depth cues as masks, and performing element multiplication with features output by the RGB image and the depth image through the feature extraction network or a feature image after multi-modal fusion, thereby realizing suppression and enhancement of the features by using the depth cues. According to the invention, the local feature enhancement of the algorithm when the quality of the depth map is uneven is realized, and the generalization and robustness of the RGB-D algorithm are enhanced.
Need to check novelty before this filing date? Find Prior Art