Decoupling Fine Detail and Global Geometry for Compressed Depth Map Super-Resolution

• URL: http://arxiv.org/abs/2411.03239v1
• Date: Tue, 05 Nov 2024 16:37:30 GMT
• Title: Decoupling Fine Detail and Global Geometry for Compressed Depth Map Super-Resolution
• Authors: Huan Zheng, Wencheng Han, Jianbing Shen,
• Abstract summary: Bit-depth compression produces a uniform depth representation in regions with subtle variations, hindering the recovery of detailed information. densely distributed random noise reduces the accuracy of estimating the global geometric structure of the scene. We propose a novel framework, termed geometry-decoupled network (GDNet), for compressed depth map super-resolution.
• Score: 55.9977636042469
• License:
• Abstract: Recovering high-quality depth maps from compressed sources has gained significant attention due to the limitations of consumer-grade depth cameras and the bandwidth restrictions during data transmission. However, current methods still suffer from two challenges. First, bit-depth compression produces a uniform depth representation in regions with subtle variations, hindering the recovery of detailed information. Second, densely distributed random noise reduces the accuracy of estimating the global geometric structure of the scene. To address these challenges, we propose a novel framework, termed geometry-decoupled network (GDNet), for compressed depth map super-resolution that decouples the high-quality depth map reconstruction process by handling global and detailed geometric features separately. To be specific, we propose the fine geometry detail encoder (FGDE), which is designed to aggregate fine geometry details in high-resolution low-level image features while simultaneously enriching them with complementary information from low-resolution context-level image features. In addition, we develop the global geometry encoder (GGE) that aims at suppressing noise and extracting global geometric information effectively via constructing compact feature representation in a low-rank space. We conduct experiments on multiple benchmark datasets, demonstrating that our GDNet significantly outperforms current methods in terms of geometric consistency and detail recovery. In the ECCV 2024 AIM Compressed Depth Upsampling Challenge, our solution won the 1st place award. Our codes will be available.

Related papers

• PGNeXt: High-Resolution Salient Object Detection via Pyramid Grafting Network [24.54269823691119]
  We present an advanced study on more challenging high-resolution salient object detection (HRSOD) from both dataset and network framework perspectives. To compensate for the lack of HRSOD dataset, we thoughtfully collect a large-scale high resolution salient object detection dataset, called UHRSD. All the images are finely annotated in pixel-level, far exceeding previous low-resolution SOD datasets.
  arXiv  Detail & Related papers  (2024-08-02T09:31:21Z)
• Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolution [52.582632746409665]
  We propose a novel Symmetric Uncertainty-aware Feature Transmission (SUFT) for color-guided DSR. Our method achieves superior performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-01T06:35:59Z)
• Super-Resolving Face Image by Facial Parsing Information [52.1267613768555]
  Face super-resolution is a technology that transforms a low-resolution face image into the corresponding high-resolution one. We build a novel parsing map guided face super-resolution network which extracts the face prior from low-resolution face image. High-resolution features contain more precise spatial information while low-resolution features provide strong contextual information.
  arXiv  Detail & Related papers  (2023-04-06T08:19:03Z)
• ${S}^{2}$Net: Accurate Panorama Depth Estimation on Spherical Surface [4.649656275858966]
  We propose an end-to-end deep network for monocular panorama depth estimation on a unit spherical surface. Specifically, we project the feature maps extracted from equirectangular images onto unit spherical surface sampled by uniformly distributed grids. We propose a global cross-attention-based fusion module to fuse the feature maps from skip connection and enhance the ability to obtain global context.
  arXiv  Detail & Related papers  (2023-01-14T07:39:15Z)
• Learning Continuous Depth Representation via Geometric Spatial Aggregator [47.1698365486215]
  We propose a novel continuous depth representation for depth map super-resolution (DSR) The heart of this representation is our proposed Geometric Spatial Aggregator (GSA), which exploits a distance field modulated by arbitrarily upsampled target gridding. We also present a transformer-style backbone named GeoDSR, which possesses a principled way to construct the functional mapping between local coordinates.
  arXiv  Detail & Related papers  (2022-12-07T07:48:23Z)
• Deep Hierarchical Super-Resolution for Scientific Data Reduction and Visualization [11.095493889344317]
  We present an approach for hierarchical super resolution (SR) using neural networks on an octree data representation. We train a hierarchy of neural networks, each capable of 2x upscaling in each spatial dimension between two levels of detail. We utilize these networks in a hierarchical super resolution algorithm that upscales multiresolution data to a uniform high resolution without introducing seam artifacts on octree node boundaries.
  arXiv  Detail & Related papers  (2021-05-30T18:32:11Z)
• High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal Fusion [84.24973877109181]
  We propose a novel attention-based hierarchical multi-modal fusion network for guided DSR. We show that our approach outperforms state-of-the-art methods in terms of reconstruction accuracy, running speed and memory efficiency.
  arXiv  Detail & Related papers  (2021-04-04T03:28:33Z)
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning [62.52242684874278]
  Cross-modality distribution of spatial and spectral information makes the problem challenging. We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net. Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
  arXiv  Detail & Related papers  (2020-06-18T06:32:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.