SparseDC: Depth Completion from sparse and non-uniform inputs

• URL: http://arxiv.org/abs/2312.00097v1
• Date: Thu, 30 Nov 2023 13:36:27 GMT
• Title: SparseDC: Depth Completion from sparse and non-uniform inputs
• Authors: Chen Long, Wenxiao Zhang, Zhe Chen, Haiping Wang, Yuan Liu, Zhen Cao, Zhen Dong, Bisheng Yang
• Abstract summary: We propose SparseDC, a model for Depth Completion of Sparse and non-uniform depth inputs. The key contributions of SparseDC are two-fold. First, we design a simple strategy, called SFFM, to improve the robustness under sparse input. Second, we propose a two-branch feature embedder to predict both the precise local geometry of regions with available depth values and accurate structures in regions with no depth.
• Score: 18.20396821395775
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose SparseDC, a model for Depth Completion of Sparse and non-uniform depth inputs. Unlike previous methods focusing on completing fixed distributions on benchmark datasets (e.g., NYU with 500 points, KITTI with 64 lines), SparseDC is specifically designed to handle depth maps with poor quality in real usage. The key contributions of SparseDC are two-fold. First, we design a simple strategy, called SFFM, to improve the robustness under sparse input by explicitly filling the unstable depth features with stable image features. Second, we propose a two-branch feature embedder to predict both the precise local geometry of regions with available depth values and accurate structures in regions with no depth. The key of the embedder is an uncertainty-based fusion module called UFFM to balance the local and long-term information extracted by CNNs and ViTs. Extensive indoor and outdoor experiments demonstrate the robustness of our framework when facing sparse and non-uniform input depths. The pre-trained model and code are available at https://github.com/WHU-USI3DV/SparseDC.

Related papers

• DepthLab: From Partial to Complete [80.58276388743306]
  Missing values remain a common challenge for depth data across its wide range of applications. This work bridges this gap with DepthLab, a foundation depth inpainting model powered by image diffusion priors. Our approach proves its worth in various downstream tasks, including 3D scene inpainting, text-to-3D scene generation, sparse-view reconstruction with DUST3R, and LiDAR depth completion.
  arXiv  Detail & Related papers  (2024-12-24T04:16:38Z)
• Self-supervised Monocular Depth Estimation with Large Kernel Attention [30.44895226042849]
  We propose a self-supervised monocular depth estimation network to get finer details. Specifically, we propose a decoder based on large kernel attention, which can model long-distance dependencies. Our method achieves competitive results on the KITTI dataset.
  arXiv  Detail & Related papers  (2024-09-26T14:44:41Z)
• HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors [10.88048563201236]
  We propose HYBRIDDEPTH, a robust depth estimation pipeline that addresses key challenges in depth estimation. HYBRIDDEPTH leverages focal stack, data conveniently accessible in common mobile devices, to produce accurate metric depth maps. Comprehensive quantitative and qualitative analyses demonstrate that HYBRIDDEPTH outperforms state-of-the-art(SOTA) models.
  arXiv  Detail & Related papers  (2024-07-26T00:51:52Z)
• Metrically Scaled Monocular Depth Estimation through Sparse Priors for Underwater Robots [0.0]
  We formulate a deep learning model that fuses sparse depth measurements from triangulated features to improve the depth predictions. The network is trained in a supervised fashion on the forward-looking underwater dataset, FLSea. The method achieves real-time performance, running at 160 FPS on a laptop GPU and 7 FPS on a single CPU core.
  arXiv  Detail & Related papers  (2023-10-25T16:32:31Z)
• Revisiting Deformable Convolution for Depth Completion [40.45231083385708]
  Depth completion aims to generate high-quality dense depth maps from sparse depth maps. Previous work usually employs RGB images as guidance, and introduces iterative spatial propagation to refine estimated coarse depth maps. We propose an effective architecture that leverages deformable kernel convolution as a single-pass refinement module.
  arXiv  Detail & Related papers  (2023-08-03T17:59:06Z)
• Focal Sparse Convolutional Networks for 3D Object Detection [121.45950754511021]
  We introduce two new modules to enhance the capability of Sparse CNNs. They are focal sparse convolution (Focals Conv) and its multi-modal variant of focal sparse convolution with fusion. For the first time, we show that spatially learnable sparsity in sparse convolution is essential for sophisticated 3D object detection.
  arXiv  Detail & Related papers  (2022-04-26T17:34:10Z)
• Monocular Depth Distribution Alignment with Low Computation [15.05244258071472]
  We model the majority of accuracy contrast between light-weight networks and heavy-weight networks. By perceiving the difference of depth features between every two regions, DANet tends to predict a reasonable scene structure. Thanks to the alignment of depth distribution shape and scene depth range, DANet sharply alleviates the distribution drift, and achieves a comparable performance with prior heavy-weight methods.
  arXiv  Detail & Related papers  (2022-03-09T06:18:26Z)
• Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion [56.85837052421469]
  Estimating scene geometry from data obtained with cost-effective sensors is key for robots and self-driving cars. In this paper, we study the problem of predicting dense depth from a single RGB image with optional sparse measurements from low-cost active depth sensors. We introduce Sparse Networks (SANs), a new module enabling monodepth networks to perform both the tasks of depth prediction and completion.
  arXiv  Detail & Related papers  (2021-03-30T21:22:26Z)
• Direct Depth Learning Network for Stereo Matching [79.3665881702387]
  A novel Direct Depth Learning Network (DDL-Net) is designed for stereo matching. DDL-Net consists of two stages: the Coarse Depth Estimation stage and the Adaptive-Grained Depth Refinement stage. We show that DDL-Net achieves an average improvement of 25% on the SceneFlow dataset and $12%$ on the DrivingStereo dataset.
  arXiv  Detail & Related papers  (2020-12-10T10:33:57Z)
• Efficient Depth Completion Using Learned Bases [94.0808155168311]
  We propose a new global geometry constraint for depth completion. By assuming depth maps often lay on low dimensional subspaces, a dense depth map can be approximated by a weighted sum of full-resolution principal depth bases.
  arXiv  Detail & Related papers  (2020-12-02T11:57:37Z)
• Adaptive Context-Aware Multi-Modal Network for Depth Completion [107.15344488719322]
  We propose to adopt the graph propagation to capture the observed spatial contexts. We then apply the attention mechanism on the propagation, which encourages the network to model the contextual information adaptively. Finally, we introduce the symmetric gated fusion strategy to exploit the extracted multi-modal features effectively. Our model, named Adaptive Context-Aware Multi-Modal Network (ACMNet), achieves the state-of-the-art performance on two benchmarks.
  arXiv  Detail & Related papers  (2020-08-25T06:00:06Z)

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.