Gaussian Belief Propagation Network for Depth Completion

• URL: http://arxiv.org/abs/2601.21291v1
• Date: Thu, 29 Jan 2026 05:44:41 GMT
• Title: Gaussian Belief Propagation Network for Depth Completion
• Authors: Jie Tang, Pingping Xie, Jian Li, Ping Tan,
• Abstract summary: Deep learning methods have achieved state-of-the-art (SOTA) performance, but handling the sparse and irregular nature of input depth data is a significant challenge.<n>We introduce the Gaussian Belief Propagation Network (GBPN), a novel framework integrating deep learning with probabilistic graphical models for end-to-end depth completion.<n>Extensive experiments demonstrate that GBPN achieves SOTA performance on the NYUv2 and KITTI benchmarks.
• Score: 38.053489092019824
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Depth completion aims to predict a dense depth map from a color image with sparse depth measurements. Although deep learning methods have achieved state-of-the-art (SOTA), effectively handling the sparse and irregular nature of input depth data in deep networks remains a significant challenge, often limiting performance, especially under high sparsity. To overcome this limitation, we introduce the Gaussian Belief Propagation Network (GBPN), a novel hybrid framework synergistically integrating deep learning with probabilistic graphical models for end-to-end depth completion. Specifically, a scene-specific Markov Random Field (MRF) is dynamically constructed by the Graphical Model Construction Network (GMCN), and then inferred via Gaussian Belief Propagation (GBP) to yield the dense depth distribution. Crucially, the GMCN learns to construct not only the data-dependent potentials of MRF but also its structure by predicting adaptive non-local edges, enabling the capture of complex, long-range spatial dependencies. Furthermore, we enhance GBP with a serial \& parallel message passing scheme, designed for effective information propagation, particularly from sparse measurements. Extensive experiments demonstrate that GBPN achieves SOTA performance on the NYUv2 and KITTI benchmarks. Evaluations across varying sparsity levels, sparsity patterns, and datasets highlight GBPN's superior performance, notable robustness, and generalizable capability.

Related papers

• UnLoc: Leveraging Depth Uncertainties for Floorplan Localization [80.55849461031879]
  UnLoc is an efficient data-driven solution for sequential camera localization within floorplans.<n>We introduce a novel probabilistic model that incorporates uncertainty estimation, modeling depth predictions as explicit probability distributions.<n>We evaluate UnLoc on large-scale synthetic and real-world datasets, demonstrating significant improvements in terms of accuracy and robustness.
  arXiv  Detail & Related papers  (2025-09-14T14:45:43Z)
• Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion [33.854696587141355]
  We propose a novel depth completion framework that leverages depth foundation models to attain remarkable robustness without large-scale training.<n>Specifically, we leverage a depth foundation model to extract environmental cues, including structural and semantic context, from RGB images to guide the propagation of sparse depth information into missing regions.<n>Our framework performs remarkably well in the OOD scenarios and outperforms existing state-of-the-art depth completion methods.
  arXiv  Detail & Related papers  (2025-08-07T02:38:24Z)
• DepthSplat: Connecting Gaussian Splatting and Depth [90.06180236292866]
  We present DepthSplat to connect Gaussian splatting and depth estimation.<n>We show that Gaussian splatting can serve as an unsupervised pre-training objective for learning powerful depth models.<n>Our DepthSplat achieves state-of-the-art performance on ScanNet, RealEstate10K and DL3DV datasets.
  arXiv  Detail & Related papers  (2024-10-17T17:59:58Z)
• LRRU: Long-short Range Recurrent Updating Networks for Depth Completion [45.48580252300282]
  Long-short Range Recurrent Updating (LRRU) network is proposed to accomplish depth completion more efficiently. LRRU first roughly fills the sparse input to obtain an initial dense depth map, and then iteratively updates it through learned spatially-variant kernels. Our initial depth map has coarse but complete scene depth information, which helps relieve the burden of directly regressing the dense depth from sparse ones.
  arXiv  Detail & Related papers  (2023-10-13T09:04:52Z)
• Bayesian Interpolation with Deep Linear Networks [92.1721532941863]
  Characterizing how neural network depth, width, and dataset size jointly impact model quality is a central problem in deep learning theory. We show that linear networks make provably optimal predictions at infinite depth. We also show that with data-agnostic priors, Bayesian model evidence in wide linear networks is maximized at infinite depth.
  arXiv  Detail & Related papers  (2022-12-29T20:57:46Z)
• MaskingDepth: Masked Consistency Regularization for Semi-supervised Monocular Depth Estimation [38.09399326203952]
  MaskingDepth is a novel semi-supervised learning framework for monocular depth estimation. It enforces consistency between the strongly-augmented unlabeled data and the pseudo-labels derived from weakly-augmented unlabeled data.
  arXiv  Detail & Related papers  (2022-12-21T06:56:22Z)
• GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs [49.55919802779889]
  We propose a Graph Convolution based Spatial Propagation Network (GraphCSPN) as a general approach for depth completion. In this work, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning. Our method achieves the state-of-the-art performance, especially when compared in the case of using only a few propagation steps.
  arXiv  Detail & Related papers  (2022-10-19T17:56:03Z)
• Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer [53.413305467674434]
  We introduce open-source RGB data to support spike depth estimation, leveraging its annotations and spatial information. We propose a cross-modality cross-domain (BiCross) framework to realize unsupervised spike depth estimation. Our method achieves state-of-the-art (SOTA) performances, compared with RGB-oriented unsupervised depth estimation methods.
  arXiv  Detail & Related papers  (2022-08-26T09:35:20Z)
• Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM [1.8899300124593648]
  Feature-based visual simultaneous localization and mapping (SLAM) methods only estimate the depth of extracted features. depth completion tasks that estimate a dense depth from a sparse depth have gained significant importance in robotic applications like exploration. We propose a mesh depth refinement (MDR) module to address this problem. The Struct-MDC outperforms other state-of-the-art algorithms on public and our custom datasets.
  arXiv  Detail & Related papers  (2022-04-29T04:29:17Z)
• Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth [24.897377434844266]
  We propose a novel structure and training strategy for monocular depth estimation. We deploy a hierarchical transformer encoder to capture and convey the global context, and design a lightweight yet powerful decoder. Our network achieves state-of-the-art performance over the challenging depth dataset NYU Depth V2.
  arXiv  Detail & Related papers  (2022-01-19T06:37:21Z)
• Shallow Network Based on Depthwise Over-Parameterized Convolution for Hyperspectral Image Classification [0.7329200485567825]
  This letter proposes a shallow model for hyperspectral image classification (HSIC) using convolutional neural network (CNN) techniques. The proposed method outperforms other state-of-the-art methods in terms of classification accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2021-12-01T03:10:02Z)
• Unsupervised Scale-consistent Depth Learning from Video [131.3074342883371]
  We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training. Thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into the ORB-SLAM2 system. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training.
  arXiv  Detail & Related papers  (2021-05-25T02:17:56Z)

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.