# Depth image denoising using nuclear norm and learning graph model

arXiv: https://arxiv.org/abs/2008.03741 · HTML: https://mlsanity.com/paper/2008.03741/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2020.

## Built on by (most cited first, 20 of 20)

- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [Parsing is All You Need for Accurate Gait Recognition in the Wild](https://mlsanity.com/paper/2308.16739/) (2023)
- [Guided Depth Map Super-resolution: A Survey](https://mlsanity.com/paper/2302.09598/) (2023)
- [Gait Recognition in the Wild with Multi-hop Temporal Switch](https://mlsanity.com/paper/2209.00355/) (2022)
- [ThermalGaussian: Thermal 3D Gaussian Splatting](https://mlsanity.com/paper/2409.07200/) (2024)
- [Style Interleaved Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2207.03132/) (2022)
- [TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition](https://mlsanity.com/paper/2102.04621/) (2021)
- [Offset equivariant networks and their applications](https://mlsanity.com/paper/2207.00292/) (2022)
- [Semi-Supervised Learning for Mars Imagery Classification and Segmentation](https://mlsanity.com/paper/2206.02180/) (2022)
- [Video Restoration with a Deep Plug-and-Play Prior](https://mlsanity.com/paper/2209.02854/) (2022)
- [Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning](https://mlsanity.com/paper/2507.21588/) (2025)
- [Scalable Deep Compressive Sensing](https://mlsanity.com/paper/2101.08024/) (2021)
- [Anchor Graph Structure Fusion Hashing for Cross-Modal Similarity Search](https://mlsanity.com/paper/2202.04327/) (2022)
- [Tensor Robust PCA with Nonconvex and Nonlocal Regularization](https://mlsanity.com/paper/2211.02404/) (2022)
- [Estimation of a Causal Directed Acyclic Graph Process using Non-Gaussianity](https://mlsanity.com/paper/2211.13800/) (2022)
- [ShapeMoir'e: Channel-Wise Shape-Guided Network for Image Demoir'eing](https://mlsanity.com/paper/2404.18155/) (2024)
- [VoxDepth: Rectification of Depth Images on Edge Devices](https://mlsanity.com/paper/2407.15067/) (2024)
- [THOR2: Topological Analysis for 3D Shape and Color-Based Human-Inspired Object Recognition in Unseen Environments](https://mlsanity.com/paper/2408.01579/) (2024)
- [3D Surface Reconstruction with Enhanced High-Frequency Details](https://mlsanity.com/paper/2505.03362/) (2025)
- [From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning](https://mlsanity.com/paper/2606.10595/) (2026)

## Abstract (arXiv)

The depth images denoising are increasingly becoming the hot research topic nowadays because they reflect the three-dimensional (3D) scene and can be applied in various fields of computer vision. But the depth images obtained from depth camera usually contain stains such as noise, which greatly impairs the performance of depth related applications. In this paper, considering that group-based image restoration methods are more effective in gathering the similarity among patches, a group based nuclear norm and learning graph (GNNLG) model was proposed. For each patch, we find and group the most similar patches within a searching window. The intrinsic low-rank property of the grouped patches is exploited in our model. In addition, we studied the manifold learning method and devised an effective optimized learning strategy to obtain the graph Laplacian matrix, which reflects the topological structure of image, to further impose the smoothing priors to the denoised depth image. To achieve fast speed and high convergence, the alternating direction method of multipliers (ADMM) is proposed to solve our GNNLG. The experimental results show that the proposed method is superior to other current state-of-the-art denoising methods in both subjective and objective criterion.