# Consistent Time-of-Flight Depth Denoising via Graph-Informed Geometric Attention

arXiv: https://arxiv.org/abs/2506.23542 · HTML: https://mlsanity.com/paper/2506.23542/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing](https://mlsanity.com/paper/1912.10557/) (2019)
- [Graph Signal Processing: Overview, Challenges and Applications](https://mlsanity.com/paper/1712.00468/) (2017)
- [Learning robust perceptive locomotion for quadrupedal robots in the wild](https://mlsanity.com/paper/2201.08117/) (2022)
- [The Fast Bilateral Solver](https://mlsanity.com/paper/1511.03296/) (2015)
- [Don't Forget The Past: Recurrent Depth Estimation from Monocular Video](https://mlsanity.com/paper/2001.02613/) (2020)
- [Graph Spectral Image Processing](https://mlsanity.com/paper/1801.04749/) (2018)
- [Temporally Consistent Online Depth Estimation in Dynamic Scenes](https://mlsanity.com/paper/2111.09337/) (2021)
- [Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset](https://mlsanity.com/paper/1807.10376/) (2018)
- [Consistent Direct Time-of-Flight Video Depth Super-Resolution](https://mlsanity.com/paper/2211.08658/) (2022)
- [Deep Graph Laplacian Regularization for Robust Denoising of Real Images](https://mlsanity.com/paper/1807.11637/) (2018)
- [Joint Graph-based Depth Refinement and Normal Estimation](https://mlsanity.com/paper/1912.01306/) (2019)
- [iToF2dToF: A Robust and Flexible Representation for Data-Driven Time-of-Flight Imaging](https://mlsanity.com/paper/2103.07087/) (2021)
- [Very Power Efficient Neural Time-of-Flight](https://mlsanity.com/paper/1812.08125/) (2018)
- [Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors](https://mlsanity.com/paper/2406.04090/) (2024)
- [RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising](https://mlsanity.com/paper/2111.15513/) (2021)
- [Graph-Based Depth Denoising & Dequantization for Point Cloud Enhancement](https://mlsanity.com/paper/2111.04946/) (2021)

## Built on by (most cited first, 1 of 1)

- [Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restoration](https://mlsanity.com/paper/2609.05507/) (2026)

## Abstract (arXiv)

Depth images captured by Time-of-Flight (ToF) sensors are prone to noise, requiring denoising for reliable downstream applications. Previous works either focus on single-frame processing, or perform multi-frame processing without considering depth variations at corresponding pixels across frames, leading to undesirable temporal inconsistency and spatial ambiguity. In this paper, we propose a novel ToF depth denoising network leveraging motion-invariant graph fusion to simultaneously enhance temporal stability and spatial sharpness. Specifically, despite depth shifts across frames, graph structures exhibit temporal self-similarity, enabling cross-frame geometric attention for graph fusion. Then, by incorporating an image smoothness prior on the fused graph and data fidelity term derived from ToF noise distribution, we formulate a maximum a posterior problem for ToF denoising. Finally, the solution is unrolled into iterative filters whose weights are adaptively learned from the graph-informed geometric attention, producing a high-performance yet interpretable network. Experimental results demonstrate that the proposed scheme achieves state-of-the-art performance in terms of accuracy and consistency on synthetic DVToF dataset and exhibits robust generalization on the real Kinectv2 dataset. Source code will be released at hrefhttps://github.com/davidweidawang/GIGA-ToFhttps://github.com/davidweidawang/GIGA-ToF.