CVJun 30, 2025

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

arXiv:2506.23542v1h-index: 5Has Code
Originality Incremental advance
AI Analysis

This addresses depth denoising for ToF sensors, improving reliability for downstream applications like robotics or AR, but appears incremental as it builds on prior multi-frame methods.

The paper tackles noise in Time-of-Flight depth images by proposing a network that uses motion-invariant graph fusion to enhance temporal stability and spatial sharpness, achieving state-of-the-art performance on synthetic and real datasets.

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 \href{https://github.com/davidweidawang/GIGA-ToF}{https://github.com/davidweidawang/GIGA-ToF}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes