Adaptive Clustering and Frequency Division Network for Efficient Monocular Depth Estimation
- 4 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (12) , 12564-12578
Abstract
Monocular depth estimation infers the relative depth of objects by analyzing visual cues in images, ultimately enhancing the comprehension of complex scenes in computer vision systems. Although existing Transformer architectures effectively capture long-range visual dependencies, two significant challenges persist: (a) insufficient integration of spatial context leads to inconsistent depth estimation, particularly under varying perspectives or lighting conditions; (b) the model’s difficulty in capturing global features hinders the parsing of subtle object differences, causing confusion in depth information and reducing sensitivity to variations in object distance and scene layout. To address the aforementioned issues, an Adaptive Clustering Mechanism (ACM) module coupled with a Deformable Frequency Division Fusion (DFDF) module was introduced. Specifically, the ACM module refines and adjusts features via cosine similarity, thereby enhancing cluster center similarity and stabilizing depth estimation. The DFDF module leverages frequency decomposition to extract differential features between objects, enhancing high-frequency information to improve the discrimination of subtle features. Integrating these components, the Frequency Division Adaptive Clustering Enhancement (FDACE) module emerges as the decoder’s core within the Adaptive Clustering and Frequency Division Network (ACFD-Net), facilitating both the precise generation of depth information and the efficient recovery of spatial resolution. Furthermore, we present a progressive depth estimation strategy that seamlessly integrates non-gradient output features from FDACE modules across various scales, and conducts independent optimizations, merging multi-scale information with localized details, and progressively calibrating depth estimates to enhance congruence with actual scenes. The ACM and DFDF modules concentrate on pivotal features, selectively enhancing high-frequency information, thereby minimizing redundant computations and optimizing resource allocation, which significantly boosts computational efficiency. Experimental results demonstrate that ACFD-Net significantly improves both the accuracy and efficiency of depth estimation. Code is released at https://github.com/Songlei7664/ACFD-Net.Keywords
Funding Information
- National Key Research and Development Program of China (2024YFD1300600)
- National Natural Science Foundation of China (62401476, 32272931, 32472964)
- Key Laboratory for Crop Production and Smart Agriculture of Yunnan Province (TG20240954)
- Northwest A&F University Ph.D. Research Startup Fund Project (2452024115)
This publication has 37 references indexed in Scilit:
- Integrating convolutional guidance and Transformer fusion with Markov Random Fields smoothing for monocular depth estimationEngineering Applications of Artificial Intelligence, 2025
- Monocular Depth Estimation for Autonomous Driving Based on Instance Clustering Guidance2024
- CATNet: Convolutional attention and transformer for monocular depth estimationPattern Recognition, 2023
- DepthFormer: Exploiting Long-range Correlation and Local Information for Accurate Monocular Depth EstimationMachine Intelligence Research, 2023
- Depth Map Decomposition for Monocular Depth Estimation2022
- LocalBins: Improving Depth Estimation by Learning Local Distributions2022
- Deep learning for monocular depth estimation: A reviewNeurocomputing, 2021
- Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks2016
- Deeper Depth Prediction with Fully Convolutional Residual Networks2016
- Indoor Segmentation and Support Inference from RGBD Images2012