To achieve precise and rapid computation of seedling height and stem diameter — key phenotypic traits for monitoring seedling growth and selecting superior varieties — this study proposes a SAM-Integrated Adaptive Fusion Depth Network (SAFD-Net). SAFD-Net integrates segmentation masks generated by Segment Anything Model (SAM) with an Adaptive Prior Extraction (APE) module to produce priors focused on individual seedling characteristics, and it fuses these priors with deep features through an Adaptive Attention Fusion (AAF) module. A Local Depth Generation (LDG) module refines depth details to improve estimation accuracy, and an Adaptive Multi-scale Fusion (AMF) module merges LDG outputs at different scales to produce high-precision depth maps. From these maps, seedling region depth, pixel height, and pixel stem diameter are extracted to compute actual seedling height and stem diameter. Comparisons with various depth estimation networks demonstrate that SAFD-Net outperforms existing models in both depth estimation and seedling measurement. Experimental evaluations on seedlings from three crops with distinct phenotypic characteristics further show that the method maintains high accuracy under varying shooting distances, lighting conditions, multiple targets, and tilt angles, offering a novel approach for phenotypic monitoring during seedling cultivation. Code is released at https://github.com/Songlei7664/SAFD-Net .

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 athttps://github.com/Songlei7664/ACFD-Net.

Large-ratio cloud occlusion significantly hampers the utilization of high-resolution remote sensing imagery. The existing reconstruction methods (1) overlook the problem of reconstructed and composite images sharing high-and low-level semantic and visual attributes in non-reconstructed regions, exacerbating the pronounced boundary effects; (2) neglect appearance discrepancies between reconstructed and non-reconstructed regions, leading to spectral degradation, and texture loss; and (3) overlook the problem of reconstructing large-ratio missing information. To address these issues, a global and local dual fusion network is proposed in this study for large-ratio cloud occlusion removal in high-resolution remote sensing images. The global foreground–background aware attention module tackles shared high-level semantic features, whereas the local visual feature enhancement module addresses appearance differences. The global and local dual fusion network combines the Sobel and reconstruction loss functions for effective reconstruction by employing a two-stage fusion strategy. Compared to the classical recurrent feature reasoning network, spatiotemporal generator network, spatial-temporal-spectral convolutional neural network, and bishift network, the proposed model demonstrates superior quantitative and visual reconstruction outcomes for the 40%, 50%, and 70% missing ratios of Gaofen-1 (2 m).