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.

Image denoising is a critical problem in industrial information applications since noisy images can have adverse effects on the performance of many industrial tasks. Currently, Transformer structures and graph convolutional networks (GCNs) have been widely employed in image denoising to capture long-range dependencies for the performance promotion. These methods, however, severely suffer from three major problems. Initially, the long-range dependencies captured by Transformers and GCNs are only focused on the pixel level and patch level, respectively. This leads to the coarse retrieved feature, hindering further performance promotion. In addition, due to the limited training data, especially for the noisy images with highly diverse and complex noise, the denoising process may lack sufficient feature for reconstructing denoised images. Eventually, the limited training data may also results in over-fitting, leading to poor generalization in the denoising process. This article first proposes adaptive graph prior network (AGP-Net) using a novel graph construction method to capture the long-range dependencies on both the pixel and patch levels. Then, we propose graph supplementary prior and graph noise prior in AGP-Net to adaptively generate supplementary feature and regularization noise for improving the performance and generalization of image denoising. Extensive ablation and benchmark tests show our AGP-Net achieve the most advanced image denoising performance.

Deep Neural Networks (DNNs) have achieved impressive results on the task of image denoising, but there are two serious problems. First, the denoising ability of DNNs-based image denoising models using traditional training strategies heavily relies on extensive training on clean-noise image pairs. Second, image denoising models based on DNNs usually have large parameters and high computational complexity. To address these issues, this paper proposes a two-stage Few-Shot Learning for Image Denoising (FSLID). Our FSLID is a two-stage denoising strategy integrating Basic Feature Learner (BFL), Denoising Feature Inducer (DFI), and Shared Image Reconstructor (SIR). BFL and SIR are first jointly unsupervised to train on the base image dataset$\mathcal {D}_{base}$consisting of easily collected high-quality clean images. Following this, the trained BFL extracts the guided features and constraint features for the noisy and corresponding clean images in the novel image dataset$\mathcal {D}_{novel}$, respectively. Furthermore, DFI encodes the noisy features of the noisy images in$\mathcal {D}_{novel}$. Then, inducing both the guided features and noisy features, DFI can generate the denoising prior features for the SIR with frozen weights to adaptively denoise the noisy images. Furthermore, we propose refined, low-channel-count, recursive multi-branch Multi-Scale Feature Recursive (MSFR) to modularly formulate an efficient DFI to capture more diverse contextual features information under a limited number of feature channels. Thus, compared with the baseline models, the FSLID composed of the proposed MSFR can significantly reduce the number of model parameters and computational complexity. Extensive experimental results demonstrate our FSLID significantly outperforms well-established baselines on multiple datasets and settings. We hope that our work will encourage further research to explore the field of few-shot image denoising.

Image denoising aims to remove the noise from noisy images. With the increasing complexity of the noise within the noisy images, current denoising methods cannot satisfactorily address this issue. This article proposes a graph attention in attention network (GAiA-Net) for image denoising. First, we introduce a novel approach to graph construction for the GAiA-Net. In the process of such graph construction, the noisy images are divided into patches to formulate the nodes in a graph. The edges are initialized using$k $-nearest neighbors. Hence, through iterative transformation and learning, both the pixel-level and structure-level features can be captured by different information exchanges and aggregation within (pixel-level) and outside (structure-level) of the nodes, respectively. Second, we propose the graph attention in attention (GAiA) in the GAiA-Net. The proposed GAiA produces the pixel-level attention within nodes to be further induced to the nodes with various distances to generate the final attention. Therefore, our GAiA-Net can capture the long dependencies on both the pixel-level and structure-level features, which can effectively reduce the complex noise in the denoising process. Comprehensive experiments demonstrate that the proposed GAiA-Net produces state-of-the-art performances on both synthetic noise image and real noise image datasets. Especially, when experimenting on complex noisy Nam datasets, our GAiA-Net achieves a PSNR of 40.40 dB and SSIM of 0.989. These results prove the satisfactory potential and effectiveness of our GAiA-Net.

Image denoising methods using deep neural networks have achieved a great progress in the image restoration. However, the recovered images restored by these deep denoising methods usually suffer from severe over-smoothness, artifacts, and detail loss. To improve the quality of restored images, we first propose Supplemental Priors (SP) method to adaptively predict depth-directed and sample-directed prior information for the reconstruction (decoder) networks. Furthermore, the over-parameterized deep neural networks and too precise supplemental prior information may cause an over-fitting, restricting the performance promotion. To improve the generalization of denoising networks, we further propose Regularization Priors (RP) method to flexibly learn depth-directed and dataset-directed regularization noise for the retrieving (encoder) networks. By respectively integrating the encoder and decoder with these plug-and-play RP block and SP block, we propose the final Adaptive Prior Denoising Networks, called APD-Nets. APD-Nets is the first attempt to simultaneously regularize and supplement denoising networks from the adaptive priors’ view with drawing learning-based mechanism into producing adaptive regularization noise and supplemental information. Extensive experiment results demonstrate our method significantly improves the generalization of denoising networks and the quality of restored images with greatly outperforming the traditional deep denoising methods both quantitatively and visually.The code will be released athttps://github.com/JiangBoCS/APD-Nets.

The crux of image reflection removal stems from the difficulty of recognizing the diverse reflection patterns. Typical methods optimize the modeling of background restoration by performing low-level supervision on the restored image to minimize its per-pixel difference from the groundtruth, which re-lies on substantial training samples to learn diverse reflection patterns robustly and avoid overfitting spurious reflection patterns. In this work, we perform supervision on the contrastive distribution between the predicted background and the reflection image. Specifically, our proposed method restores the background and the reflection images in parallel, and seeks to maximize the distribution consistency between the predicted background-reflection contrast and the groundtruth contrast in the latent space. Such supervision pushes the model to focus on contrastive modeling between the background and reflection image. Extensive experiments on four real-world bench-marks demonstrate that our method consistently outperforms state-of-the-art methods.