The complex entanglement between darkness and noise hinders the advance of low-light image enhancement. Most existing methods adopted lightening-then-denoising or embedded a special denoising module into enhancement network without specific noise knowledge as supervision to restore low-light images. However, they either fail to remove the amplified noise or blur the detail information. Against above drawbacks, we propose a novel dual prior guidance method for low-light image enhancement that relights darkness and suppresses noise simultaneously. Concretely, the main novelties of our proposed method are three-fold. Firstly, our formulation originates from a statistic observation that darkness can be disentangled into luminance channel, yet noise still exists each channel when low-light images are transformed from RGB space to YCbCr space. It inspires us to design an ingenious method, extracting noise and darkness, termed END, to enhance low-light images. Secondly, we propose a prior extraction network with prior composition module to extract luminance and noise priors from different channels. Thirdly, an image enhancement network deployed with prior guidance module is proposed to progressively lighten the darkness and remove noise. Extensive experiments on multiple benchmarks demonstrate that our proposed method achieves remarkable performance compared to other state-of-the-art low-light image enhancement methods. The source code and trained model can be found inhttps://github.com/WHK-Huake/END.

Learning-based image compression algorithms typically focus on designing encoding and decoding networks and improving the accuracy of entropy model estimation to enhance the rate-distortion (RD) performance. However, few algorithms leverage the compression distortion prior from existing compression algorithms to improve RD performance. In this paper, we propose a latent diffusion model-based remote sensing image compression (LDM-RSIC) method, which aims to enhance the final decoding quality of RS images by utilizing the generated distortion prior from a LDM. Our approach consists of two stages. In Stage I, a self-encoder learns prior from the high-quality input image. In Stage II, the prior is generated through a LDM, conditioned on the decoded image of an existing learning-based image compression algorithm, to be used as auxiliary information for generating the texture-rich enhanced images. To better utilize the prior, a channel attention and gate-based dynamic feature attention module (DFAM) is embedded into a Transformer-based multi-scale enhancement network (MEN) for image enhancement. Extensive experimental results demonstrate the proposed LDM-RSIC outperforms existing state-of-the-art traditional and learning-based image compression algorithms in terms of both subjective perception and objective metrics. The code will be available at https://github.com/mlkk518/LDM-RSIC.

Retinex theory-based low-light image enhancement methods have received increasing attention and achieved tremendous advancements. However, there still exist two seldom-explored issues: 1) The above methods only formally simulate the Retinex decomposition, resulting in lacking explicit interpretability. 2) They usually are performed in single-scale space, leading to suboptimal enhancement results. In this paper, we propose an interpretable Multi-scale Retinex Unfolding Network (MRUNet) for low-light image enhancement, which can tackle both of the aforementioned issues simultaneously. Specifically, we formulate low-light image enhancement as a multi-scale Retinex optimization problem and design an iteration minimization solution to solve it. The optimization solution is further unfolded to fabricate MRUNet, which is empowered with clear physical significance and multi-scale prior knowledge in favor of image enhancement. However, it will aggravate model size and efficiency when exploiting multiple proximal mapping networks to extract multi-scale prior from multi-scale inputs. To surmount the issue, we propose a Scale-Aware Proximal mapping Module (SAPM), which efficiently collect multi-scale prior knowledge via the weight sharing strategy. In SAPM, we tailor a scale-aware transformer to model the specific scale-similarity among different scales. Extensive experiments manifest that MRUNet surpasses other Retinex-based low-light image enhancement methods on multiple benchmarks.

Different from object counting in surveillance scenes, remote sensing object counting encounters knotty challenges due to its tiny scale and cluttered background. However, existing remote sensing counting methods pursue favorable performance by sacrificing resolution to obtain semantic information, resulting in the loss of significant features of tiny-scale objects. To surmount the above issue, we propose a novel hierarchical kernel interaction network, dubbed HKINet, for remote sensing object counting. HKINet is comprised of several hierarchical kernel interaction modules (HKIMs) to simultaneously preserve high-resolution features and extract deep-layer semantic information. Specifically speaking, HKIM hierarchically performs multiresolution convolutions to avoid information loss in low resolution. Moreover, a scale interaction block (SIB) is used to combine multiresolution features for semantic information interaction. Finally, hierarchical resolutions are fused to output the prediction density map. To validate the superiority of our proposed HKINet, we conduct extensive experiments on four remote sensing object counting datasets, e.g., RSOC, CARPK, PUCPR+, and DroneCrowd datasets, and experimental results demonstrate HKINet outperforms other state-of-the-art remote sensing counting methods in terms of mean absolute error (MAE) and root mean squared error (RMSE).

Approximate message passing-based compressive sensing reconstruction has received increasing attention, the performance of which depends heavily on the ability of the denoising operator. However, most methods only employ an off-the-shelf denoising model as the denoising operator of the iteration solver, which imposes an unfavorable limit on reconstruction performance of compressive sensing. To solve the aforementioned issue, we propose a novel versatile denoising-based approximate message passing model, abbreviated as VD-AMP, for compressive sensing (CS) recovery. To be specific, we meticulously design a double encoder-decoder denoising network (DEDNet), which manifests the impressive performance in Gaussian denoising. Moreover, a fine-grained noise level division (FNLD) solution is proposed to release the potential of the well-designed DEDNet so as to improve the reconstruction performance. However, strengthening the denoiser alone fails to remove the distortion artifact of reconstruction images at low sampling rates. To alleviate the defect, we propose an anti-aliasing sampling (AS), which firstly maps the input image to a smoothing sub-space using the proposed DEDNet before vanilla sampling, reducing aliasing between high-frequency and low-frequency information on measurement. Extensive experiments on benchmark datasets demonstrate that the proposed VD-AMP significantly outperforms state-of-the-art CS reconstruction models by a large margin, e.g., up to 2 dB gains on PSNR.

By transmitting a single frequency‐shifted waveform, coherent frequency diverse array (FDA) can provide a simple way to realize full spatial coverages with stable gains. Owing to the range‐angle dependency in coherent FDA, the authors implement a two‐dimensional angle‐time matched filter to perform equivalent transmit beamforming and matched filtering simultaneously. However, such filter structures merely control main‐lobes of equivalent transmit beams towards target directions. It fails to form nulls at interference directions. Moreover, traditional adaptive beamforming by designing adaptive weight vectors are no longer applicable. Additionally, they find that the range resolution scales linearly with the element number. To tackle these issues, a space‐time matched filter (STMF) in combination with the hybrid coding technique is proposed. Aiming at mitigating interferences, the STMF is designed with a formulation of quadratically constrained quadratic programing. By relaxation of quadratic constraints, the hard non‐convex problem can be turned into the second‐order cone programing to obtain optimal filter parameters. Furthermore, the hybrid coding technique is devised to jointly improve the range resolution. Numerical experiments of both two‐dimensional range‐angle outputs and one‐dimensional range profiles via filtering are provided, which demonstrate that the STMF with hybrid coding can effectively suppress sidelobe interferences with a range resolution enhancement.

Coherent frequency diverse array (FDA) can provide the full spatial illumination with a stable transmit gain by employing a single frequency‐shifted waveform. However, the authors find that the range resolution is scaled linearly with the number of elements. In this work, the problem is first quantitatively analysed through mathematical derivation. To solve the issue, a subarray‐based coherent FDA transmitting pulsed linear frequency modulation signals is proposed. The essence of the subaperture technique is to partition the transmit antenna array into multiple regular or irregular subarrays, wherein an identical carrier frequency is utilised in each subarray. Meanwhile, distinct carrier frequencies are adopted between subarrays. Moreover, the multi‐dimensional ambiguity function is studied to assess the properties including the range resolution, spatial coverage and sidelobe level. Simulation results demonstrate that the proposed approach has superiorities in range resolution enhancement and range sidelobe reduction.