In this paper, we investigate the limitations of the Vector Quantized Latent Diffusion Model (VQ-LDM) in restoration tasks. We identify a performance gap between the Vector Quantization (VQ) and Diffusion Model components, manifested as a significant discrepancy between the reconstruction quality of ground truth images processed via VQ autoregression and degraded images restored by VQ-LDM. Through experiments, we attribute this gap primarily to the lack of robustness in the mapped points of VQ within the original VQ-LDM framework. To address this issue, we propose a geometric based optimization approach. First, we introduce a simple yet effective method, termed interpolation-based latent initial state optimization, which mitigates the performance gap by replacing the original mapped points with interpolated values, supported by theoretical analysis. Here, the latent initial state refers specifically to the input of the diffusion model. Building upon this, we further propose a Chebyshev center-based latent initial state optimization, an elegant theoretical solution from a geometric perspective, that further enhances restoration performance. Our improvements consistently achieve superior results across nine benchmark datasets.

Visible-Infrared Person Re-identification aims to retrieve images of specific identities across modalities. To relieve the large cross-modality discrepancy, researchers introduce the auxiliary modality within the image space to assist modality-invariant representation learning. However, the challenge persists in constraining the inherent quality of generated auxiliary images, further leading to a bottleneck in retrieval performance. In this paper, we propose a novel Auxiliary Representation Guided Network (ARGN) to explore the potential of auxiliary representations, which are directly generated within the modality-shared embedding space. In contrast to the original visible and infrared representations, which contain information solely from their respective modalities, these auxiliary representations integrate cross-modality information by fusing both modalities. In our framework, we utilize these auxiliary representations as modality guidance to reduce the cross-modality discrepancy. First, we propose a High-quality Auxiliary Representation Learning (HARL) framework to generate identity-consistent auxiliary representations. The primary objective of our HARL is to ensure that auxiliary representations capture diverse modality information from both modalities while concurrently preserving identity-related discrimination. Second, guided by these auxiliary representations, we design an Auxiliary Representation Guided Constraint (ARGC) to optimize the modality-shared embedding space. By incorporating this constraint, the modality-shared embedding space is optimized to achieve enhanced intra-identity compactness and inter-identity separability, further improving the retrieval performance. In addition, to improve the robustness of our framework against the modality variation, we introduce a Part-based Adaptive Gaussian Module (PAGM) to adaptively extract discriminative information across modalities. Finally, extensive experiments are conducted to demonstrate the superiority of our method over state-of-the-art approaches on three VI-ReID datasets.

In image editing, Denoising Diffusion Implicit Models (DDIM) inversion has become a widely adopted method and is extensively used in various image editing approaches. The core concept of DDIM inversion stems from the deterministic sampling technique of DDIM, which allows the DDIM process to be viewed as an Ordinary Differential Equation (ODE) process that is reversible. This enables the prediction of corresponding noise from a reference image, ensuring that the restored image from this noise remains consistent with the reference image. Image editing exploits this property by modifying the cross-attention between text and images to edit specific objects while preserving the remaining regions. However, in the DDIM inversion, using the $t-1$ time step to approximate the noise prediction at time step $t$ introduces errors between the restored image and the reference image. Recent approaches have modeled each step of the DDIM inversion process as finding a fixed-point problem of an implicit function. This approach significantly mitigates the error in the restored image but lacks theoretical support regarding the existence of such fixed points. Therefore, this paper focuses on the study of fixed points in DDIM inversion and provides theoretical support. Based on the obtained theoretical insights, we further optimize the loss function for the convergence of fixed points in the original DDIM inversion, improving the visual quality of the edited image. Finally, we extend the fixed-point based image editing to the application of unsupervised image dehazing, introducing a novel text-based approach for unsupervised dehazing.

Visible-Infrared Person Re-identification aims to retrieve specific identities from different modalities. In order to relieve the modality discrepancy, previous works mainly concentrate on aligning the distribution of high-level features, while disregarding the exploration of fine-grained information. In this paper, we propose a novel Fine-grained Information Exploration Network (FIENet) to implement discriminative representation, further alleviating the modality discrepancy. Firstly, we propose a Progressive Feature Aggregation Module (PFAM) to progressively aggregate mid-level features, and a Multi-Perception Interaction Module (MPIM) to achieve the interaction with diverse perceptions. Additionally, combined with PFAM and MPIM, more fine-grained information can be extracted, which is beneficial for FIENet to focus on discriminative human parts in both modalities effectively. Secondly, in terms of the feature center, we introduce an Identity-Guided Center Loss (IGCL) to supervise identity representation with intra-identity and inter-identity information. Finally, extensive experiments are conducted to demonstrate that our method achieves state-of-the-art performance.

In this letter, we propose a novel ship detection method in high-resolution synthetic aperture radar (SAR) images. In the proposed method, the superpixel is utilized as the basic processing cell. We propose a superpixel-level Fisher vector to characterize the difference between the target and clutter superpixel due to the strong discriminating ability of the Fisher vector. Besides feature extraction, the threshold determination is another key step in the detection scheme. We determine the threshold in a semisupervised way, which combines the advantages of both supervised and unsupervised methods. Based on the threshold, the target superpixels are discriminated and we obtain the final detection result. Compared with existing methods, the proposed method shows robust performance under low signal-to-clutter ratio (SCR) conditions. Experiments performed on both synthetic data and a TerraSAR-X image demonstrate the effectiveness of the proposed method.

Rotational parameter estimation is fundamental to the focusing of imaging algorithm and inverse synthetic aperture radar (ISAR) image size calibration. Previous research has indicated that scattering points (SPs) in different imaging time windows locate at various associated positions in range-Doppler (RD) planes. This paper exploits the relation to estimate the rotation parameters (RPs) and translation error parameters for medium processing time length and nonuniform rotation situation. The iterative closet point (ICP) method inspires an alternating iterative algorithm consisting of the SP assignment and parameter optimization. In the parameter optimization step, multiple SP set pairs are utilized to construct the objective function that represents the degree of mismatch between point set pairs. A compatible fast SP extracting method is also presented to reduce the computational complexity. The experimental results show that the proposed algorithm can provide fast, accurate, and robust estimation for parameters in nonuniform rotation case.