Synthesizing novel views from unconstrained image collections is an important but challenging task in computer vision. Existing methods, which optimize per-image appearance and transient occlusion through implicit neural networks from dense training views (approximately 1000 images), struggle to perform effectively with sparse inputs, resulting in noticeable artifacts. In this work, we introduce SparseGS-W, a novel framework designed to boost the reconstruction of unconstrained scenes and novel view synthesis using as few as five training images. Motivated by the observation that diffusion prior constrained by limited sparse inputs can remove artifacts through fast and efficient fine-tuning, we propose a plug-and-play Constrained Novel-View Enhancement module to iteratively enhance the quality of rendered novel views. We further present an Occlusion Handling scheme, which flexibly removes occlusions utilizing the inherent inpainting capability of constrained diffusion priors. Both components are capable of extracting appearance features from any user-provided reference image, enabling flexible modeling of illumination-consistent scenes. Extensive experiments demonstrate that SparseGS-W achieves superior performance not only in full-reference metrics, but also in commonly used non-reference metrics such as FID, ClipIQA and MUSIQ.

Restoring high-quality images from degraded hazy images is a challenging task, particularly in real-world scenarios. Recent investigations seek to address this limitation by exploring advanced methods for synthesizing haze and incorporating real-world hazy images. Due to the inherent diversity and complexity of real-world haze, these methods struggle to accurately model haze representations. Based on our observation that the hazy images generated by advanced text-to-image diffusion models exhibit a remarkable resemblance to real-world haze, it suggests that these diffusion models effectively internalize haze representations. Hence, we propose FreeDehaze, a novel training-free diffusion method for real-world image dehazing. FreeDehaze is a posterior-based framework capable of addressing non-linear dehazing challenges without relying on additional degradation estimation networks. It follows the human cognition for image restoration, beginning with perception and subsequently enhancing the image. The core method initially generates pseudo-clean images based on abstract textual descriptions. Subsequently, optimal transport aligns the denoising network output with the pseudo-clean image within a PCA-based haze subspace, facilitating high-fidelity dehazing. Extensive experiments demonstrate that FreeDehaze outperforms comparative methods in subjective metrics on challenging datasets (e.g., RTTS, URHI, and O-HAZE) and achieves competitive objective metrics, demonstrating strong generalization although without additional training.

The occurrence of frequency aliasing between the camera and high-frequency scene elements causes moiré patterns in images, leading to color distortions and a loss of fine details, thereby reducing image quality. The intricate frequency characteristics and diverse appearances inherent in moiré patterns render their removal, commonly referred to as demoiréing, particularly challenging. Recent advancements in deep learning-based demoiréing methods have showcased notable efficacy. However, prevailing techniques often specialize in mitigating moiré patterns exclusively within either the frequency or spatial domains. Additionally, these methods generally perform well at specific image resolutions, but struggle to maintain effectiveness across different resolutions due to less generalized architectures. To address these issues, we propose a Dual-domain Multi-level Multi-scale Network DMMNet, working in both spatial and frequency domains sequentially. The Multi-scale Multi-level Demoire Stage (MMDS) in our framework focuses on moiré patterns removal in the spatial domain. To adeptly integrate features from various semantic levels, we introduce a pioneering plug-and-play Adjacent Cross Attention (ACA) module within the MMDS. Subsequently, the Frequency Separation and Reconstruction Stage (FSRS) restores high-frequency texture details, reconstructs color information, and eliminates residual moiré patterns in the wavelet frequency domain. Ultimately, the clean image is obtained by converting it back to the spatial domain. Extensive experimental assessments, spanning both quantitative metrics and qualitative visual evaluations, attest to the superior efficacy of DMMNet to State-Of-The-Art (SOTA) demoiréing methods, concurrently exhibiting enhanced generalization for demoiréing across diverse image resolutions. We posit that the proposed methodology presents a viable solution for broader applications in the realm of demoiréing. Code will be available onhttps://github.com/Mr-Ma-yikun/DMMNet.

Synthetic aperture radar (SAR) has the advantage of all-weather observation, but its imaging principle based on the backscattering of electromagnetic waves makes its information less interpretable. One feasible approach is to convert SAR images into optical images, which not only improves the interpretability of SAR images but also fills the gaps in information captured by optical sensors due to weather and light limitations. Since conditional generative adversarial network (cGAN) has the powerful ability to generate images, many studies have started to apply it to image translation tasks. For SAR-to-optical translation, some specialized cGAN models have been proposed, but most of them struggle to process SAR images with widely varying styles, often generating images with poor quality. To this end, we propose a hybrid cGAN that combines the advantages of convolutional neural network (CNN) and vision transformer (ViT). With the advantage of ViT to capture long-distance feature dependencies, the global features can be extracted and then fused with the local features extracted by CNN to improve the representation capabilities of our generator. Moreover, we expand the receptive field of the residual blocks in CNN by hierarchical convolution. Perceptual loss and classification loss are added for training to further improve the fidelity of the generated images. Finally, we introduce the multiscale strategy into the discriminator to balance its learning ability with that of the generator. Both visual and quantitative experiments are conducted with other state-of-the-art methods. The results show that our method not only achieves the optimal results in all the evaluation metrics but also generates images that are more consistent with the human visual system. In addition, the potential of our method to process multitype SAR images with significant style differences is also experimentally demonstrated.