In this work, we observe that the generators, which are pre-trained on massive natural images, inherently hold the promising potential for superior low-light image enhancement against varying scenarios. Specifically, for the low-light image enhancement process of a single image, we introduce the pre-trained generators to restore the details and colors degraded by low-light conditions, thereby improving the visual effect. Taking one step further, we introduce a novel optimization strategy, which backpropagates the gradients to the input seeds rather than the parameters of the low-light image enhancement model, thus intactly retaining the generative knowledge learned from natural images and achieving faster convergence speed. Benefiting from the pre-trained knowledge and seed-optimization strategy, the low-light image enhancement model can significantly regularize the visibility and fidelity of the enhanced result, thus rapidly generating high-quality images without training on any low-light dataset. Extensive experiments on various benchmarks demonstrate the effectiveness of the proposed method, showing its potential advantages over numerous state-of-the-art methods both qualitatively and quantitatively.

In this paper, we first assess and harness various Vision Foundation Models (VFMs) in the context of Domain Generalized Semantic Segmentation (DGSS). Driven by the motivation that Leveraging Stronger pre-trained models and Fewer trainable parameters for Superior generalizability, we introduce a robust fine-tuning approach, namely “Rein”, to parameter-efficiently harness VFMs for DGSS. Built upon a set of trainable tokens, each linked to distinct instances, Rein precisely refines and forwards the feature maps from each layer to the next layer within the backbone. This process produces diverse refinements for different categories within a single image. With fewer trainable parameters, Rein efficiently fine-tunes VFMs for DGSS tasks, surprisingly surpassing full parameter fine-tuning. Extensive experiments across various settings demonstrate that Rein significantly outperforms state-of-the-art methods. Remarkably, with just an extra 1% of trainable parameters within the frozen backbone, Rein achieves a mIoU of 78.4% on the Cityscapes, without accessing any real urban-scene datasets. Code is available at https://github.com/w1oves/Rein.git.

In this work, we observe that model trained on vast general images via masking strategy, has been naturally embedded with their distribution knowledge, thus spontaneously attains the underlying potential for strong image denoising. Based on this observation, we propose a novel zero-shot denoising paradigm, i.e., $\textbf{M}$asked $\textbf{P}$re-train then $\textbf{I}$terative fill ($\textbf{MPI}$). MPI first trains model via masking and then employs pre-trained weight for high-quality zero-shot image denoising on a single noisy image. Concretely, MPI comprises two key procedures: $\textbf{1) Masked Pre-training}$ involves training model to reconstruct massive natural images with random masking for generalizable representations, gathering the potential for valid zero-shot denoising on images with varying noise degradation and even in distinct image types. $\textbf{2) Iterative filling}$ exploits pre-trained knowledge for effective zero-shot denoising. It iteratively optimizes the image by leveraging pre-trained weights, focusing on alternate reconstruction of different image parts, and gradually assembles fully denoised image within limited number of iterations. Comprehensive experiments across various noisy scenarios underscore the notable advances of MPI over previous approaches with a marked reduction in inference time.

Surface defect detection is a critical task in industrial production, and numerous methods have been proposed to achieve high detection accuracy. Although deep-learning-based approaches have achieved state-of-the-art (SOTA) performances, their vast computational cost and high memory footprint prevent their deployment in resource-constrained environments. To address this problem, we propose a collaborative filter pruning method for the defect detection model, which significantly reduces the number of required calculations and parameters while maintaining high performance, even in cases with tasks suffering from the class imbalance problem. Our method aims to obtain lightweight pruned models by removing unimportant filters according to their importance evaluated by both structural similarity and detail richness of corresponding feature maps. Moreover, to improve the performance of pruned models, we propose a knowledge-fused fine-tuning approach that fuses the knowledge derived from two teacher networks to look after both representation learning and classifier learning, alleviating the class imbalance problem. Experimental results on four public datasets demonstrate that the proposed approach performs favorably relative to the SOTA methods. In particular, the proposed method achieves 39× and 59× parameter compression for VGG-16 and ResNet-50, respectively, on the NEU-CLS dataset, with a very small detection accuracy loss (<0.2%).

A mirror-like surface (MLS) reflects highlight, aggravating the image saturation in structured light 3-D reconstruction systems and precluding defect detection based on reconstructed 3-D profiles. Previous studies have focused on a strategy of limiting the luminous flux entering the camera. However, the high intensity of the reflected highlight forces the limitation to be strengthened, which heavily reduces the modulation in the images for the 3-D reconstruction. Therefore, we propose a new strategy to adjust the source of the reflected highlight, i.e., the bidirectional reflectance (BR) of the MLS, which fundamentally suppresses the highlight and removes the limitation on the luminous flux. To execute the proposed strategy, an unfixed view structured light system (UVSLS) is established. The UVSLS converts the reflection viewer from the real camera to the virtual camera, realizing the flexible adjustment of the MLS BR. Finally, an MLS 3-D reconstruction framework is constructed to obtain the 3-D profile of the MLS. Experiments demonstrate that the proposed framework reduces the saturated pixels by 73.72% compared with the conventional method. Compared with the previous methods, the saturated pixels are reduced by an average of 47.62%.