The quadratic computational complexity of softmax attention presents a fundamental bottleneck to scaling modern language models to long sequences. While the proposed Lightning Attention mechanism offers a linear-complexity alternative, its state-of-the-art implementations remain predominantly optimized for GPU architectures and fail to fully leverage the capabilities of alternative accelerators such as Ascend NPUs. To bridge this gap, we propose EPLoN (Exploiting Efficient Parallelism with Selective Rematerialization for Lightning Attention on NPU). EPLoN presents a high-performance implementation of Lightning Attention optimized for heterogeneous Ascend NPUs. EPLoN reformulates the algorithm, introducing an efficient parallelism scheme with a rematerialization strategy based on inter- and intra-core that maximizes the utilization of the NPU architecture. In a cross-architectural comparison against the state-of-the-art FlashLinearAttention (FLA) on an Nvidia GPU of comparable computational capacity, our evaluation achieves a speedup of up to 3.39 × and a geometric mean speedup of 1.73 ×, while reducing peak memory consumption by approximately 33%.

For image super-resolution (SR), bridging the gap between the performance on synthetic datasets and real-world degradation scenarios remains a challenge. This work introduces a novel “Low-Res Leads the Way” (LWay) training framework, merging Supervised Pre-training with Self-supervised Learning to enhance the adaptability of SR models to real-world images. Our approach utilizes a low-resolution (LR) reconstruction network to extract degradation embeddings from LR images, merging them with super-resolved outputs for LR reconstruction. Leveraging unseen LR images for self-supervised learning guides the model to adapt its modeling space to the target domain, facili-tating fine-tuning of SR models without requiring paired high-resolution (HR) images. The integration of Discrete Wavelet Transform (DWT)further refines the focus on high-frequency details. Extensive evaluations show that our method significantly improves the generalization and de-tail restoration capabilities of SR models on unseen real-world datasets, outperforming existing methods. Our training regime is universally compatible, requiring no network architecture modifications, making it a practical solution for real-world SR applications.

Existing super-resolution (SR) models primarily focus on restoring local texture details, often neglecting the global semantic information within the scene. This oversight can lead to the omission of crucial semantic details or the intro-duction of inaccurate textures during the recovery process. In our work, we introduce the Cognitive Super-Resolution (CoSeR) framework, empowering SR models with the ca-pacity to comprehend low-resolution images. We achieve this by marrying image appearance and language under-standing to generate a cognitive embedding, which not only activates prior information from large text-to-image diffusion models but also facilitates the generation of high-quality reference images to optimize the SR process. To fur-ther improve image fidelity, we propose a novel condition injection scheme called “Ali-in-Attention ”, consolidating all conditional information into a single module. Conse-quently, our method successfully restores semantically cor-rect and photorealistic details, demonstrating state-of-the-art performance across multiple benchmarks. Project page: https://coser-main.github.io/

Image representation is critical for many visual tasks. Instead of representing images discretely with 2D arrays of pixels, a recent study, namely local implicit image function (LIIF), denotes images as a continuous function where pixel values are expansion by using the corresponding coordinates as inputs. Due to its continuous nature, LIIF can be adopted for arbitrary-scale image super-resolution tasks, resulting in a single effective and efficient model for various up-scaling factors. However, LIIF often suffers from structural distortions and ringing artifacts around edges, mostly because all pixels share the same model, thus ignoring the local properties of the image. In this paper, we propose a novel adaptive local image function (A-LIIF) to alleviate this problem. Specifically, our A-LIIF consists of two main components: an encoder and a expansion network. The former captures cross-scale image features, while the latter models the continuous up-scaling function by a weighted combination of multiple local implicit image functions. Accordingly, our A-LIIF can reconstruct the high-frequency textures and structures more accurately. Experiments on multiple benchmark datasets verify the effectiveness of our method. Our codes are available at https://github.com/LeeHW-THU/A-LIIF.

Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring. However, CNN-based methods show limitations in capturing long-range dependencies and modeling non-local self-similarity. In this paper, we propose a novel framework, Flow-Guided Sparse Transformer (FGST), for video deblurring. In FGST, we customize a self-attention module, Flow-Guided Sparse Window-based Multi-head Self-Attention (FGSW-MSA). For each $query$ element on the blurry reference frame, FGSW-MSA enjoys the guidance of the estimated optical flow to globally sample spatially sparse yet highly related $key$ elements corresponding to the same scene patch in neighboring frames. Besides, we present a Recurrent Embedding (RE) mechanism to transfer information from past frames and strengthen long-range temporal dependencies. Comprehensive experiments demonstrate that our proposed FGST outperforms state-of-the-art (SOTA) methods on both DVD and GOPRO datasets and yields visually pleasant results in real video deblurring. https://github.com/linjing7/VR-Baseline

How to properly model the inter-frame relation within the video sequence is an important but unsolved challenge for video restoration (VR). In this work, we propose an unsupervised flow-aligned sequence-to-sequence model (S2SVR) to address this problem. On the one hand, the sequence-to-sequence model, which has proven capable of sequence modeling in the field of natural language processing, is explored for the first time in VR. Optimized serialization modeling shows potential in capturing long-range dependencies among frames. On the other hand, we equip the sequence-to-sequence model with an unsupervised optical flow estimator to maximize its potential. The flow estimator is trained with our proposed unsupervised distillation loss, which can alleviate the data discrepancy and inaccurate degraded optical flow issues of previous flow-based methods. With reliable optical flow, we can establish accurate correspondence among multiple frames, narrowing the domain difference between 1D language and 2D misaligned frames and improving the potential of the sequence-to-sequence model. S2SVR shows superior performance in multiple VR tasks, including video deblurring, video super-resolution, and compressed video quality enhancement. https://github.com/linjing7/VR-Baseline

The majority of prevailing video interpolation methods compute flows to estimate the intermediate motion. However, accurate estimation of the intermediate motion is difficult with low-order motion model hypothesis, which induces enormous difficulties for subsequent processing. To alleviate the limitation, we propose a two-stage flow-free video interpolation architecture. Rather than utilizing pre-defined motion models, our method represents complex motion through data-driven learning. In the first stage, we analyze spatial-temporal information and generate coarse anchor frame features. In the second stage, we employ transformers to transfer neighboring features to the intermediate time steps and enhance the spatial textures. To improve the quality of coarse anchor frame features and the robustness in dealing with the multi-scale textures with large-scale motion, we propose a multi-scale architecture and transformers with variable token sizes to progressively enhance the features. The experimental results demonstrate that our model outperforms state-of-the-art methods for both single frame and multi frames interpolation tasks, and the extended ablation studies verify the effectiveness of our model.

The latest advances in full-reference image quality assessment (IQA) involve unifying structure and texture similarity based on deep representations. The resulting Deep Image Structure and Texture Similarity (DISTS) metric, however, makes rather global quality measurements, ignoring the fact that natural photographic images are locally structured and textured across space and scale. In this paper, we describe a locally adaptive structure and texture similarity index for full-reference IQA, which we term A-DISTS. Specifically, we rely on a single statistical feature, namely the dispersion index, to localize texture regions at different scales. The estimated probability (of one patch being texture) is in turn used to adaptively pool local structure and texture measurements. The resulting A-DISTS is adapted to local image content, and is free of expensive human perceptual scores for supervised training. We demonstrate the advantages of A-DISTS in terms of correlation with human data on ten IQA databases and optimization of single image super-resolution methods.

We present automated techniques for the verification and control of partially observable, probabilistic systems for both discrete and dense models of time. For the discrete-time case, we formally model these systems using partially observable Markov decision processes; for dense time, we propose an extension of probabilistic timed automata in which local states are partially visible to an observer or controller. We give probabilistic temporal logics that can express a range of quantitative properties of these models, relating to the probability of an event’s occurrence or the expected value of a reward measure. We then propose techniques to either verify that such a property holds or synthesise a controller for the model which makes it true. Our approach is based on a grid-based abstraction of the uncountable belief space induced by partial observability and, for dense-time models, an integer discretisation of real-time behaviour. The former is necessarily approximate since the underlying problem is undecidable, however we show how both lower and upper bounds on numerical results can be generated. We illustrate the effectiveness of the approach by implementing it in the PRISM model checker and applying it to several case studies from the domains of task and network scheduling, computer security and planning.