Equipping Diffusion Models with Differentiable Spatial Entropy for Low-Light Image Enhancement

Image restoration, which aims to recover high-quality images from their corrupted counterparts, often faces the challenge of being an ill-posed problem that allows multiple solutions for a single input. However, most deep learning based works simply employ l1 loss to train their network in a deterministic way, resulting in over-smoothed predictions with inferior perceptual quality. In this work, we propose a novel method that shifts the focus from a deterministic pixel-by-pixel comparison to a statistical perspective, emphasizing the learning of distributions rather than individual pixel values. The core idea is to introduce spatial entropy into the loss function to measure the distribution difference between predictions and targets. To make this spatial entropy differentiable, we employ kernel density estimation (KDE) to approximate the probabilities for specific intensity values of each pixel with their neighbor areas. Specifically, we equip the entropy with diffusion models and aim for superior accuracy and enhanced perceptual quality over l1 based noise matching loss. In the experiments, we evaluate the proposed method for low light enhancement on two datasets and the NTIRE challenge 2024. All these results illustrate the effectiveness of our statistic-based entropy loss. Code is available at https://github.com/shermanlian/spatial-entropy-loss.

BokehOrNot: Transforming Bokeh Effect with Image Transformer and Lens Metadata Embedding

Bokeh effect is an optical phenomenon that offers a pleasant visual experience, typically generated by high-end cameras with wide aperture lenses. The task of bokeh effect transformation aims to produce a desired effect in one set of lenses and apertures based on another combination. Current models are limited in their ability to render a specific set of bokeh effects, primarily transformations from sharp to blur. In this paper, we propose a novel universal method for embedding lens metadata into the model and introducing a loss calculation method using alpha masks from the newly released Bokeh Effect Transformation Dataset(BETD) [3]. Based on the above techniques, we propose the BokehOrNot model, which is capable of producing both blur-to-sharp and sharp-to-blur bokeh effect with various combinations of lenses and aperture sizes. Our proposed model outperforms current leading bokeh rendering and image restoration models and renders visually natural bokeh effects. Our code is available at: https://github.com/indicator0/bokehornot.

Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

Sliding Window Recurrent Network for Efficient Video Super-Resolution

Video super-resolution (VSR) is the task of restoring high-resolution frames from a sequence of low-resolution inputs. Different from single image super-resolution, VSR can utilize frames' temporal information to reconstruct results with more details. Recently, with the rapid development of convolution neural networks (CNN), the VSR task has drawn increasing attention and many CNN-based methods have achieved remarkable results. However, only a few VSR approaches can be applied to real-world mobile devices due to the computational resources and runtime limitations. In this paper, we propose a \textit{Sliding Window based Recurrent Network} (SWRN) which can be real-time inference while still achieving superior performance. Specifically, we notice that video frames should have both spatial and temporal relations that can help to recover details, and the key point is how to extract and aggregate information. Address it, we input three neighboring frames and utilize a hidden state to recurrently store and update the important temporal information. Our experiment on REDS dataset shows that the proposed method can be well adapted to mobile devices and produce visually pleasant results.

Kernel-aware Raw Burst Blind Super-Resolution

Burst super-resolution (SR) provides a possibility of restoring rich details from low-quality images. However, since low-resolution (LR) images in practical applications have multiple complicated and unknown degradations, existing non-blind (e.g., bicubic) designed networks usually lead to a severe performance drop in recovering high-resolution (HR) images. Moreover, handling multiple misaligned noisy raw inputs is also challenging. In this paper, we address the problem of reconstructing HR images from raw burst sequences acquired from modern handheld devices. The central idea is a kernel-guided strategy which can solve the burst SR with two steps: kernel modeling and HR restoring. The former estimates burst kernels from raw inputs, while the latter predicts the super-resolved image based on the estimated kernels. Furthermore, we introduce a kernel-aware deformable alignment module which can effectively align the raw images with consideration of the blurry priors. Extensive experiments on synthetic and real-world datasets demonstrate that the proposed method can perform favorable state-of-the-art performance in the burst SR problem.