EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation

Recently, Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated metrics have emerged to evaluate the image-text alignment capabilities of generative models. However, the performance comparison among these automated metrics is limited by existing small datasets. Additionally, these datasets lack the capacity to assess the performance of automated metrics at a fine-grained level. In this study, we contribute an EvalMuse-40K benchmark, gathering 40K image-text pairs with fine-grained human annotations for image-text alignment-related tasks. In the construction process, we employ various strategies such as balanced prompt sampling and data re-annotation to ensure the diversity and reliability of our benchmark. This allows us to comprehensively evaluate the effectiveness of image-text alignment metrics for T2I models. Meanwhile, we introduce two new methods to evaluate the image-text alignment capabilities of T2I models: FGA-BLIP2 which involves end-to-end fine-tuning of a vision-language model to produce fine-grained image-text alignment scores and PN-VQA which adopts a novel positive-negative VQA manner in VQA models for zero-shot fine-grained evaluation. Both methods achieve impressive performance in image-text alignment evaluations. We also use our methods to rank current AIGC models, in which the results can serve as a reference source for future study and promote the development of T2I generation. The data and code will be made publicly available.

DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts

Image retouching aims to enhance the visual quality of photos. Considering the different aesthetic preferences of users, the target of retouching is subjective. However, current retouching methods mostly adopt deterministic models, which not only neglects the style diversity in the expert-retouched results and tends to learn an average style during training, but also lacks sample diversity during inference. In this paper, we propose a diffusion-based method, named DiffRetouch. Thanks to the excellent distribution modeling ability of diffusion, our method can capture the complex fine-retouched distribution covering various visual-pleasing styles in the training data. Moreover, four image attributes are made adjustable to provide a user-friendly editing mechanism. By adjusting these attributes in specified ranges, users are allowed to customize preferred styles within the learned fine-retouched distribution. Additionally, the affine bilateral grid and contrastive learning scheme are introduced to handle the problem of texture distortion and control insensitivity respectively. Extensive experiments have demonstrated the superior performance of our method on visually appealing and sample diversity. The code will be made available to the community.

MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results

The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). Building on the achievements of the previous MIPI Workshops held at ECCV 2022 and CVPR 2023, we introduce our third MIPI challenge including three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Few-shot RAW Image Denoising track on MIPI 2024. In total, 165 participants were successfully registered, and 7 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art erformance on Few-shot RAW Image Denoising. More details of this challenge and the link to the dataset can be found at https://mipichallenge.org/MIPI2024.

The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report

This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes. The task of this challenge is to super-resolve an input image with a magnification factor of x4 based on pairs of low and corresponding high-resolution images. The primary objective is to develop networks that optimize various aspects such as runtime, parameters, and FLOPs, while still maintaining a peak signal-to-noise ratio (PSNR) of approximately 26.90 dB on the DIV2K_LSDIR_valid dataset and 26.99 dB on the DIV2K_LSDIR_test dataset. In addition, this challenge has 4 tracks including the main track (overall performance), sub-track 1 (runtime), sub-track 2 (FLOPs), and sub-track 3 (parameters). In the main track, all three metrics (ie runtime, FLOPs, and parameter count) were considered. The ranking of the main track is calculated based on a weighted sum-up of the scores of all other sub-tracks. In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking. In sub-track 2, the number of FLOPs was considered. The score calculated based on the corresponding FLOPs was used to determine the ranking. In sub-track 3, the number of parameters was considered. The score calculated based on the corresponding parameters was used to determine the ranking. RLFN is set as the baseline for efficiency measurement. The challenge had 262 registered participants, and 34 teams made valid submissions. They gauge the state-of-the-art in efficient single-image super-resolution. To facilitate the reproducibility of the challenge and enable other researchers to build upon these findings, the code and the pre-trained model of validated solutions are made publicly available at https://github.com/Amazingren/NTIRE2024_ESR/.

The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation

Guided depth super-resolution (GDSR) involves restoring missing depth details using the high-resolution RGB image of the same scene. Previous approaches have struggled with the heterogeneity and complementarity of the multi-modal inputs, and neglected the issues of modal misalignment, geometrical misalignment, and feature selection. In this study, we rethink some essential components in GDSR networks and propose a simple yet effective Dynamic Dual Alignment and Aggregation network (D2A2). D2A2 mainly consists of 1) a dynamic dual alignment module that adapts to alleviate the modal misalignment via a learnable domain alignment block and geometrically align cross-modal features by learning the offset; and 2) a mask-to-pixel feature aggregate module that uses the gated mechanism and pixel attention to filter out irrelevant texture noise from RGB features and combine the useful features with depth features. By combining the strengths of RGB and depth features while minimizing disturbance introduced by the RGB image, our method with simple reuse and redesign of basic components achieves state-of-the-art performance on multiple benchmark datasets. The code is available at https://github.com/JiangXinni/D2A2.

LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation

With the impressive progress in diffusion-based text-to-image generation, extending such powerful generative ability to text-to-video raises enormous attention. Existing methods either require large-scale text-video pairs and a large number of training resources or learn motions that are precisely aligned with template videos. It is non-trivial to balance a trade-off between the degree of generation freedom and the resource costs for video generation. In our study, we present a few-shot-based tuning framework, LAMP, which enables text-to-image diffusion model Learn A specific Motion Pattern with 8~16 videos on a single GPU. Specifically, we design a first-frame-conditioned pipeline that uses an off-the-shelf text-to-image model for content generation so that our tuned video diffusion model mainly focuses on motion learning. The well-developed text-to-image techniques can provide visually pleasing and diverse content as generation conditions, which highly improves video quality and generation freedom. To capture the features of temporal dimension, we expand the pretrained 2D convolution layers of the T2I model to our novel temporal-spatial motion learning layers and modify the attention blocks to the temporal level. Additionally, we develop an effective inference trick, shared-noise sampling, which can improve the stability of videos with computational costs. Our method can also be flexibly applied to other tasks, e.g. real-world image animation and video editing. Extensive experiments demonstrate that LAMP can effectively learn the motion pattern on limited data and generate high-quality videos. The code and models are available at https://rq-wu.github.io/projects/LAMP.

Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising

Calibration-based methods have dominated RAW image denoising under extremely low-light environments. However, these methods suffer from several main deficiencies: 1) the calibration procedure is laborious and time-consuming, 2) denoisers for different cameras are difficult to transfer, and 3) the discrepancy between synthetic noise and real noise is enlarged by high digital gain. To overcome the above shortcomings, we propose a calibration-free pipeline for Lighting Every Drakness (LED), regardless of the digital gain or camera sensor. Instead of calibrating the noise parameters and training repeatedly, our method could adapt to a target camera only with few-shot paired data and fine-tuning. In addition, well-designed structural modification during both stages alleviates the domain gap between synthetic and real noise without any extra computational cost. With 2 pairs for each additional digital gain (in total 6 pairs) and 0.5% iterations, our method achieves superior performance over other calibration-based methods. Our code is available at https://github.com/Srameo/LED .

Random Weights Networks Work as Loss Prior Constraint for Image Restoration

In this paper, orthogonal to the existing data and model studies, we instead resort our efforts to investigate the potential of loss function in a new perspective and present our belief ``Random Weights Networks can Be Acted as Loss Prior Constraint for Image Restoration''. Inspired by Functional theory, we provide several alternative solutions to implement our belief in the strict mathematical manifolds including Taylor's Unfolding Network, Invertible Neural Network, Central Difference Convolution and Zero-order Filtering as ``random weights network prototype'' with respect of the following four levels: 1) the different random weights strategies; 2) the different network architectures, \emph{eg,} pure convolution layer or transformer; 3) the different network architecture depths; 4) the different numbers of random weights network combination. Furthermore, to enlarge the capability of the randomly initialized manifolds, we devise the manner of random weights in the following two variants: 1) the weights are randomly initialized only once during the whole training procedure; 2) the weights are randomly initialized at each training iteration epoch. Our propose belief can be directly inserted into existing networks without any training and testing computational cost. Extensive experiments across multiple image restoration tasks, including image de-noising, low-light image enhancement, guided image super-resolution demonstrate the consistent performance gains obtained by introducing our belief. To emphasize, our main focus is to spark the realms of loss function and save their current neglected status. Code will be publicly available.

Unlocking Masked Autoencoders as Loss Function for Image and Video Restoration

Image and video restoration has achieved a remarkable leap with the advent of deep learning. The success of deep learning paradigm lies in three key components: data, model, and loss. Currently, many efforts have been devoted to the first two while seldom study focuses on loss function. With the question ``are the de facto optimization functions e.g., $L_1$, $L_2$, and perceptual losses optimal?'', we explore the potential of loss and raise our belief ``learned loss function empowers the learning capability of neural networks for image and video restoration''. Concretely, we stand on the shoulders of the masked Autoencoders (MAE) and formulate it as a `learned loss function', owing to the fact the pre-trained MAE innately inherits the prior of image reasoning. We investigate the efficacy of our belief from three perspectives: 1) from task-customized MAE to native MAE, 2) from image task to video task, and 3) from transformer structure to convolution neural network structure. Extensive experiments across multiple image and video tasks, including image denoising, image super-resolution, image enhancement, guided image super-resolution, video denoising, and video enhancement, demonstrate the consistent performance improvements introduced by the learned loss function. Besides, the learned loss function is preferable as it can be directly plugged into existing networks during training without involving computations in the inference stage. Code will be publicly available.

BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer

In this work, we propose a Robust, Efficient, and Component-specific makeup transfer method (abbreviated as BeautyREC). A unique departure from prior methods that leverage global attention, simply concatenate features, or implicitly manipulate features in latent space, we propose a component-specific correspondence to directly transfer the makeup style of a reference image to the corresponding components (e.g., skin, lips, eyes) of a source image, making elaborate and accurate local makeup transfer. As an auxiliary, the long-range visual dependencies of Transformer are introduced for effective global makeup transfer. Instead of the commonly used cycle structure that is complex and unstable, we employ a content consistency loss coupled with a content encoder to implement efficient single-path makeup transfer. The key insights of this study are modeling component-specific correspondence for local makeup transfer, capturing long-range dependencies for global makeup transfer, and enabling efficient makeup transfer via a single-path structure. We also contribute BeautyFace, a makeup transfer dataset to supplement existing datasets. This dataset contains 3,000 faces, covering more diverse makeup styles, face poses, and races. Each face has annotated parsing map. Extensive experiments demonstrate the effectiveness of our method against state-of-the-art methods. Besides, our method is appealing as it is with only 1M parameters, outperforming the state-of-the-art methods (BeautyGAN: 8.43M, PSGAN: 12.62M, SCGAN: 15.30M, CPM: 9.24M, SSAT: 10.48M).