论文检索

Zhaoyang Wang, Dongyang Li, Mingyang Zhang, Hao Luo, Maoguo Gong

Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to effectively capture the complex spectral-spatial relationships and low-level details, while diffusion models represent a promising generative model known for their exceptional performance in modeling complex relations and learning high and low-level visual features. The direct application of diffusion models to HSI SR is hampered by challenges such as difficulties in model convergence and protracted inference time. In this work, we introduce a novel Group-Autoencoder (GAE) framework that synergistically combines with the diffusion model to construct a highly effective HSI SR model (DMGASR). Our proposed GAE framework encodes high-dimensional HSI data into low-dimensional latent space where the diffusion model works, thereby alleviating the difficulty of training the diffusion model while maintaining band correlation and considerably reducing inference time. Experimental results on both natural and remote sensing hyperspectral datasets demonstrate that the proposed method is superior to other state-of-the-art methods both visually and metrically.

Ruichen Wang, Zekang Chen, Chen Chen, Jian Ma, Haonan Lu, Xiaodong Lin

Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited compositional capabilities, leading to attribute leakage, entity leakage, and missing entities. In this paper, we propose a novel attention mask control strategy based on predicted object boxes to address these issues. In particular, we first train a BoxNet to predict a box for each entity that possesses the attribute specified in the prompt. Then, depending on the predicted boxes, a unique mask control is applied to the cross- and self-attention maps. Our approach produces a more semantically accurate synthesis by constraining the attention regions of each token in the prompt to the image. In addition, the proposed method is straightforward and effective and can be readily integrated into existing cross-attention-based T2I generators. We compare our approach to competing methods and demonstrate that it can faithfully convey the semantics of the original text to the generated content and achieve high availability as a ready-to-use plugin. Please refer to https://github.com/OPPO-Mente-Lab/attention-mask-control.

Chenyang Wang, Junjun Jiang, Kui Jiang, Xianming Liu

Human face captured at night or in dimly lit environments has become a common practice, accompanied by complex low-light and low-resolution degradations. However, the existing face super-resolution (FSR) technologies and derived cascaded schemes are inadequate to recover credible textures. In this paper, we propose a novel approach that decomposes the restoration task into face structural fidelity maintaining and texture consistency learning. The former aims to enhance the quality of face images while improving the structural fidelity, while the latter focuses on eliminating perturbations and artifacts caused by low-light degradation and reconstruction. Based on this, we develop a novel low-light low-resolution face super-resolution framework. Our method consists of two steps: an illumination correction face super-resolution network (IC-FSRNet) for lighting the face and recovering the structural information, and a detail enhancement model (DENet) for improving facial details, thus making them more visually appealing and easier to analyze. As the relighted regions could provide complementary information to boost face super-resolution and vice versa, we introduce the mutual learning to harness the informative components from relighted regions and reconstruction, and achieve the iterative refinement. In addition, DENet equipped with diffusion probabilistic model is built to further improve face image visual quality. Experiments demonstrate that the proposed joint optimization framework achieves significant improvements in reconstruction quality and perceptual quality over existing two-stage sequential solutions. Code is available at https://github.com/wcy-cs/IC-FSRDENet.

Zhangyong Tang, Tianyang Xu, Xiaojun Wu, Xue-Feng Zhu, Josef Kittler

Generative models (GMs) have received increasing research interest for their remarkable capacity to achieve comprehensive understanding. However, their potential application in the domain of multi-modal tracking has remained unexplored. In this context, we seek to uncover the potential of harnessing generative techniques to address the critical challenge, information fusion, in multi-modal tracking. In this paper, we delve into two prominent GM techniques, namely, Conditional Generative Adversarial Networks (CGANs) and Diffusion Models (DMs). Different from the standard fusion process where the features from each modality are directly fed into the fusion block, we combine these multi-modal features with random noise in the GM framework, effectively transforming the original training samples into harder instances. This design excels at extracting discriminative clues from the features, enhancing the ultimate tracking performance. Based on this, we conduct extensive experiments across two multi-modal tracking tasks, three baseline methods, and four challenging benchmarks. The experimental results demonstrate that the proposed generative-based fusion mechanism achieves state-of-the-art performance by setting new records on GTOT, LasHeR and RGBD1K. Code will be available at https://github.com/Zhangyong-Tang/GMMT.

Zhaorui Tan, Xi Yang, Kaizhu Huang

Data augmentation has been recently leveraged as an effective regularizer in various vision-language deep neural networks. However, in text-to-image synthesis (T2Isyn), current augmentation wisdom still suffers from the semantic mismatch between augmented paired data. Even worse, semantic collapse may occur when generated images are less semantically constrained. In this paper, we develop a novel Semantic-aware Data Augmentation (SADA) framework dedicated to T2Isyn. In particular, we propose to augment texts in the semantic space via an Implicit Textual Semantic Preserving Augmentation, in conjunction with a specifically designed Image Semantic Regularization Loss as Generated Image Semantic Conservation, to cope well with semantic mismatch and collapse. As one major contribution, we theoretically show that Implicit Textual Semantic Preserving Augmentation can certify better text-image consistency while Image Semantic Regularization Loss regularizing the semantics of generated images would avoid semantic collapse and enhance image quality. Extensive experiments validate that SADA enhances text-image consistency and improves image quality significantly in T2Isyn models across various backbones. Especially, incorporating SADA during the tuning process of Stable Diffusion models also yields performance improvements.

Shuai Tan, Bin Ji, Ye Pan

Although automatically animating audio-driven talking heads has recently received growing interest, previous efforts have mainly concentrated on achieving lip synchronization with the audio, neglecting two crucial elements for generating expressive videos: emotion style and art style. In this paper, we present an innovative audio-driven talking face generation method called Style2Talker. It involves two stylized stages, namely Style-E and Style-A, which integrate text-controlled emotion style and picture-controlled art style into the final output. In order to prepare the scarce emotional text descriptions corresponding to the videos, we propose a labor-free paradigm that employs large-scale pretrained models to automatically annotate emotional text labels for existing audio-visual datasets. Incorporating the synthetic emotion texts, the Style-E stage utilizes a large-scale CLIP model to extract emotion representations, which are combined with the audio, serving as the condition for an efficient latent diffusion model designed to produce emotional motion coefficients of a 3DMM model. Moving on to the Style-A stage, we develop a coefficient-driven motion generator and an art-specific style path embedded in the well-known StyleGAN. This allows us to synthesize high-resolution artistically stylized talking head videos using the generated emotional motion coefficients and an art style source picture. Moreover, to better preserve image details and avoid artifacts, we provide StyleGAN with the multi-scale content features extracted from the identity image and refine its intermediate feature maps by the designed content encoder and refinement network, respectively. Extensive experimental results demonstrate our method outperforms existing state-of-the-art methods in terms of audio-lip synchronization and performance of both emotion style and art style.

Sitong Su, Jianzhi Liu, Lianli Gao, Jingkuan Song

Recently Text-to-Video (T2V) synthesis has undergone a breakthrough by training transformers or diffusion models on large-scale datasets. Nevertheless, inferring such large models incurs huge costs. Previous inference acceleration works either require costly retraining or are model-specific. To address this issue, instead of retraining we explore the inference process of two mainstream T2V models using transformers and diffusion models. The exploration reveals the redundancy in temporal attention modules of both models, which are commonly utilized to establish temporal relations among frames. Consequently, we propose a training-free and generalized pruning strategy called F3-Pruning to prune redundant temporal attention weights. Specifically, when aggregate temporal attention values are ranked below a certain ratio, corresponding weights will be pruned. Extensive experiments on three datasets using a classic transformer-based model CogVideo and a typical diffusion-based model Tune-A-Video verify the effectiveness of F3-Pruning in inference acceleration, quality assurance and broad applicability.

Zifan Song, Guosheng Hu, Cairong Zhao

Text-based person search is a challenging task aimed at locating specific target pedestrians through text descriptions. Recent advancements have been made in this field, but there remains a deficiency in datasets tailored for text-based person search. The creation of new, real-world datasets is hindered by concerns such as the risk of pedestrian privacy leakage and the substantial costs of annotation. In this paper, we introduce a framework, named Diverse Person (DP), to achieve efficient and high-quality text-based person search data generation without involving privacy concerns. Specifically, we propose to leverage available images of clothing and accessories as reference attribute images to edit the original dataset images through diffusion models. Additionally, we employ a Large Language Model (LLM) to produce annotations that are both high in quality and stylistically consistent with those found in real-world datasets. Extensive experimental results demonstrate that the baseline models trained with our DP can achieve new state-of-the-art results on three public datasets, with performance improvements up to 4.82%, 2.15%, and 2.28% on CUHK-PEDES, ICFG-PEDES, and RSTPReid in terms of Rank-1 accuracy, respectively.

Jaeyoon Sim, Sooyeon Jeon, InJun Choi, Guorong Wu, Won Hwa Kim

Various Graph Neural Networks (GNN) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes excessively averaged as the number of hidden layers increases. The issue stems from the intrinsic formulation of conventional graph convolution where the nodal features are aggregated from a direct neighborhood per layer across the entire nodes in the graph. As setting different number of hidden layers per node is infeasible, recent works leverage a diffusion kernel to redefine the graph structure and incorporate information from farther nodes. Unfortunately, such approaches suffer from heavy diagonalization of a graph Laplacian or learning a large transform matrix. In this regards, we propose a diffusion learning framework where the range of feature aggregation is controlled by the scale of a diffusion kernel. For efficient computation, we derive closed-form derivatives of approximations of the graph convolution with respect to the scale, so that node-wise range can be adaptively learned.With a downstream classifier, the entire framework is made trainable in an end-to-end manner. Our model is tested on various standard datasets for node-wise classification for the state-of-the-art performance, and it is also validated on a real-world brain network data for graph classifications to demonstrate its practicality for Alzheimer classification.

Xiaolong Shen, Jianxin Ma, Chang Zhou, Zongxin Yang

Generating photorealistic 3D faces from given conditions is a challenging task. Existing methods often rely on time-consuming one-by-one optimization approaches, which are not efficient for modeling the same distribution content, e.g., faces. Additionally, an ideal controllable 3D face generation model should consider both facial attributes and expressions. Thus we propose a novel approach called TEx-Face(TExt & Expression-to-Face) that addresses these challenges by dividing the task into three components, i.e., 3D GAN Inversion, Conditional Style Code Diffusion, and 3D Face Decoding. For 3D GAN inversion, we introduce two methods, which aim to enhance the representation of style codes and alleviate 3D inconsistencies. Furthermore, we design a style code denoiser to incorporate multiple conditions into the style code and propose a data augmentation strategy to address the issue of insufficient paired visual-language data. Extensive experiments conducted on FFHQ, CelebA-HQ, and CelebA-Dialog demonstrate the promising performance of our TEx-Face in achieving the efficient and controllable generation of photorealistic 3D faces. The code will be publicly available.

Cuifeng Shen, Yulu Gan, Chen Chen, Xiongwei Zhu, Lele Cheng, Tingting Gao, Jinzhi Wang

The goal of conditional image-to-video (cI2V) generation is to create a believable new video by beginning with the condition, i.e., one image and text. The previous cI2V generation methods conventionally perform in RGB pixel space, with limitations in modeling motion consistency and visual continuity. Additionally, the efficiency of generating videos in pixel space is quite low. In this paper, we propose a novel approach to address these challenges by disentangling the target RGB pixels into two distinct components: spatial content and temporal motions. Specifically, we predict temporal motions which include motion vector and residual based on a 3D-UNet diffusion model. By explicitly modeling temporal motions and warping them to the starting image, we improve the temporal consistency of generated videos. This results in a reduction of spatial redundancy, emphasizing temporal details. Our proposed method achieves performance improvements by disentangling content and motion, all without introducing new structural complexities to the model. Extensive experiments on various datasets confirm our approach's superior performance over the majority of state-of-the-art methods in both effectiveness and efficiency.

Kai Shang, Mingwen Shao, Chao Wang, Yuanshuo Cheng, Shuigen Wang

Diffusion models have achieved remarkable progress in low-light image enhancement. However, there remain two practical limitations: (1) existing methods mainly focus on the spatial domain for the diffusion process, while neglecting the essential features in the frequency domain; (2) conventional patch-based sampling strategy inevitably leads to severe checkerboard artifacts due to the uneven overlapping. To address these limitations in one go, we propose a Multi-Domain Multi-Scale (MDMS) diffusion model for low-light image enhancement. In particular, we introduce a spatial-frequency fusion module to seamlessly integrates spatial and frequency information. By leveraging the Multi-Domain Learning (MDL) paradigm, our proposed model is endowed with the capability to adaptively facilitate noise distribution learning, thereby enhancing the quality of the generated images. Meanwhile, we propose a Multi-Scale Sampling (MSS) strategy that follows a divide-ensemble manner by merging the restored patches under different resolutions. Such a multi-scale learning paradigm explicitly derives patch information from different granularities, thus leading to smoother boundaries. Furthermore, we empirically adopt the Bright Channel Prior (BCP) which indicates natural statistical regularity as an additional restoration guidance. Experimental results on LOL and LOLv2 datasets demonstrate that our method achieves state-of-the-art performance for the low-light image enhancement task. Codes are available at https://github.com/Oliiveralien/MDMS.

Dvir Samuel, Rami Ben-Ari, Simon Raviv, Nir Darshan, Gal Chechik

Text-to-image diffusion models can synthesize high quality images, but they have various limitations. Here we highlight a common failure mode of these models, namely, generating uncommon concepts and structured concepts like hand palms. We show that their limitation is partly due to the long-tail nature of their training data: web-crawled data sets are strongly unbalanced, causing models to under-represent concepts from the tail of the distribution. We characterize the effect of unbalanced training data on text-to-image models and offer a remedy. We show that rare concepts can be correctly generated by carefully selecting suitable generation seeds in the noise space, using a small reference set of images, a technique that we call SeedSelect. SeedSelect does not require retraining or finetuning the diffusion model. We assess the faithfulness, quality and diversity of SeedSelect in creating rare objects and generating complex formations like hand images, and find it consistently achieves superior performance. We further show the advantage of SeedSelect in semantic data augmentation. Generating semantically appropriate images can successfully improve performance in few-shot recognition benchmarks, for classes from the head and from the tail of the training data of diffusion models.

Zhiyao Ren, Yibing Zhan, Liang Ding, Gaoang Wang, Chaoyue Wang, Zhongyi Fan, Dacheng Tao

Denoising Diffusion Probabilistic Models (DDPMs) have achieved significant success in generation tasks. Nevertheless, the exposure bias issue, i.e., the natural discrepancy between the training (the output of each step is calculated individually by a given input) and inference (the output of each step is calculated based on the input iteratively obtained based on the model), harms the performance of DDPMs. To our knowledge, few works have tried to tackle this issue by modifying the training process for DDPMs, but they still perform unsatisfactorily due to 1) partially modeling the discrepancy and 2) ignoring the prediction error accumulation. To address the above issues, in this paper, we propose a multi-step denoising scheduled sampling (MDSS) strategy to alleviate the exposure bias for DDPMs. Analyzing the formulations of the training and inference of DDPMs, MDSS 1) comprehensively considers the discrepancy influence of prediction errors on the output of the model (the Gaussian noise) and the output of the step (the calculated input signal of the next step), and 2) efficiently models the prediction error accumulation by using multiple iterations of a mathematical formulation initialized from one-step prediction error obtained from the model. The experimental results, compared with previous works, demonstrate that our approach is more effective in mitigating exposure bias in DDPM, DDIM, and DPM-solver. In particular, MDSS achieves an FID score of 3.86 in 100 sample steps of DDIM on the CIFAR-10 dataset, whereas the second best obtains 4.78. The code will be available on GitHub.

Yiming Qin, Nanxuan Zhao, Bin Sheng, Rynson W.H. Lau

Regenerating urban layout is an essential process for urban regeneration. In this paper, we propose a new task called text-driven urban layout regeneration, which provides an intuitive input modal - text - for users to specify the regeneration, instead of designing complex rules. Given the target region to be regenerated, we propose a one-stage text-driven urban layout regeneration model, Text2City, to jointly and progressively regenerate the urban layout (i.e., road and building layouts) based on textual layout descriptions and surrounding context (i.e., urban layouts and functions of the surrounding regions). Text2City first extracts road and building attributes from the textual layout description to guide the regeneration. It includes a novel one-stage joint regenerator network based on the conditioned denoising diffusion probabilistic models (DDPMs) and prior knowledge exchange. To harmonize the regenerated layouts through joint optimization, we propose the interactive & enhanced guidance module for self-enhancement and prior knowledge exchange between road and building layouts during the regeneration. We also design a series of constraints from attribute-, geometry- and pixel-levels to ensure rational urban layout generation. To train our model, we build a large-scale dataset containing urban layouts and layout descriptions, covering 147K regions. Qualitative and quantitative evaluations show that our proposed method outperforms the baseline methods in regenerating desirable urban layouts that meet the textual descriptions.

Yuming Qiao, Fanyi Wang, Jingwen Su, Yanhao Zhang, Yunjie Yu, Siyu Wu, Guo-Jun Qi

Image editing approaches with diffusion models have been rapidly developed, yet their applicability are subject to requirements such as specific editing types (e.g., foreground or background object editing, style transfer), multiple conditions (e.g., mask, sketch, caption), and time consuming fine-tuning of diffusion models. For alleviating these limitations and realizing efficient real image editing, we propose a novel editing technique that only requires an input image and target text for various editing types including non-rigid edits without fine-tuning diffusion model. Our method contains three novelties: (I) Target-text Inversion Schedule (TTIS) is designed to fine-tune the input target text embedding to achieve fast image reconstruction without image caption and acceleration of convergence. (II) Progressive Transition Scheme applies progressive linear interpolation between target text embedding and its fine-tuned version to generate transition embedding for maintaining non-rigid editing capability. (III) Balanced Attention Module (BAM) balances the tradeoff between textual description and image semantics. By the means of combining self-attention map from reconstruction process and cross-attention map from transition process, the guidance of target text embeddings in diffusion process is optimized. In order to demonstrate editing capability, effectiveness and efficiency of the proposed BARET, we have conducted extensive qualitative and quantitative experiments. Moreover, results derived from user study and ablation study further prove the superiority over other methods.

Bo Peng, Xinyuan Chen, Yaohui Wang, Chaochao Lu, Yu Qiao

Recent works have successfully extended large-scale text-to-image models to the video domain, producing promising results but at a high computational cost and requiring a large amount of video data. In this work, we introduce ConditionVideo, a training-free approach to text-to-video generation based on the provided condition, video, and input text, by leveraging the power of off-the-shelf text-to-image generation methods (e.g., Stable Diffusion). ConditionVideo generates realistic dynamic videos from random noise or given scene videos. Our method explicitly disentangles the motion representation into condition-guided and scenery motion components. To this end, the ConditionVideo model is designed with a UNet branch and a control branch. To improve temporal coherence, we introduce sparse bi-directional spatial-temporal attention (sBiST-Attn). The 3D control network extends the conventional 2D controlnet model, aiming to strengthen conditional generation accuracy by additionally leveraging the bi-directional frames in the temporal domain. Our method exhibits superior performance in terms of frame consistency, clip score, and conditional accuracy, outperforming other compared methods.

Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan

The incredible generative ability of large-scale text-to-image (T2I) models has demonstrated strong power of learning complex structures and meaningful semantics. However, relying solely on text prompts cannot fully take advantage of the knowledge learned by the model, especially when flexible and accurate controlling (e.g., structure and color) is needed. In this paper, we aim to ``dig out" the capabilities that T2I models have implicitly learned, and then explicitly use them to control the generation more granularly. Specifically, we propose to learn low-cost T2I-Adapters to align internal knowledge in T2I models with external control signals, while freezing the original large T2I models. In this way, we can train various adapters according to different conditions, achieving rich control and editing effects in the color and structure of the generation results. Further, the proposed T2I-Adapters have attractive properties of practical value, such as composability and generalization ability. Extensive experiments demonstrate that our T2I-Adapter has promising generation quality and a wide range of applications. Our code is available at https://github.com/TencentARC/T2I-Adapter.

Zhiyuan Ma, Guoli Jia, Bowen Zhou

With the great success of text-conditioned diffusion models in creative text-to-image generation, various text-driven image editing approaches have attracted the attentions of many researchers. However, previous works mainly focus on discreteness-sensitive instructions such as adding, removing or replacing specific objects, background elements or global styles (i.e., “hard editing”), while generally ignoring subject-binding but semantically fine-changing continuity-sensitive instructions such as actions, poses or adjectives, and so on (i.e., “soft editing”), which hampers generative AI from generating user-customized visual contents. To mitigate this predicament, we propose a spatio-temporal guided adaptive editing algorithm AdapEdit, which realizes adaptive image editing by introducing a soft-attention strategy to dynamically vary the guiding degree from the editing conditions to visual pixels from both temporal and spatial perspectives. Note our approach has a significant advantage in preserving model priors and does not require model training, fine-tuning, extra data, or optimization. We present our results over a wide variety of raw images and editing instructions, demonstrating competitive performance and showing it significantly outperforms the previous approaches. Code is available: https://github.com/AnonymousPony/adap-edit.

Zhiyuan Ma, Zhihuan Yu, Jianjun Li, Bowen Zhou

As a class of fruitful approaches, diffusion probabilistic models (DPMs) have shown excellent advantages in high-resolution image reconstruction. On the other hand, masked autoencoders (MAEs), as popular self-supervised vision learners, have demonstrated simpler and more effective image reconstruction and transfer capabilities on downstream tasks. However, they all require extremely high training costs, either due to inherent high temporal-dependence (i.e., excessively long diffusion steps) or due to artificially low spatial-dependence (i.e., human-formulated high mask ratio, such as 0.75). To the end, this paper presents LMD, a faster image reconstruction framework with Latent Masking Diffusion. First, we propose to project and reconstruct images in latent space through a pre-trained variational autoencoder, which is theoretically more efficient than in the pixel-based space. Then, we combine the advantages of MAEs and DPMs to design a progressive masking diffusion model, which gradually increases the masking proportion by three different schedulers and reconstructs the latent features from simple to difficult, without sequentially performing denoising diffusion as in DPMs or using fixed high masking ratio as in MAEs, so as to alleviate the high training time-consumption predicament. Our approach allows for learning high-capacity models and accelerate their training (by 3x or more) and barely reduces the original accuracy. Inference speed in downstream tasks also significantly outperforms the previous approaches.