Image-generative artificial intelligence (AI) has garnered significant attention in recent years. In particular, the diffusion model, a core component of generative AI, produces high-quality images with rich diversity. In this study, we proposed a novel computed tomography (CT) reconstruction method by combining the denoising diffusion probabilistic model with iterative CT reconstruction. In sharp contrast to previous studies, we optimized the fidelity loss of CT reconstruction with respect to the latent variable of the diffusion model, instead of the image and model parameters. To suppress the changes in anatomical structures produced by the diffusion model, we shallowed the diffusion and reverse processes and fixed a set of added noises in the reverse process to make it deterministic during the inference. We demonstrated the effectiveness of the proposed method through the sparse-projection CT reconstruction of 1/10 projection data. Despite the simplicity of the implementation, the proposed method has the potential to reconstruct high-quality images while preserving the patient's anatomical structures and was found to outperform existing methods, including iterative reconstruction, iterative reconstruction with total variation, and the diffusion model alone in terms of quantitative indices such as the structural similarity index and peak signal-to-noise ratio. We also explored further sparse-projection CT reconstruction using 1/20 projection data with the same trained diffusion model. As the number of iterations increased, the image quality improved comparable to that of 1/10 sparse-projection CT reconstruction. In principle, this method can be widely applied not only to CT but also to other imaging modalities.
Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations
School of Computational Science and Engineering, Georgia Institute of Technology（计算科学与工程学院，佐治亚理工学院）；Environmental Science Division, Argonne National Laboratory（环境科学部，阿贡国家实验室）
We present a sound and complete algorithm, called iterative causal discovery (ICD), for recovering causal graphs in the presence of latent confounders and selection bias. ICD relies on the causal Markov and faithfulness assumptions and recovers the equivalence class of the underlying causal graph. It starts with a complete graph, and consists of a single iterative stage that gradually refines this graph by identifying conditional independence (CI) between connected nodes. Independence and causal relations entailed after any iteration are correct, rendering ICD anytime. Essentially, we tie the …
Recently, the power of unconditional image synthesis has significantly advanced through the use of Generative Adversarial Networks (GANs). The task of inverting an image into its corresponding latent code of the trained GAN is of utmost importance as it allows for the manipulation of real images, leveraging the rich semantics learned by the network. Recognizing the limitations of current inversion approaches, in this work we present a novel inversion scheme that extends current encoder-based inversion methods by introducing an iterative refinement mechanism. Instead of directly predicting the …
Latent Iterative Refinement Flow: A Geometric Constrained Approach for Few-Shot Generation
School of Mathematics（数学学院）；Statistics, Huazhong University of Science（统计学，华中科技大学）；School of Electronic Information（电子信息学院）；Communications, Huazhong University of Science（通信学院，华中科技大学）；Center for Mathematical Science, Huazhong University of Science（数学科学中心，华中科技大学）；Huawei（华为）
Geometric Intelligence（几何智能）；Uber AI Labs（优步人工智能实验室）；University of Wyoming（怀俄明大学）；Montreal Institute for Learning Algorithms（蒙特利尔学习算法研究所）；University of Freiburg（弗莱堡大学）
Generating high-resolution, photo-realistic images has been a long-standing goal in machine learning. Recently, Nguyen et al. (2016) showed one interesting way to synthesize novel images by performing gradient ascent in the latent space of a generator network to maximize the activations of one or multiple neurons in a separate classifier network. In this paper we extend this method by introducing an additional prior on the latent code, improving both sample quality and sample diversity, leading to a state-of-the-art generative model that produces high quality images at higher resolutions (227x…
A Markovian View of Iterative-Feedback Loops in Image Generative Models: Neural Resonance and Model Collapse
Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA（印第安纳大学信息学、计算与工程学院）；Department of Computer Science, Stonehill College, Easton, MA, USA（石溪学院计算机科学系）
South China University of Technology（华南理工大学）；Tencent（腾讯）；Cardiff University（卡迪夫大学）；The University of Hong Kong（香港大学）
We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer from the entangled semantics of the latent space. We explicitly disentangle the latent semantics by utilizing the progressive nature of the generator, deriving structure attributes from the shallow layers and appearance attributes from the deeper ones. Identity and pose information within the structure attributes are further separated by introducing a landmark…
Carnegie Mellon University（卡内基梅隆大学）；Courant Institute of Mathematical Sciences, New York University（纽约大学柯朗数学研究所）；University of Southern California（南加州大学）；University of Pennsylvania（宾夕法尼亚大学）
University of Amsterdam（阿姆斯特丹大学）；Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative Adversarial Networks that synthesize unseen class features by leveraging class-specific semantic embeddings. During training, they generate semantically consistent features, but discard this constraint during feature synthesis and classification. We propose to enforce semantic consistency at all stages of (generalized) zero-shot learning: training, feature …
Singing voice synthesis (SVS) systems are built to synthesize high-quality and expressive singing voice, in which the acoustic model generates the acoustic features (e.g., mel-spectrogram) given a music score. Previous singing acoustic models adopt a simple loss (e.g., L1 and L2) or generative adversarial network (GAN) to reconstruct the acoustic features, while they suffer from over-smoothing and unstable training issues respectively, which hinder the naturalness of synthesized singing. In this work, we propose DiffSinger, an acoustic model for SVS based on the diffusion probabilistic model. …
IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images
School of Information Engineering, Guangdong University of Technology（广东工业大学信息工程学院）；CRRC Academy Co., Ltd.（中车研究院有限公司）；School of Computer Science, Sun Yat-sen University（中山大学计算机学院）
IterInv: Iterative Inversion for Pixel-Level T2I Models
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Optics and Electronics（光电技术研究所）；Computer Vision Center（计算机视觉中心）；Universitat Autonoma de Barcelona（巴塞罗那自治大学）
California Institute of Technology（加州理工学院）；Disney Research（迪士尼研究院）
Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By replacing conventional optimization-based inference with a learned model, inference is amortized over data examples and therefore more computationally efficient. However, standard inference models are restricted to direct mappings from data to approximate posterior estimates. The failure of these models to reach fully optimized approximate posterior estimates results in an amortization gap. We aim toward closing this gap …
We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Powered by the iterative latent cross-attention of Perceiver, our framework scales with linear complexity, in contrast to the quadratic complexity of self-attention used in many state-of-the-art transformer-based models. To further improve the efficiency of our framework, we also study applying LayerDrop on cross-attention layers and introduce a mixed-stream architecture for cross-modal retrieval. We evaluate Perceiver-VL on diverse video-text and i…
RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement
German Cancer Research Center (DKFZ)（德国癌症研究中心）；Helmholtz Information and Data Science School for Health（亥姆霍兹健康信息与数据科学学院）；Helmholtz Imaging（亥姆霍兹影像中心）；University of Freiburg（弗莱堡大学）；Latent Labs；National Center for Tumor Diseases (NCT)（国家肿瘤疾病中心）；Heidelberg University Hospital（海德堡大学医院）
CurvNet: Latent Contour Representation and Iterative Data Engine for Curvature Angle Estimation
School of Computer Science（计算机科学学院）；Technology, China University of Mining（采矿技术，中国矿业大学）；Mine Digitization Engineering Research Center of the Ministry of Education（教育部长矿山数字化工程研究中心）；School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）；Xuzhou Central Hospital/The Xuzhou Clinical School of Xuzhou Medical University（徐州中心医院/徐州医学院徐州临床学院）；Xuzhou Rehabilitation Hospital/The Affiliated Xuzhou Rehabilitation Hospital of Xuzhou Medical University（徐州康复医院/徐州医学院附属徐州康复医院）
Korea Advanced Institute of Science and Technology (KAIST)（韩国高等科学技术院（KAIST））
Semantic segmentation algorithms require access to well-annotated datasets captured under diverse illumination conditions to ensure consistent performance. However, poor visibility conditions at varying illumination conditions result in laborious and error-prone labeling. Alternatively, using synthetic samples to train segmentation algorithms has gained interest with the drawback of domain gap that results in sub-optimal performance. While current state-of-the-art (SoTA) have proposed different mechanisms to bridge the domain gap, they still perform poorly in low illumination conditions with a…
In inverse problems we aim to reconstruct some underlying signal of interest from potentially corrupted and often ill-posed measurements. Classical optimization-based techniques proceed by optimizing a data consistency metric together with a regularizer. Current state-of-the-art machine learning approaches draw inspiration from such techniques by unrolling the iterative updates for an optimization-based solver and then learning a regularizer from data. This loop unrolling (LU) method has shown tremendous success, but often requires a deep model for the best performance leading to high memory c…
One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image super-resolution (SR) fail to maintain this advantage. They utilize CNNs in two decoupled steps, i.e., first upsampling the low resolution (LR) image to the high resolution (HR) size with hand-designed techniques (e.g., bicubic interpolation), and then applying CNNs on the upsampled LR image to reconstruct HR results. In this paper, we seek an alternative and p…
GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry
College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）；Zhejiang Key Laboratory of Visual Information Intelligent Processing（浙江省视觉信息智能处理重点实验室）；State Key Lab of CAD & CG, Zhejiang University（CAD与CG国家重点实验室）
