Unrolling Plug-and-Play Network for Hyperspectral Unmixing

Deep learning based unmixing methods have received great attention in recent years and achieve remarkable performance. These methods employ a data-driven approach to extract structure features from hyperspectral image, however, they tend to be less physical interpretable. Conventional unmixing methods are with much more interpretability, whereas they require manually designing regularization and choosing penalty parameters. To overcome these limitations, we propose a novel unmixing method by unrolling the plug-and-play unmixing algorithm to conduct the deep architecture. Our method integrates both inner and outer priors. The carefully designed unfolding deep architecture is used to learn the spectral and spatial information from the hyperspectral image, which we refer to as inner priors. Additionally, our approach incorporates deep denoisers that have been pretrained on a large volume of image data to leverage the outer priors. Secondly, we design a dynamic convolution to model the multiscale information. Different scales are fused using an attention module. Experimental results of both synthetic and real datasets demonstrate that our method outperforms compared methods.

Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model

Diffusion models have obtained substantial progress in image-to-video (I2V) generation. However, such models are not fully understood. In this paper, we report a significant but previously overlooked issue in I2V diffusion models (I2V-DMs), namely, conditional image leakage. I2V-DMs tend to over-rely on the conditional image at large time steps, neglecting the crucial task of predicting the clean video from noisy inputs, which results in videos lacking dynamic and vivid motion. We further address this challenge from both inference and training aspects by presenting plug-and-play strategies accordingly. First, we introduce a training-free inference strategy that starts the generation process from an earlier time step to avoid the unreliable late-time steps of I2V-DMs, as well as an initial noise distribution with optimal analytic expressions (Analytic-Init) by minimizing the KL divergence between it and the actual marginal distribution to effectively bridge the training-inference gap. Second, to mitigate conditional image leakage during training, we design a time-dependent noise distribution for the conditional image, which favors high noise levels at large time steps to sufficiently interfere with the conditional image. We validate these strategies on various I2V-DMs using our collected open-domain image benchmark and the UCF101 dataset. Extensive results demonstrate that our methods outperform baselines by producing videos with more dynamic and natural motion without compromising image alignment and temporal consistency. The project page: \url{https://cond-image-leak.github.io/}.

PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Poses

In this paper, we introduce PoseCrafter, a one-shot method for personalized video generation following the control of flexible poses. Built upon Stable Diffusion and ControlNet, we carefully design an inference process to produce high-quality videos without the corresponding ground-truth frames. First, we select an appropriate reference frame from the training video and invert it to initialize all latent variables for generation. Then, we insert the corresponding training pose into the target pose sequences to enhance faithfulness through a trained temporal attention module. Furthermore, to alleviate the face and hand degradation resulting from discrepancies between poses of training videos and inference poses, we implement simple latent editing through an affine transformation matrix involving facial and hand landmarks. Extensive experiments on several datasets demonstrate that PoseCrafter achieves superior results to baselines pre-trained on a vast collection of videos under 8 commonly used metrics. Besides, PoseCrafter can follow poses from different individuals or artificial edits and simultaneously retain the human identity in an open-domain training video.

Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models

We introduce Vidu, a high-performance text-to-video generator that is capable of producing 1080p videos up to 16 seconds in a single generation. Vidu is a diffusion model with U-ViT as its backbone, which unlocks the scalability and the capability for handling long videos. Vidu exhibits strong coherence and dynamism, and is capable of generating both realistic and imaginative videos, as well as understanding some professional photography techniques, on par with Sora -- the most powerful reported text-to-video generator. Finally, we perform initial experiments on other controllable video generation, including canny-to-video generation, video prediction and subject-driven generation, which demonstrate promising results.

AE-RED: A Hyperspectral Unmixing Framework Powered by Deep Autoencoder and Regularization by Denoising

Spectral unmixing has been extensively studied with a variety of methods and used in many applications. Recently, data-driven techniques with deep learning methods have obtained great attention to spectral unmixing for its superior learning ability to automatically learn the structure information. In particular, autoencoder based architectures are elaborately designed to solve blind unmixing and model complex nonlinear mixtures. Nevertheless, these methods perform unmixing task as blackboxes and lack of interpretability. On the other hand, conventional unmixing methods carefully design the regularizer to add explicit information, in which algorithms such as plug-and-play (PnP) strategies utilize off-the-shelf denoisers to plug powerful priors. In this paper, we propose a generic unmixing framework to integrate the autoencoder network with regularization by denoising (RED), named AE-RED. More specially, we decompose the unmixing optimized problem into two subproblems. The first one is solved using deep autoencoders to implicitly regularize the estimates and model the mixture mechanism. The second one leverages the denoiser to bring in the explicit information. In this way, both the characteristics of the deep autoencoder based unmixing methods and priors provided by denoisers are merged into our well-designed framework to enhance the unmixing performance. Experiment results on both synthetic and real data sets show the superiority of our proposed framework compared with state-of-the-art unmixing approaches.

Guided Deep Generative Model-based Spatial Regularization for Multiband Imaging Inverse Problems

When adopting a model-based formulation, solving inverse problems encountered in multiband imaging requires to define spatial and spectral regularizations. In most of the works of the literature, spectral information is extracted from the observations directly to derive data-driven spectral priors. Conversely, the choice of the spatial regularization often boils down to the use of conventional penalizations (e.g., total variation) promoting expected features of the reconstructed image (e.g., piecewise constant). In this work, we propose a generic framework able to capitalize on an auxiliary acquisition of high spatial resolution to derive tailored data-driven spatial regularizations. This approach leverages on the ability of deep learning to extract high level features. More precisely, the regularization is conceived as a deep generative network able to encode spatial semantic features contained in this auxiliary image of high spatial resolution. To illustrate the versatility of this approach, it is instantiated to conduct two particular tasks, namely multiband image fusion and multiband image inpainting. Experimental results obtained on these two tasks demonstrate the benefit of this class of informed regularizations when compared to more conventional ones.

ControlVideo: Adding Conditional Control for One Shot Text-to-Video Editing

In this paper, we present ControlVideo, a novel method for text-driven video editing. Leveraging the capabilities of text-to-image diffusion models and ControlNet, ControlVideo aims to enhance the fidelity and temporal consistency of videos that align with a given text while preserving the structure of the source video. This is achieved by incorporating additional conditions such as edge maps, fine-tuning the key-frame and temporal attention on the source video-text pair with carefully designed strategies. An in-depth exploration of ControlVideo's design is conducted to inform future research on one-shot tuning video diffusion models. Quantitatively, ControlVideo outperforms a range of competitive baselines in terms of faithfulness and consistency while still aligning with the textual prompt. Additionally, it delivers videos with high visual realism and fidelity w.r.t. the source content, demonstrating flexibility in utilizing controls containing varying degrees of source video information, and the potential for multiple control combinations. The project page is available at \href{https://ml.cs.tsinghua.edu.cn/controlvideo/}{https://ml.cs.tsinghua.edu.cn/controlvideo/}.

Equivariant Energy-Guided SDE for Inverse Molecular Design

Inverse molecular design is critical in material science and drug discovery, where the generated molecules should satisfy certain desirable properties. In this paper, we propose equivariant energy-guided stochastic differential equations (EEGSDE), a flexible framework for controllable 3D molecule generation under the guidance of an energy function in diffusion models. Formally, we show that EEGSDE naturally exploits the geometric symmetry in 3D molecular conformation, as long as the energy function is invariant to orthogonal transformations. Empirically, under the guidance of designed energy functions, EEGSDE significantly improves the baseline on QM9, in inverse molecular design targeted to quantum properties and molecular structures. Furthermore, EEGSDE is able to generate molecules with multiple target properties by combining the corresponding energy functions linearly.

Automatic reorientation by deep learning to generate short axis SPECT myocardial perfusion images

Single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) can be displayed both in traditional short-axis (SA) cardiac planes and polar maps for interpretation and quantification. It is essential to reorient the reconstructed transaxial SPECT MPI into standard SA slices. This study is aimed to develop a deep-learning-based approach for automatic reorientation of MPI. Methods: A total of 254 patients were enrolled, including 228 stress SPECT MPIs and 248 rest SPECT MPIs. Five-fold cross-validation with 180 stress and 201 rest MPIs was used for training and internal validation; the remaining images were used for testing. The rigid transformation parameters (translation and rotation) from manual reorientation were annotated by an experienced operator and used as the ground truth. A convolutional neural network (CNN) was designed to predict the transformation parameters. Then, the derived transform was applied to the grid generator and sampler in spatial transformer network (STN) to generate the reoriented image. A loss function containing mean absolute errors for translation and mean square errors for rotation was employed. A three-stage optimization strategy was adopted for model optimization: 1) optimize the translation parameters while fixing the rotation parameters; 2) optimize rotation parameters while fixing the translation parameters; 3) optimize both translation and rotation parameters together.

EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations

Score-based diffusion generative models (SDGMs) have achieved the SOTA FID results in unpaired image-to-image translation (I2I). However, we notice that existing methods totally ignore the training data in the source domain, leading to sub-optimal solutions for unpaired I2I. To this end, we propose energy-guided stochastic differential equations (EGSDE) that employs an energy function pretrained on both the source and target domains to guide the inference process of a pretrained SDE for realistic and faithful unpaired I2I. Building upon two feature extractors, we carefully design the energy function such that it encourages the transferred image to preserve the domain-independent features and discard domainspecific ones. Further, we provide an alternative explanation of the EGSDE as a product of experts, where each of the three experts (corresponding to the SDE and two feature extractors) solely contributes to faithfulness or realism. Empirically, we compare EGSDE to a large family of baselines on three widely-adopted unpaired I2I tasks under four metrics. EGSDE not only consistently outperforms existing SDGMs-based methods in almost all settings but also achieves the SOTA realism results (e.g., FID of 65.82 in Cat to Dog and FID of 59.75 in Wild to Dog on AFHQ) without harming the faithful performance.