Measurement Guidance in Diffusion Models: Insight from Medical Image Synthesis.

In the field of healthcare, the acquisition of sample is usually restricted by multiple considerations, including cost, labor- intensive annotation, privacy concerns, and radiation hazards, therefore, synthesizing images-of-interest is an important tool to data augmentation. Diffusion models have recently attained state-of-the-art results in various synthesis tasks, and embedding energy functions has been proved that can effectively guide the pre-trained model to synthesize target samples. However, we notice that current method development and validation are still limited to improving indicators, such as Fréchet Inception Distance score (FID) and Inception Score (IS), and have not provided deeper investigations on downstream tasks, like disease grading and diagnosis. Moreover, existing classifier guidance which can be regarded as a special case of energy function can only has a singular effect on altering the distribution of the synthetic dataset. This may contribute to in-distribution synthetic sample that has limited help to downstream model optimization. All these limitations remind that we still have a long way to go to achieve controllable generation. In this work, we first conducted an analysis on previous guidance as well as its contributions on further applications from the perspective of data distribution. To synthesize samples which can help downstream applications, we then introduce uncertainty guidance in each sampling step and design an uncertainty-guided diffusion models. Extensive experiments on four medical datasets, with ten classic networks trained on the augmented sample sets provided a comprehensive evaluation on the practical contributions of our methodology. Furthermore, we provide a theoretical guarantee for general gradient guidance in diffusion models, which would benefit future research on investigating other forms of measurement guidance for specific generative tasks. Codes and models are available at: https://github.com/yangqy1110/MGDM.

Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance.

Creating a vivid video from the event or scenario in our imagination is a truly fascinating experience. Recent advancements in text-to-video synthesis have unveiled the potential to achieve this with prompts only. While text is convenient in conveying the overall scene context, it may be insufficient to control precisely. In this paper, we explore customized video generation by utilizing text as context description and motion structure (e.g. frame- wise depth) as concrete guidance. Our method, dubbed Make-Your-Video, involves joint-conditional video generation using a Latent Diffusion Model that is pre-trained for still image synthesis and then promoted for video generation with the introduction of temporal modules. This two-stage learning scheme not only reduces the computing resources required, but also improves the performance by transferring the rich concepts available in image datasets solely into video generation. Moreover, we use a simple yet effective causal attention mask strategy to enable longer video synthesis, which mitigates the potential quality degradation effectively. Experimental results show the superiority of our method over existing baselines, particularly in terms of temporal coherence and fidelity to users' guidance. In addition, our model enables several intriguing applications that demonstrate potential for practical usage. The code, model weights, and videos are publicly available at our project page: https://doubiiu.github.io/projects/Make-Your-Video/.

Scale-Arbitrary Invertible Image Downscaling.

Conventional social media platforms usually downscale high-resolution (HR) images to restrict their resolution to a specific size for saving transmission/storage cost, which makes those visual details inaccessible to other users. To bypass this obstacle, recent invertible image downscaling methods jointly model the downscaling/upscaling problems and achieve impressive performance. However, they only consider fixed integer scale factors and may be inapplicable to generic downscaling tasks towards resolution restriction as posed by social media platforms. In this paper, we propose an effective and universal Scale-Arbitrary Invertible Image Downscaling Network (AIDN), to downscale HR images with arbitrary scale factors in an invertible manner. Particularly, the HR information is embedded in the downscaled low-resolution (LR) counterparts in a nearly imperceptible form such that our AIDN can further restore the original HR images solely from the LR images. The key to supporting arbitrary scale factors is our proposed Conditional Resampling Module (CRM) that conditions the downscaling/upscaling kernels and sampling locations on both scale factors and image content. Extensive experimental results demonstrate that our AIDN achieves top performance for invertible downscaling with both arbitrary integer and non-integer scale factors. Also, both quantitative and qualitative evaluations show our AIDN is robust to the lossy image compression standard. The source code and trained models are publicly available at https://github.com/Doubiiu/AIDN.

Taming Reversible Halftoning via Predictive Luminance.

Traditional halftoning usually drops colors when dithering images with binary dots, which makes it difficult to recover the original color information. We proposed a novel halftoning technique that converts a color image into a binary halftone with full restorability to its original version. Our novel base halftoning technique consists of two convolutional neural networks (CNNs) to produce the reversible halftone patterns, and a noise incentive block (NIB) to mitigate the flatness degradation issue of CNNs. Furthermore, to tackle the conflicts between the blue-noise quality and restoration accuracy in our novel base method, we proposed a predictor-embedded approach to offload predictable information from the network, which in our case is the luminance information resembling from the halftone pattern. Such an approach allows the network to gain more flexibility to produce halftones with better blue-noise quality without compromising the restoration quality. Detailed studies on the multiple-stage training method and loss weightings have been conducted. We have compared our predictor-embedded method and our novel method regarding spectrum analysis on halftone, halftone accuracy, restoration accuracy, and the data embedding studies. Our entropy evaluation evidences our halftone contains less encoding information than our novel base method. The experiments show our predictor-embedded method gains more flexibility to improve the blue-noise quality of halftones and maintains a comparable restoration quality with a higher tolerance for disturbances.

LF2MV: Learning An Editable Meta-View Towards Light Field Representation.

Light fields are 4D scene representations that are typically structured as arrays of views or several directional samples per pixel in a single view. However, this highly correlated structure is not very efficient to transmit and manipulate, especially for editing. To tackle this issue, we propose a novel representation learning framework that can encode the light field into a single meta-view that is both compact and editable. Specifically, the meta-view composes of three visual channels and a complementary meta channel that is embedded with geometric and residual appearance information. The visual channels can be edited using existing 2D image editing tools, before reconstructing the whole edited light field. To facilitate edit propagation against occlusion, we design a special editing-aware decoding network that consistently propagates the visual edits to the whole light field upon reconstruction. Extensive experiments show that our proposed method achieves competitive representation accuracy and meanwhile enables consistent edit propagation.

Resident and staff perspectives of person-centered climate in nursing homes: a cross-sectional study.

BACKGROUND: Person-centered care is widely recognized as a gold standard and is based on a supportive psychosocial climate for both residents and staff in nursing homes. Residents and staff may have different perspectives as to whether the climate in which they interact is person-centered, perhaps due to their different expectations of the nursing home environment and the provision of care services. The aim of this study was to explore and compare resident and staff perspectives of person-centered climate in aged care nursing homes. METHODS: This is a descriptive cross-sectional study using a cluster random sampling method. The study collected data in 2016 from residents (n = 251) and nursing staff (n = 249) in 23 nursing homes using a Person-centered Climate Questionnaire-Patient version and Person-centered Climate-Staff version. T-tests for independent-samples were used to compare scores ranked by nursing staff and residents. RESULTS: The mean scores of 'A climate of safety' subscale and 'A climate of everydayness' subscale rated by residents were significantly lower than those rated by nursing staff. The mean scores of 'A climate of hospitality' rated by residents were very low among the three subscales, an indicator of the need to improve a more home-like environment for residents. Residents in larger size nursing homes showed a higher score of person-centered climate compared with their counterparts in small size nursing homes. CONCLUSIONS: This study reveals that the perspectives and perceptions of person-centered climate differ between residents and nursing staff. Therefore, both resident and staff perspectives should be taken into account in attempting to improve person-centered climate for better care outcomes.

A Unified Framework for Street-View Panorama Stitching.

In this paper, we propose a unified framework to generate a pleasant and high-quality street-view panorama by stitching multiple panoramic images captured from the cameras mounted on the mobile platform. Our proposed framework is comprised of four major steps: image warping, color correction, optimal seam line detection and image blending. Since the input images are captured without a precisely common projection center from the scenes with the depth differences with respect to the cameras to different extents, such images cannot be precisely aligned in geometry. Therefore, an efficient image warping method based on the dense optical flow field is proposed to greatly suppress the influence of large geometric misalignment at first. Then, to lessen the influence of photometric inconsistencies caused by the illumination variations and different exposure settings, we propose an efficient color correction algorithm via matching extreme points of histograms to greatly decrease color differences between warped images. After that, the optimal seam lines between adjacent input images are detected via the graph cut energy minimization framework. At last, the Laplacian pyramid blending algorithm is applied to further eliminate the stitching artifacts along the optimal seam lines. Experimental results on a large set of challenging street-view panoramic images captured form the real world illustrate that the proposed system is capable of creating high-quality panoramas.