Explanation supervision aims to enhance deep learning models by integrating additional signals to guide the generation of model explanations, showcasing notable improvements in both the predictability and explainability of the model. However, the application of explanation supervision to higher-dimensional data, such as 3D medical images, remains an under-explored domain. Challenges associated with supervising visual explanations in the presence of an additional dimension include: 1) spatial correlation changed, 2) lack of direct 3D annotations, and 3) uncertainty varies across different parts of the explanation. To address these challenges, we propose a Dynamic Uncertainty-aware Explanation supervision (DUE) framework for 3D explanation supervision that ensures uncertainty-aware explanation guidance when dealing with sparsely annotated 3D data with diffusion-based 3D interpolation. Our proposed framework is validated through comprehensive experiments on diverse real-world medical imaging datasets. The results demonstrate the effectiveness of our framework in enhancing the predictability and explainability of deep learning models in the context of medical imaging diagnosis applications.
Recent works on text-to-3d generation show that using only 2D diffusion supervision for 3D generation tends to produce results with inconsistent appearances (e.g., faces on the back view) and inaccurate shapes (e.g., animals with extra legs). Existing methods mainly address this issue by retraining diffusion models with images rendered from 3D data to ensure multi-view consistency while struggling to balance 2D generation quality with 3D consistency. In this paper, we present a new framework Sculpt3D that equips the current pipeline with explicit injection of 3D priors from retrieved reference objects without re-training the 2D diffusion model. Specifically, we demonstrate that high-quality and diverse 3D geometry can be guaranteed by keypoints supervision through a sparse ray sampling approach. Moreover, to ensure accurate appearances of different views, we further modulate the output of the 2D diffusion model to the correct patterns of the template views without altering the generated object's style. These two decoupled designs effectively harness 3D information from reference objects to generate 3D objects while preserving the generation quality of the 2D diffusion model. Extensive experiments show our method can largely improve the multi-view consistency while retaining fidelity and diversity. Our project page is available at: https://stellarcheng.github.io/Sculpt3D/.
We propose a unified framework aimed at enhancing the diffusion priors for 3D generation tasks. Despite the critical importance of these tasks, existing methodologies often struggle to generate high-caliber results. We begin by examining the inherent limitations in previous diffusion priors. We identify a divergence between the diffusion priors and the training procedures of diffusion models that substantially impairs the quality of 3D generation. To address this issue, we propose a novel, unified framework that iteratively optimizes both the 3D model and the diffusion prior. Leveraging the different learnable parameters of the diffusion prior, our approach offers multiple configurations, affording various trade-offs between performance and implementation complexity. Notably, our experimental results demonstrate that our method markedly surpasses existing techniques, establishing new state-of-the-art in the realm of text-to-3D generation. Furthermore, our approach exhibits impressive performance on both NeRF and the newly introduced 3D Gaussian Splatting backbones. Additionally, our framework yields insightful contributions to the understanding of recent score distillation methods, such as the VSD and DDS loss.
3D editing plays a crucial role in many areas such as gaming and virtual reality. Traditional 3D editing methods, which rely on representations like meshes and point clouds, often fall short in realistically depicting complex scenes. On the other hand, methods based on implicit 3D representations, like Neural Radiance Field (NeRF), render complex scenes effectively but suffer from slow processing speeds and limited control over specific scene areas. In response to these challenges, our paper presents GaussianEditor, an innovative and efficient 3D editing algorithm based on Gaussian Splatting (GS), a novel 3D representation. GaussianEditor enhances precision and control in editing through our proposed Gaussian semantic tracing, which traces the editing target throughout the training process. Additionally, we propose Hierarchical Gaussian splatting (HGS) to achieve stabilized and fine results under stochastic generative guidance from 2D diffusion models. We also develop editing strategies for efficient object removal and integration, a challenging task for existing methods. Our comprehensive experiments demonstrate GaussianEditor's superior control, efficacy, and rapid performance, marking a significant advancement in 3D editing. Project Page: https://buaacyw.github.io/gaussian-editor/
Background: Dual-energy CT (DECT) and material decomposition play vital roles in quantitative medical imaging. However, the decomposition process may suffer from significant noise amplification, leading to severely degraded image signal-to-noise ratios (SNRs). While existing iterative algorithms perform noise suppression using different image priors, these heuristic image priors cannot accurately represent the features of the target image manifold. Although deep learning-based decomposition methods have been reported, these methods are in the supervised-learning framework requiring paired data for training, which is not readily available in clinical settings. Purpose: This work aims to develop an unsupervised-learning framework with data-measurement consistency for image-domain material decomposition in DECT.
Explanation(attention)-guided learning is a method that enhances a model's predictive power by incorporating human understanding during the training phase. While attention-guided learning has shown promising results, it often involves time-consuming and computationally expensive model retraining. To address this issue, we introduce the attention-prompted prediction technique, which enables direct prediction guided by the attention prompt without the need for model retraining. However, this approach presents several challenges, including: 1) How to incorporate the visual attention prompt into the model's decision-making process and leverage it for future predictions even in the absence of a prompt? and 2) How to handle the incomplete information from the visual attention prompt? To tackle these challenges, we propose a novel framework called Visual Attention-Prompted Prediction and Learning, which seamlessly integrates visual attention prompts into the model's decision-making process and adapts to images both with and without attention prompts for prediction. To address the incomplete information of the visual attention prompt, we introduce a perturbation-based attention map modification method. Additionally, we propose an optimization-based mask aggregation method with a new weight learning function for adaptive perturbed annotation aggregation in the attention map modification process. Our overall framework is designed to learn in an attention-prompt guided multi-task manner to enhance future predictions even for samples without attention prompts and trained in an alternating manner for better convergence. Extensive experiments conducted on two datasets demonstrate the effectiveness of our proposed framework in enhancing predictions for samples, both with and without provided prompts.
The distributed data analytic system -- Spark is a common choice for processing massive volumes of heterogeneous data, while it is challenging to tune its parameters to achieve high performance. Recent studies try to employ auto-tuning techniques to solve this problem but suffer from three issues: limited functionality, high overhead, and inefficient search. In this paper, we present a general and efficient Spark tuning framework that can deal with the three issues simultaneously. First, we introduce a generalized tuning formulation, which can support multiple tuning goals and constraints conveniently, and a Bayesian optimization (BO) based solution to solve this generalized optimization problem. Second, to avoid high overhead from additional offline evaluations in existing methods, we propose to tune parameters along with the actual periodic executions of each job (i.e., online evaluations). To ensure safety during online job executions, we design a safe configuration acquisition method that models the safe region. Finally, three innovative techniques are leveraged to further accelerate the search process: adaptive sub-space generation, approximate gradient descent, and meta-learning method. We have implemented this framework as an independent cloud service, and applied it to the data platform in Tencent. The empirical results on both public benchmarks and large-scale production tasks demonstrate its superiority in terms of practicality, generality, and efficiency. Notably, this service saves an average of 57.00% memory cost and 34.93% CPU cost on 25K in-production tasks within 20 iterations, respectively.
To reduce the risks associated with ionizing radiation, a reduction of radiation exposure in PET imaging is needed. However, this leads to a detrimental effect on image contrast and quantification. High-quality PET images synthesized from low-dose data offer a solution to reduce radiation exposure. We introduce a diffusion-model-based approach for estimating full-dose PET images from low-dose ones: the PET Consistency Model (PET-CM) yielding synthetic quality comparable to state-of-the-art diffusion-based synthesis models, but with greater efficiency. There are two steps: a forward process that adds Gaussian noise to a full dose PET image at multiple timesteps, and a reverse diffusion process that employs a PET Shifted-window Vision Transformer (PET-VIT) network to learn the denoising procedure conditioned on the corresponding low-dose PETs. In PET-CM, the reverse process learns a consistency function for direct denoising of Gaussian noise to a clean full-dose PET. We evaluated the PET-CM in generating full-dose images using only 1/8 and 1/4 of the standard PET dose. Comparing 1/8 dose to full-dose images, PET-CM demonstrated impressive performance with normalized mean absolute error (NMAE) of 1.233+/-0.131%, peak signal-to-noise ratio (PSNR) of 33.915+/-0.933dB, structural similarity index (SSIM) of 0.964+/-0.009, and normalized cross-correlation (NCC) of 0.968+/-0.011, with an average generation time of 62 seconds per patient. This is a significant improvement compared to the state-of-the-art diffusion-based model with PET-CM reaching this result 12x faster. In the 1/4 dose to full-dose image experiments, PET-CM is also competitive, achieving an NMAE 1.058+/-0.092%, PSNR of 35.548+/-0.805dB, SSIM of 0.978+/-0.005, and NCC 0.981+/-0.007 The results indicate promising low-dose PET image quality improvements for clinical applications.
Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs). Nonetheless, existing Text-to-3D approaches often grapple with challenges such as over-saturation, inadequate detailing, and unrealistic outputs. This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues. Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images based on the renderings of coarse 3D models. Although the generated images mostly alleviate the aforementioned issues, challenges such as view inconsistency and significant content variance persist due to the inherent generative nature of large diffusion models, posing extensive difficulties in leveraging these images effectively. To overcome this hurdle, we advocate integrating a discriminator alongside a novel Diffusion-GAN dual training strategy to guide the training of 3D models. For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data. We conduct a comprehensive set of experiments that demonstrate the effectiveness of our method over baseline approaches.