我们提出了Diffustereo，这是一种仅使用稀疏相机（在这项工作中8）进行高质量3D人类重建的新型系统。其核心是一种新型基于扩散的立体声模块，该模块将扩散模型（一种强大的生成模型）引入迭代立体声匹配网络中。为此，我们设计了一个新的扩散内核和其他立体限制，以促进网络中的立体声匹配和深度估计。我们进一步提出了一个多级立体声网络体系结构，以处理高分辨率（最多4K）输入，而无需无法负担的内存足迹。考虑到人类的一组稀疏视图颜色图像，提出的基于多级扩散的立体声网络可以产生高准确的深度图，然后通过有效的多视图融合策略将其转换为高质量的3D人类模型。总体而言，我们的方法可以自动重建人类模型，其质量是高端密集摄像头钻机，这是使用更轻巧的硬件设置来实现的。实验表明，我们的方法在定性和定量上都优于最先进的方法。

我们提出了FITE，这是一种对服装中的人体化身进行建模的第一刻度框架。我们的框架首先学习了代表粗衣拓扑的隐式表面模板，然后采用模板来指导点集的产生，从而进一步捕获姿势依赖的服装变形，例如皱纹。我们的管道结合了隐式和明确表示的优点，即处理变化拓扑的能力以及有效捕获细节的能力。我们还提出了扩散的皮肤，以促进模板训练，尤其是用于宽松衣服的模板训练，以及基于投影的姿势编码，以从网格模板中提取姿势信息，而无需预定义的紫外线图或连接性。我们的代码可在https://github.com/jsnln/fite上公开获取。

基于回归的方法可以通过直接以馈送方式将原始像素直接映射到模型参数来估算从单眼图像的身体，手甚至全身模型。但是，参数的微小偏差可能导致估计的网格和输入图像之间的明显未对准，尤其是在全身网格恢复的背景下。为了解决这个问题，我们建议在我们的回归网络中进行锥体网状对准反馈（PYMAF）循环，以进行良好的人类网格恢复，并将其扩展到PYMAF-X，以恢复表达全身模型。 PYMAF的核心思想是利用特征金字塔并根据网格图像对准状态明确纠正预测参数。具体而言，给定当前预测的参数，将相应地从更优质的特征中提取网格对准的证据，并将其送回以进行参数回流。为了增强一致性的看法，采用辅助密集的监督来提供网格图像对应指南，同时引入了空间对齐的注意，以使我们的网络对全球环境的认识。当扩展PYMAF以进行全身网状恢复时，PYMAF-X中提出了一种自适应整合策略来调整肘部扭转旋转，该旋转会产生自然腕部姿势，同时保持部分特定估计的良好性能。我们的方法的功效在几个基准数据集上得到了验证，以实现身体和全身网状恢复，在该数据集中，PYMAF和PYMAF-X有效地改善了网格图像的对准并实现了新的最新结果。具有代码和视频结果的项目页面可以在https://www.liuyebin.com/pymaf-x上找到。

为了解决由单眼人类体积捕获中部分观察结果引起的不足问题，我们提出了Avatarcap，这是一个新颖的框架，该框架将可动画的化身引入了可见和不可见区域中高保真重建的捕获管道中。我们的方法首先为该主题创建一个可动画化的化身，从少量（〜20）的3D扫描作为先验。然后给出了该主题的单眼RGB视频，我们的方法集成了图像观察和头像先验的信息，因此无论可见性如何，都会重新构建具有动态细节的高保真3D纹理模型。为了学习有效的头像，仅从少数样品中捕获体积捕获，我们提出了GeoteXavatar，该地理Xavatar利用几何和纹理监督以分解的隐式方式限制了姿势依赖性动力学。进一步提出了一种涉及规范正常融合和重建网络的头像条件的体积捕获方法，以在观察到的区域和无形区域中整合图像观测和化身动力学，以整合图像观测和头像动力学。总体而言，我们的方法可以通过详细的和姿势依赖性动力学实现单眼人体体积捕获，并且实验表明我们的方法优于最新的最新状态。代码可在https://github.com/lizhe00/avatarcap上找到。

我们介绍了Doublefield，这是一个新颖的框架，结合了高保真人体重建和渲染的表面场和辐射场的优点。在DoubleField中，表面字段和辐射字段通过共享特征嵌入和表面引导采样策略相关联。此外，将视图到视图变压器被引入熔丝多视图特征，并直接从高分辨率输入学习视图依赖性功能。通过DoubleField和视图到视图变压器的建模功能，我们的方法显着提高了几何形状和外观的重建质量，同时支持直接推理，现场特定的高分辨率FineTuning和快速渲染。 Doublefield的功效通过多个数据集的定量评估和真实世界稀疏多视图系统的定性结果验证，显示了其高质量人体模型重建和光学真实自由观点人类渲染的优异能力。数据和源代码将公开用于研究目的。请参阅我们的项目页面：http：//www.liuyebin.com/dbfield/dbfield.html。

Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics. To capture robust movement patterns from these graphs, long-range and multi-scale context aggregation and spatial-temporal dependency modeling are critical aspects of a powerful feature extractor. However, existing methods have limitations in achieving (1) unbiased long-range joint relationship modeling under multiscale operators and (2) unobstructed cross-spacetime information flow for capturing complex spatial-temporal dependencies. In this work, we present (1) a simple method to disentangle multi-scale graph convolutions and (2) a unified spatial-temporal graph convolutional operator named G3D. The proposed multi-scale aggregation scheme disentangles the importance of nodes in different neighborhoods for effective long-range modeling. The proposed G3D module leverages dense cross-spacetime edges as skip connections for direct information propagation across the spatial-temporal graph. By coupling these proposals, we develop a powerful feature extractor named MS-G3D based on which our model 1 outperforms previous state-of-the-art methods on three large-scale datasets: NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400.

Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than CLS token- and feature-based distillation; 2) An intermediate layer of the teacher network as target perform better than that using the last layer when the depth of the student mismatches that of the teacher; 3) Weak regularization is preferred; etc. With these findings, we achieve significant fine-tuning accuracy improvements over the scratch MIM pre-training on ImageNet-1K classification, using all the ViT-Tiny, ViT-Small, and ViT-base models, with +4.2%/+2.4%/+1.4% gains, respectively. Our TinyMIM model of base size achieves 52.2 mIoU in AE20K semantic segmentation, which is +4.1 higher than the MAE baseline. Our TinyMIM model of tiny size achieves 79.6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget. This strong performance suggests an alternative way for developing small vision Transformer models, that is, by exploring better training methods rather than introducing inductive biases into architectures as in most previous works. Code is available at https://github.com/OliverRensu/TinyMIM.

In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed implicitly, by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. CMT obtains 73.0% NDS on nuScenes benchmark. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code will be released at https://github.com/junjie18/CMT.

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset. However, the existing dataset distillation techniques mainly aim at achieving the best trade-off between resource usage efficiency and model utility. The security risks stemming from them have not been explored. This study performs the first backdoor attack against the models trained on the data distilled by dataset distillation models in the image domain. Concretely, we inject triggers into the synthetic data during the distillation procedure rather than during the model training stage, where all previous attacks are performed. We propose two types of backdoor attacks, namely NAIVEATTACK and DOORPING. NAIVEATTACK simply adds triggers to the raw data at the initial distillation phase, while DOORPING iteratively updates the triggers during the entire distillation procedure. We conduct extensive evaluations on multiple datasets, architectures, and dataset distillation techniques. Empirical evaluation shows that NAIVEATTACK achieves decent attack success rate (ASR) scores in some cases, while DOORPING reaches higher ASR scores (close to 1.0) in all cases. Furthermore, we conduct a comprehensive ablation study to analyze the factors that may affect the attack performance. Finally, we evaluate multiple defense mechanisms against our backdoor attacks and show that our attacks can practically circumvent these defense mechanisms.

Blind image quality assessment (BIQA) remains challenging due to the diversity of distortion and image content variation, which complicate the distortion patterns crossing different scales and aggravate the difficulty of the regression problem for BIQA. However, existing BIQA methods often fail to consider multi-scale distortion patterns and image content, and little research has been done on learning strategies to make the regression model produce better performance. In this paper, we propose a simple yet effective Progressive Multi-Task Image Quality Assessment (PMT-IQA) model, which contains a multi-scale feature extraction module (MS) and a progressive multi-task learning module (PMT), to help the model learn complex distortion patterns and better optimize the regression issue to align with the law of human learning process from easy to hard. To verify the effectiveness of the proposed PMT-IQA model, we conduct experiments on four widely used public datasets, and the experimental results indicate that the performance of PMT-IQA is superior to the comparison approaches, and both MS and PMT modules improve the model's performance.