最近，音频驱动的会说话的面部视频产生引起了广泛的关注。但是，很少有研究能够解决这些会说话的面部视频的情感编辑问题，并具有连续可控的表达式，这是行业中强烈的需求。面临的挑战是，与语音有关的表达和与情感有关的表达通常是高度耦合的。同时，由于表达式与其他属性（例如姿势）的耦合，即在每个框架中翻译角色的表达可能会同时改变头部姿势，因此传统的图像到图像翻译方法无法在我们的应用中很好地工作。培训数据分布。在本文中，我们提出了一种高质量的面部表达编辑方法，用于谈话面部视频，使用户可以连续控制编辑视频中的目标情感。我们为该任务提供了一个新的视角，作为运动信息编辑的特殊情况，我们使用3DMM捕获主要的面部运动和由StyleGAN模拟的相关纹理图，以捕获外观细节。两种表示（3DMM和纹理图）都包含情感信息，并且可以通过神经网络进行连续修改，并通过系数/潜在空间平均轻松平滑，从而使我们的方法变得简单而有效。我们还引入了口腔形状的保存损失，以控制唇部同步和编辑表达的夸张程度之间的权衡。广泛的实验和用户研究表明，我们的方法在各种评估标准中实现了最先进的表现。

从单眼视频中估算移动摄像头的姿势是一个具有挑战性的问题，尤其是由于动态环境中移动对象的存在，在动态环境中，现有摄像头姿势估计方法的性能易于几何一致的像素。为了应对这一挑战，我们为视频提供了一种强大的密度间接结构，该结构是基于由成对光流初始化的致密对应的。我们的关键想法是将远程视频对应性优化为密集的点轨迹，并使用它来学习对运动分割的强大估计。提出了一种新型的神经网络结构来处理不规则的点轨迹数据。然后，在远程点轨迹的一部分中，通过全局捆绑式调整估算和优化摄像头姿势，这些轨迹被归类为静态。 MPI Sintel数据集的实验表明，与现有最新方法相比，我们的系统产生的相机轨迹明显更准确。此外，我们的方法能够在完全静态的场景上保留相机姿势的合理准确性，该场景始终优于端到端深度学习的强大最新密度对应方法，这证明了密集间接方法的潜力基于光流和点轨迹。由于点轨迹表示是通用的，因此我们进一步介绍了具有动态对象的复杂运动的野外单眼视频的比较。代码可在https://github.com/bytedance/particle-sfm上找到。

点云降级旨在从噪音和异常值损坏的原始观察结果中恢复清洁点云，同时保留细粒细节。我们提出了一种新型的基于深度学习的DeNoising模型，该模型结合了正常的流量和噪声解散技术，以实现高降解精度。与提取点云特征以进行点校正的现有作品不同，我们从分布学习和特征分离的角度制定了denoising过程。通过将嘈杂的点云视为清洁点和噪声的联合分布，可以从将噪声对应物从潜在点表示中解​​散出来，而欧几里得和潜在空间之间的映射是通过标准化流量来建模的。我们评估了具有各种噪声设置的合成3D模型和现实世界数据集的方法。定性和定量结果表明，我们的方法表现优于先前的最先进的基于深度学习的方法。

Point Cloud升级旨在从给定的稀疏中产生密集的点云，这是一项具有挑战性的任务，这是由于点集的不规则和无序的性质。为了解决这个问题，我们提出了一种新型的基于深度学习的模型，称为PU-Flow，该模型结合了正常的流量和权重预测技术，以产生均匀分布在基础表面上的致密点。具体而言，我们利用标准化流的可逆特征来转换欧几里得和潜在空间之间的点，并将UPSMPLING过程作为潜在空间中相邻点的集合，从本地几何环境中自适应地学习。广泛的实验表明，我们的方法具有竞争力，并且在大多数测试用例中，它在重建质量，近距到表面的准确性和计算效率方面的表现优于最先进的方法。源代码将在https://github.com/unknownue/pu-flow上公开获得。

漫画是一种人类面孔的艺术风格，吸引了娱乐业的相当大的关注。到目前为止，存在少数3D漫画生成方法，所有这些都需要一些漫画信息（例如，漫画素描或2D漫画）作为输入。然而，这种输入难以由非专业用户提供。在本文中，我们提出了一个端到端的深度神经网络模型，可直接从正常的2D脸照片产生高质量的3D漫画。我们系统最具挑战性的问题是面部照片的源域（以正常的2D面为特征）与3D漫画的目标域有很大差异（以3D夸大的面形状和纹理为特征）。为了解决这一挑战，我们：（1）建立一个大型数据集5,343个3D漫画网格，并使用它来建立3D漫画形状空间中的PCA模型; （2）从输入面照片重建正常的全3D头，并在3D漫画形状空间中使用其PCA表示来建立输入照片和3D漫画形状之间的对应关系; （3）提出了一种基于以前对讽刺的心理研究的新颖性状损失和新颖的漫画损失。实验包括新型两级用户学习，表明我们的系统可以直接从正常面部照片产生高质量的3D漫画。

众所周知，即使通过核心点之间捕获数据点之间的相似性，也可以通过捕获相似性来提供准确的预测和不确定性估计，以提供准确的预测和不确定性估计。然而，传统的GP内核在捕获高维数据点之间的相似性时不是非常有效的。神经网络可用于学习在高维数据中编码复杂结构的良好表示，并且可以用作GP内核的输入。然而，神经网络的巨大数据要求使得这种方法在小数据设置中无效。为了解决代表学习和数据效率的冲突问题，我们建议通过使用概率神经网络来学习概率嵌入的深核。我们的方法将高维数据映射到低维子空间中的概率分布，然后计算这些分布之间的内核以捕获相似性。要启用端到端学习，我们可以推导出用于培训模型的功能梯度血清过程。各种数据集的实验表明，我们的方法在监督和半监督设置中占GP内核学习中的最先进。我们还将我们的方法扩展到其他小型数据范例，例如少量分类，在迷你想象网和小熊数据集上以前的方式胜过先前的方法。

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.

Few Shot Instance Segmentation (FSIS) requires models to detect and segment novel classes with limited several support examples. In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework. Our key insights are two folds: Firstly, with the aid of support masks, we can generate dynamic class centers more appropriately to re-weight query features. Secondly, we find that support object queries have already encoded key factors after base training. In this way, the query features can be enhanced twice from two aspects, i.e., feature-level and instance-level. In particular, we firstly design a mask-based dynamic weighting module to enhance support features and then propose to link object queries for better calibration via cross-attention. After the above steps, the novel classes can be improved significantly over our strong baseline. Additionally, our new framework can be easily extended to incremental FSIS with minor modification. When benchmarking results on the COCO dataset for FSIS, gFSIS, and iFSIS settings, our method achieves a competitive performance compared to existing approaches across different shots, e.g., we boost nAP by noticeable +8.2/+9.4 over the current state-of-the-art FSIS method for 10/30-shot. We further demonstrate the superiority of our approach on Few Shot Object Detection. Code and model will be available.

This paper focuses on designing efficient models with low parameters and FLOPs for dense predictions. Even though CNN-based lightweight methods have achieved stunning results after years of research, trading-off model accuracy and constrained resources still need further improvements. This work rethinks the essential unity of efficient Inverted Residual Block in MobileNetv2 and effective Transformer in ViT, inductively abstracting a general concept of Meta-Mobile Block, and we argue that the specific instantiation is very important to model performance though sharing the same framework. Motivated by this phenomenon, we deduce a simple yet efficient modern \textbf{I}nverted \textbf{R}esidual \textbf{M}obile \textbf{B}lock (iRMB) for mobile applications, which absorbs CNN-like efficiency to model short-distance dependency and Transformer-like dynamic modeling capability to learn long-distance interactions. Furthermore, we design a ResNet-like 4-phase \textbf{E}fficient \textbf{MO}del (EMO) based only on a series of iRMBs for dense applications. Massive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, \eg, our EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass \textbf{SoTA} CNN-/Transformer-based models, while trading-off the model accuracy and efficiency well.