Recent work on 4D point cloud sequences has attracted a lot of attention. However, obtaining exhaustively labeled 4D datasets is often very expensive and laborious, so it is especially important to investigate how to utilize raw unlabeled data. However, most existing self-supervised point cloud representation learning methods only consider geometry from a static snapshot omitting the fact that sequential observations of dynamic scenes could reveal more comprehensive geometric details. And the video representation learning frameworks mostly model motion as image space flows, let alone being 3D-geometric-aware. To overcome such issues, this paper proposes a new 4D self-supervised pre-training method called Complete-to-Partial 4D Distillation. Our key idea is to formulate 4D self-supervised representation learning as a teacher-student knowledge distillation framework and let the student learn useful 4D representations with the guidance of the teacher. Experiments show that this approach significantly outperforms previous pre-training approaches on a wide range of 4D point cloud sequence understanding tasks including indoor and outdoor scenarios.
translated by 谷歌翻译
本文提出了一个4D主链,以供长期点云视频理解。捕获空间上下文的一种典型方法是使用无层次结构的4DCONV或变压器。但是,由于相机运动,场景变化,采样模式和4D数据的复杂性,这些方法既没有有效也没有高效的效率。为了解决这些问题,我们利用原始平面作为中层表示,以捕获4D点云视频中的长期空间上下文,并提出了一个名为Point Point Primitive Transformer(PPTR)的新型层次骨架,主要由该骨架组成,该骨架主要由主要的点变压器和原始变压器。广泛的实验表明,PPTR在不同任务上优于先前的艺术状态
translated by 谷歌翻译
The recent success of pre-trained 2D vision models is mostly attributable to learning from large-scale datasets. However, compared with 2D image datasets, the current pre-training data of 3D point cloud is limited. To overcome this limitation, we propose a knowledge distillation method for 3D point cloud pre-trained models to acquire knowledge directly from the 2D representation learning model, particularly the image encoder of CLIP, through concept alignment. Specifically, we introduce a cross-attention mechanism to extract concept features from 3D point cloud and compare them with the semantic information from 2D images. In this scheme, the point cloud pre-trained models learn directly from rich information contained in 2D teacher models. Extensive experiments demonstrate that the proposed knowledge distillation scheme achieves higher accuracy than the state-of-the-art 3D pre-training methods for synthetic and real-world datasets on downstream tasks, including object classification, object detection, semantic segmentation, and part segmentation.
translated by 谷歌翻译
我们提出了一种新的方法来将4D动态对象前瞻灌输到学习的3D表示,通过无监督的预训练。我们观察到对象通过环境的动态移动提供了关于其对象的重要提示,因此提出了利用这种动态理解的学习学习的3D表示,然后可以有效地传送到下游3D语义场景中的改进性能。我们提出了一种新的数据增强方案,利用静态3D环境中移动的合成3D形状,并在3D-4D约束下采用对比学习,该约束将4D Imormces编码到学习的3D表示中。实验表明,我们无监督的代表学习导致下游3D语义分割,对象检测和实例分割任务的改进,而且,显着提高了数据稀缺方案的性能。
translated by 谷歌翻译
Masked Modeling (MM) has demonstrated widespread success in various vision challenges, by reconstructing masked visual patches. Yet, applying MM for large-scale 3D scenes remains an open problem due to the data sparsity and scene complexity. The conventional random masking paradigm used in 2D images often causes a high risk of ambiguity when recovering the masked region of 3D scenes. To this end, we propose a novel informative-preserved reconstruction, which explores local statistics to discover and preserve the representative structured points, effectively enhancing the pretext masking task for 3D scene understanding. Integrated with a progressive reconstruction manner, our method can concentrate on modeling regional geometry and enjoy less ambiguity for masked reconstruction. Besides, such scenes with progressive masking ratios can also serve to self-distill their intrinsic spatial consistency, requiring to learn the consistent representations from unmasked areas. By elegantly combining informative-preserved reconstruction on masked areas and consistency self-distillation from unmasked areas, a unified framework called MM-3DScene is yielded. We conduct comprehensive experiments on a host of downstream tasks. The consistent improvement (e.g., +6.1 mAP@0.5 on object detection and +2.2% mIoU on semantic segmentation) demonstrates the superiority of our approach.
translated by 谷歌翻译
由于缺乏大规模标记的3D数据集,大多数3D神经网络都是从划痕训练。在本文中,我们通过利用来自丰富的2D数据集学习的2D网络来介绍一种新的3D预预测方法。我们提出了通过将像素级和点级别特征映射到同一嵌入空间中的对比度的像素到点知识转移来有效地利用2D信息。由于2D和3D网络之间的异构性质,我们介绍了后投影功能以对准2D和3D之间的功能以使转移成为可能。此外,我们设计了一个上采样功能投影层,以增加高级2D特征图的空间分辨率,这使得能够学习细粒度的3D表示。利用普雷累染的2D网络,所提出的预介绍过程不需要额外的2D或3D标记数据,进一步缓解了昂贵的3D数据注释成本。据我们所知,我们是第一个利用现有的2D培训的权重,以预先rain 3D深度神经网络。我们的密集实验表明,使用2D知识预订的3D模型可以通过各种真实世界3D下游任务进行3D网络的性能。
translated by 谷歌翻译
现代自我监督的学习算法通常强制执行跨视图实例的表示的持久性。虽然非常有效地学习整体图像和视频表示,但这种方法成为在视频中学习时空时间细粒度的特征的子最优,其中场景和情况通过空间和时间演变。在本文中,我们介绍了上下文化的时空对比学习(Const-CL)框架,以利用自我监督有效学习时空时间细粒度的表示。我们首先设计一种基于区域的自我监督的借口任务,该任务要求模型从一个视图中学习将实例表示转换为上下文特征的另一个视图。此外,我们介绍了一个简单的网络设计,有效地调和了整体和本地表示的同时学习过程。我们评估我们对各种下游任务和CONST-CL的学习表现,实现了四个数据集的最先进结果。对于时空行动本地化,Const-CL可以使用AVA-Kinetics验证集的检测到框实现39.4%的地图和30.5%地图。对于对象跟踪,Const-CL在OTB2015上实现了78.1%的精度和55.2%的成功分数。此外,Const-CL分别在视频动作识别数据集,UCF101和HMDB51上实现了94.8%和71.9%的前1个微调精度。我们计划向公众发布我们的代码和模型。
translated by 谷歌翻译
Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (e.g., ImageNet) can help boost performance once fine-tuned on a usually much smaller target set, has been instrumental to many applications in language and vision. Yet, very little is known about its usefulness in 3D point cloud understanding. We see this as an opportunity considering the effort required for annotating data in 3D. In this work, we aim at facilitating research on 3D representation learning. Different from previous works, we focus on high-level scene understanding tasks. To this end, we select a suite of diverse datasets and tasks to measure the effect of unsupervised pre-training on a large source set of 3D scenes. Our findings are extremely encouraging: using a unified triplet of architecture, source dataset, and contrastive loss for pre-training, we achieve improvement over recent best results in segmentation and detection across 6 different benchmarks for indoor and outdoor, real and synthetic datasets -demonstrating that the learned representation can generalize across domains. Furthermore, the improvement was similar to supervised pre-training, suggesting that future efforts should favor scaling data collection over more detailed annotation. We hope these findings will encourage more research on unsupervised pretext task design for 3D deep learning. Our code is publicly available at https://github.com/facebookresearch/PointContrast
translated by 谷歌翻译
The past few years have witnessed the prevalence of self-supervised representation learning within the language and 2D vision communities. However, such advancements have not been fully migrated to the community of 3D point cloud learning. Different from previous pre-training pipelines for 3D point clouds that generally fall into the scope of either generative modeling or contrastive learning, in this paper, we investigate a translative pre-training paradigm, namely PointVST, driven by a novel self-supervised pretext task of cross-modal translation from an input 3D object point cloud to its diverse forms of 2D rendered images (e.g., silhouette, depth, contour). Specifically, we begin with deducing view-conditioned point-wise embeddings via the insertion of the viewpoint indicator, and then adaptively aggregate a view-specific global codeword, which is further fed into the subsequent 2D convolutional translation heads for image generation. We conduct extensive experiments on common task scenarios of 3D shape analysis, where our PointVST shows consistent and prominent performance superiority over current state-of-the-art methods under diverse evaluation protocols. Our code will be made publicly available.
translated by 谷歌翻译
了解3D场景是自治代理的关键先决条件。最近,LIDAR和其他传感器已经以点云帧的时间序列形式提供了大量数据。在这项工作中,我们提出了一种新的问题 - 顺序场景流量估计(SSFE) - 该旨在预测给定序列中所有点云的3D场景流。这与先前研究的场景流程估计问题不同,这侧重于两个框架。我们介绍SPCM-NET架构,通过计算相邻点云之间的多尺度时空相关性,然后通过订单不变的复制单元计算多级时空相关性来解决这个问题。我们的实验评估证实,与仅使用两个框架相比,点云序列的复发处理导致SSFE明显更好。另外,我们证明可以有效地修改该方法,用于顺序点云预测(SPF),一种需要预测未来点云帧的相关问题。我们的实验结果是使用SSFE和SPF的新基准进行评估,包括合成和实时数据集。以前,场景流估计的数据集仅限于两个帧。我们为这些数据集提供非琐碎的扩展,用于多帧估计和预测。由于难以获得现实世界数据集的地面真理运动,我们使用自我监督的培训和评估指标。我们认为,该基准将在该领域的未来研究中关键。将可访问基准和型号的所有代码。
translated by 谷歌翻译
点云的学习表示是3D计算机视觉中的重要任务,尤其是没有手动注释的监督。以前的方法通常会从自动编码器中获得共同的援助,以通过重建输入本身来建立自我判断。但是,现有的基于自我重建的自动编码器仅关注全球形状,而忽略本地和全球几何形状之间的层次结构背景,这是3D表示学习的重要监督。为了解决这个问题,我们提出了一个新颖的自我监督点云表示学习框架,称为3D遮挡自动编码器(3D-OAE)。我们的关键想法是随机遮住输入点云的某些局部补丁,并通过使用剩余的可见图来恢复遮挡的补丁,从而建立监督。具体而言,我们设计了一个编码器,用于学习可见的本地贴片的特征,并设计了一个用于利用这些功能预测遮挡贴片的解码器。与以前的方法相反,我们的3D-OAE可以去除大量的斑块,并仅使用少量可见斑块进行预测,这使我们能够显着加速训练并产生非平凡的自我探索性能。训练有素的编码器可以进一步转移到各种下游任务。我们证明了我们在广泛使用基准下的不同判别和生成应用中的最先进方法的表现。
translated by 谷歌翻译
Pre-training by numerous image data has become de-facto for robust 2D representations. In contrast, due to the expensive data acquisition and annotation, a paucity of large-scale 3D datasets severely hinders the learning for high-quality 3D features. In this paper, we propose an alternative to obtain superior 3D representations from 2D pre-trained models via Image-to-Point Masked Autoencoders, named as I2P-MAE. By self-supervised pre-training, we leverage the well learned 2D knowledge to guide 3D masked autoencoding, which reconstructs the masked point tokens with an encoder-decoder architecture. Specifically, we first utilize off-the-shelf 2D models to extract the multi-view visual features of the input point cloud, and then conduct two types of image-to-point learning schemes on top. For one, we introduce a 2D-guided masking strategy that maintains semantically important point tokens to be visible for the encoder. Compared to random masking, the network can better concentrate on significant 3D structures and recover the masked tokens from key spatial cues. For another, we enforce these visible tokens to reconstruct the corresponding multi-view 2D features after the decoder. This enables the network to effectively inherit high-level 2D semantics learned from rich image data for discriminative 3D modeling. Aided by our image-to-point pre-training, the frozen I2P-MAE, without any fine-tuning, achieves 93.4% accuracy for linear SVM on ModelNet40, competitive to the fully trained results of existing methods. By further fine-tuning on on ScanObjectNN's hardest split, I2P-MAE attains the state-of-the-art 90.11% accuracy, +3.68% to the second-best, demonstrating superior transferable capacity. Code will be available at https://github.com/ZrrSkywalker/I2P-MAE.
translated by 谷歌翻译
Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long videos. In this paper, we introduce a new framework of contrastive action representation learning (CARL) to learn frame-wise action representation in a self-supervised or weakly-supervised manner, especially for long videos. Specifically, we introduce a simple but effective video encoder that considers both spatial and temporal context by combining convolution and transformer. Inspired by the recent massive progress in self-supervised learning, we propose a new sequence contrast loss (SCL) applied to two related views obtained by expanding a series of spatio-temporal data in two versions. One is the self-supervised version that optimizes embedding space by minimizing KL-divergence between sequence similarity of two augmented views and prior Gaussian distribution of timestamp distance. The other is the weakly-supervised version that builds more sample pairs among videos using video-level labels by dynamic time wrapping (DTW). Experiments on FineGym, PennAction, and Pouring datasets show that our method outperforms previous state-of-the-art by a large margin for downstream fine-grained action classification and even faster inference. Surprisingly, although without training on paired videos like in previous works, our self-supervised version also shows outstanding performance in video alignment and fine-grained frame retrieval tasks.
translated by 谷歌翻译
运动,作为视频中最明显的现象,涉及随时间的变化,对视频表示学习的发展是独一无二的。在本文中,我们提出了问题:特别是对自我监督视频表示学习的运动有多重要。为此,我们撰写了一个二重奏,用于利用对比学习政权的数据增强和特征学习的动作。具体而言,我们介绍了一种以前的对比学习(MCL)方法,其将这种二重奏视为基础。一方面,MCL大写视频中的每个帧的光流量,以在时间上和空间地样本地样本(即,横跨时间的相关帧斑块的序列)作为数据增强。另一方面,MCL进一步将卷积层的梯度图对准来自空间,时间和时空视角的光流程图,以便在特征学习中地进行地面运动信息。在R(2 + 1)D骨架上进行的广泛实验证明了我们MCL的有效性。在UCF101上,在MCL学习的表示上培训的线性分类器实现了81.91%的前1个精度,表现优于6.78%的训练预测。在动力学-400上,MCL在线方案下实现66.62%的前1个精度。代码可在https://github.com/yihengzhang-cv/mcl-motion-focused-contrastive-learning。
translated by 谷歌翻译
尽管对视频表示学习的自我监督预先预测方法的突出成功,但在未标记的预测数据集很小或源任务(预先训练)中的未标记数据和目标任务中标记的数据(Fineetuning)之间的域差异。为了缓解这些问题,我们提出了一种新的方法来通过基于知识相似性蒸馏,Auxskd的辅助预押阶段补充自我监督预测,以便更好地推广,具有明显较少量的视频数据,例如,动力学-100而不是动力学-400。我们的方法通过捕获未标记的视频数据的段之间的相似信息,将其知识迭代地将其知识蒸发到学生模型。然后,学生模型通过利用此先验知识来解决借口任务。我们还介绍了一种新颖的借口任务,视频段速度预测或VSPP,这需要我们的模型来预测输入视频的随机选择段的播放速度,以提供更可靠的自我监督的表示。我们的实验结果表明,在K100上预先训练时,UCF101和HMDB51数据集的最先进结果卓越。此外,我们表明我们的辅助辅助辅助持久性辅助阶段作为最近的艺术的自我监督方法(例如VideOpace和Rspnet),可以在UCF101和HMDB51上提高结果。我们的代码即将发布。
translated by 谷歌翻译
近年来,3D视觉的自我监督预训练引起了研究的兴趣。为了学习信息的表示,许多以前的作品都利用了3D功能的不向导,\ eg,同一场景的视图之间的透视感,深度和RGB图像之间的模态侵权次数,点云和voxels之间的格式不变。尽管他们取得了令人鼓舞的结果,但以前的研究缺乏对这些不稳定的系统性比较。为了解决这个问题,我们的工作首次引入了一个统一的框架,根据该框架可以研究各种预培训方法。我们进行了广泛的实验,并仔细研究了3D预训练中不同不变的贡献。另外,我们提出了一种简单但有效的方法,该方法可以共同预先培训3D编码器和使用对比度学习的深度图编码器。通过我们的方法进行预训练的模型在下游任务方面具有显着的性能提高。例如,预先训练的投票表现优于Sun RGB-D和扫描对象检测基准的先前方法,并具有明显的利润。
translated by 谷歌翻译
基于激光雷达的3D场景感知是自动驾驶的基本和重要任务。大多数基于激光雷达的3D识别任务的最新方法都集中在单帧3D点云数据上,并且这些方法在这些方法中被忽略。我们认为,整个框架的时间信息为3D场景感知提供了重要的知识,尤其是在驾驶场景中。在本文中,我们专注于空间和时间变化,以更好地探索3D帧的时间信息。我们设计了一个时间变化 - 意识到的插值模块和时间体素点炼油厂,以捕获4D点云中的时间变化。时间变化 - 意识插值通过捕获空间连贯性和时间变化信息来生成从上一个和当前帧的局部特征。时间体素点炼油厂在3D点云序列上构建了时间图,并使用图形卷积模块捕获时间变化。时间体素点炼油厂还将粗素级预测转换为精细的点级预测。通过我们提出的模块,新的网络TVSN在Semantickitti和Semantiposs上实现了最先进的性能。具体而言,我们的方法在MIOU中达到52.5 \%(以前的最佳方法+5.5%)在Semantickitti的多个扫描细分任务上,semanticposs的多个扫描分段任务(63.0%)(以前的最佳方法+2.8%)。
translated by 谷歌翻译
我们呈现Point-Bert,一种用于学习变压器的新范式,以概括BERT对3D点云的概念。灵感来自BERT,我们将屏蔽点建模(MPM)任务设计为预列火车点云变压器。具体地,我们首先将点云划分为几个本地点修补程序,并且具有离散变化性AutoEncoder(DVAE)的点云标记器被设计为生成包含有意义的本地信息的离散点令牌。然后,我们随机掩盖了一些输入点云的补丁并将它们送入骨干变压器。预训练目标是在销售器获得的点代币的监督下恢复蒙面地点的原始点令牌。广泛的实验表明,拟议的BERT风格的预训练策略显着提高了标准点云变压器的性能。配备了我们的预培训策略,我们表明,纯变压器架构对ModelNet40的准确性为93.8%,在ScanObjectnn的最艰难的设置上的准确性为83.1%,超越精心设计的点云模型,手工制作的设计更少。我们还证明,Point-Bert从新的任务和域中获悉的表示,我们的模型在很大程度上推动了几个射击点云分类任务的最先进。代码和预先训练的型号可在https://github.com/lulutang0608/pint -bert上获得
translated by 谷歌翻译
许多3D表示(例如,点云)是下面连续3D表面的离散样本。该过程不可避免地介绍了底层的3D形状上的采样变化。在学习3D表示中,应忽略应忽略变化,而应捕获基础3D形状的可转换知识。这成为现有代表学习范式的大挑战。本文在点云上自动编码。标准自动编码范例强制编码器捕获这种采样变体,因为解码器必须重建具有采样变化的原始点云。我们介绍了隐式AutoEncoder(IAE),这是一种简单而有效的方法,通过用隐式解码器替换点云解码器来解决这一挑战。隐式解码器输出与相同模型的不同点云采样之间共享的连续表示。在隐式表示下重建可以优先考虑编码器丢弃采样变体,引入更多空间以学习有用的功能。在一个简单的线性AutoEncoder下,理论上理论地证明这一索赔。此外,隐式解码器提供丰富的空间来为不同的任务设计合适的隐式表示。我们展示了IAE对3D对象和3D场景的各种自我监督学习任务的有用性。实验结果表明,IAE在每项任务中始终如一地优于最先进的。
translated by 谷歌翻译
大规模点云的注释仍然耗时,并且对于许多真实世界任务不可用。点云预训练是用于获得快速适配的可扩展模型的一个潜在解决方案。因此,在本文中,我们调查了一种新的自我监督学习方法,称为混合和解除戒(MD),用于点云预培训。顾名思义,我们探索如何将原始点云与混合点云分开,并利用这一具有挑战的任务作为模型培训的借口优化目标。考虑到原始数据集中的有限培训数据,这远低于普遍的想象,混合过程可以有效地产生更高质量的样本。我们构建一个基线网络以验证我们的直觉,只包含两个模块,编码器和解码器。给定混合点云,首先预先训练编码器以提取语义嵌入。然后,利用实例 - 自适应解码器根据嵌入来解除点云。尽管简单,编码器本质上是能够在训练后捕获点云关键点,并且可以快速适应下游任务,包括预先训练和微调范例的分类和分割。在两个数据集上的广泛实验表明编码器+我们的(MD)显着超越了从头划痕培训的编码器和快速收敛的编码器。在消融研究中,我们进一步研究了每个部件的效果,并讨论了拟议的自我监督学习策略的优势。我们希望这种自我监督的学习尝试点云可以铺平了减少对大规模标记数据的深度学习模型依赖的方式,并在将来节省了大量的注释成本。
translated by 谷歌翻译