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.

Point clouds are characterized by irregularity and unstructuredness, which pose challenges in efficient data exploitation and discriminative feature extraction. In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels. \mr{Intuitively, Flattening-Net implicitly approximates a locally smooth 3D-to-2D surface flattening process while effectively preserving neighborhood consistency.} \mr{As a generic representation modality, PGI inherently encodes the intrinsic property of the underlying manifold structure and facilitates surface-style point feature aggregation.} To demonstrate its potential, we construct a unified learning framework directly operating on PGIs to achieve \mr{diverse types of high-level and low-level} downstream applications driven by specific task networks, including classification, segmentation, reconstruction, and upsampling. Extensive experiments demonstrate that our methods perform favorably against the current state-of-the-art competitors. We will make the code and data publicly available at https://github.com/keeganhk/Flattening-Net.

Point clouds captured by scanning devices are often incomplete due to occlusion. Point cloud completion aims to predict the complete shape based on its partial input. Existing methods can be classified into supervised and unsupervised methods. However, both of them require a large number of 3D complete point clouds, which are difficult to capture. In this paper, we propose Cross-PCC, an unsupervised point cloud completion method without requiring any 3D complete point clouds. We only utilize 2D images of the complete objects, which are easier to capture than 3D complete and clean point clouds. Specifically, to take advantage of the complementary information from 2D images, we use a single-view RGB image to extract 2D features and design a fusion module to fuse the 2D and 3D features extracted from the partial point cloud. To guide the shape of predicted point clouds, we project the predicted points of the object to the 2D plane and use the foreground pixels of its silhouette maps to constrain the position of the projected points. To reduce the outliers of the predicted point clouds, we propose a view calibrator to move the points projected to the background into the foreground by the single-view silhouette image. To the best of our knowledge, our approach is the first point cloud completion method that does not require any 3D supervision. The experimental results of our method are superior to those of the state-of-the-art unsupervised methods by a large margin. Moreover, compared to some supervised methods, our method achieves similar performance. We will make the source code publicly available at https://github.com/ltwu6/cross-pcc.

作为3D对象的两个基本表示方式，2D多视图图像和3D点云反映了来自视觉外观和几何结构各个方面的形状信息。与基于深度学习的2D多视图图像建模不同，该模型在各种3D形状分析任务中展示了领先的性能，基于3D点云的几何建模仍然遭受学习能力不足。在本文中，我们创新地构建了一个统一的跨模式知识转移框架，该框架将2D图像的歧视性视觉描述器提炼成3D点云的几何描述符。从技术上讲，在经典的教师学习范式下，我们提出了多视觉愿景到几何的蒸馏，由深入的2D图像编码器作为老师和深层的3D点云编码器组成。为了实现异质特征对齐，我们进一步提出了可见性感知的特征投影，通过该投影可以通过该投影将每个点嵌入可以汇总到多视图几何描述符中。对3D形状分类，部分分割和无监督学习的广泛实验验证了我们方法的优势。我们将公开提供代码和数据。

由遮挡，信号丢失或手动注释错误引起的3D边界框的地面真相注释的固有歧义可能会使训练过程中的深3D对象检测器混淆，从而使检测准确性恶化。但是，现有方法在某种程度上忽略了此类问题，并将标签视为确定性。在本文中，我们提出了GLENET，这是一个从条件变异自动编码器改编的生成标签不确定性估计框架，以建模典型的3D对象与其潜在的潜在基边界框之间具有潜在变量的一对一关系。 Glenet产生的标签不确定性是一个插件模块，可以方便地集成到现有的深3D检测器中，以构建概率检测器并监督本地化不确定性的学习。此外，我们提出了概率探测器中的不确定性质量估计量架构，以指导对IOU分支的培训，并预测了本地化不确定性。我们将提出的方法纳入各种流行的3D检测器中，并观察到它们的性能显着提高到Waymo Open DataSet和Kitti数据集中的当前最新技术。

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.

Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary findings on the possibility for deep models to transfer knowledge from language to music, by finetuning large language models pre-trained on a massive text corpus on only hundreds of MIDI files of drum performances. We show that by doing so, one of the largest, state-of-the-art models (GPT3) is capable of generating reasonable drum grooves, while models that are not pre-trained (Transformer) shows no such ability beyond naive repetition. Evaluating generated music is a challenging task, more so is evaluating drum grooves with little precedence in literature. Hence, we propose a tailored structural evaluation method and analyze drum grooves produced by GPT3 compared to those played by human professionals, exposing the strengths and weaknesses of such generation by language-to-music transfer. Our findings suggest that language-to-music transfer learning with large language models is viable and promising.