Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models.

Nowadays, pre-training big models on large-scale datasets has achieved great success and dominated many downstream tasks in natural language processing and 2D vision, while pre-training in 3D vision is still under development. In this paper, we provide a new perspective of transferring the pre-trained knowledge from 2D domain to 3D domain with Point-to-Pixel Prompting in data space and Pixel-to-Point distillation in feature space, exploiting shared knowledge in images and point clouds that display the same visual world. Following the principle of prompting engineering, Point-to-Pixel Prompting transforms point clouds into colorful images with geometry-preserved projection and geometry-aware coloring. Then the pre-trained image models can be directly implemented for point cloud tasks without structural changes or weight modifications. With projection correspondence in feature space, Pixel-to-Point distillation further regards pre-trained image models as the teacher model and distills pre-trained 2D knowledge to student point cloud models, remarkably enhancing inference efficiency and model capacity for point cloud analysis. We conduct extensive experiments in both object classification and scene segmentation under various settings to demonstrate the superiority of our method. In object classification, we reveal the important scale-up trend of Point-to-Pixel Prompting and attain 90.3% accuracy on ScanObjectNN dataset, surpassing previous literature by a large margin. In scene-level semantic segmentation, our method outperforms traditional 3D analysis approaches and shows competitive capacity in dense prediction tasks.

AdaPoinTr: Diverse Point Cloud Completion With Adaptive Geometry-Aware Transformers.

In this paper, we propose a Transformer encoder-decoder architecture, called PoinTr, which reformulates point cloud completion as a set-to-set translation problem and employs a geometry-aware block to model local geometric relationships explicitly. The migration of Transformers enables our model to better learn structural knowledge and preserve detailed information for point cloud completion. Taking a step towards more complicated and diverse situations, we further propose AdaPoinTr by developing an adaptive query generation mechanism and designing a novel denoising task during completing a point cloud. Coupling these two techniques enables us to train the model efficiently and effectively: we reduce training time (by 15x or more) and improve completion performance (over 20%). Additionally, we propose two more challenging benchmarks with more diverse incomplete point clouds that can better reflect real-world scenarios to promote future research. We also show our method can be extended to the scene-level point cloud completion scenario by designing a new geometry-enhanced semantic scene completion framework. Extensive experiments on the existing and newly-proposed datasets demonstrate the effectiveness of our method, which attains 6.53 CD on PCN, 0.81 CD on ShapeNet-55 and 0.392 MMD on real-world KITTI, surpassing other work by a large margin and establishing new state-of-the-arts on various benchmarks. Most notably, AdaPoinTr can achieve such promising performance with higher throughputs and fewer FLOPs compared with the previous best methods in practice.

An improved method using adaptive smoothing for GNSS tomographic imaging of ionosphere.

Global navigation satellite system (GNSS) is a well-established sensors in the recent ionosphere research. By comparing with classical meteorological equipments, the GNSS application can obtain more reliable and precious ionospheric total electron content (TEC) result. However, the most used GNSS ionospheric tomography technique is sensitive to a priori information due to the sparse and non-uniform distribution of GNSS stations. In this paper, we propose an improved method based on adaptive Laplacian smoothing and algebraic reconstruction technique (ALS-ART). Compared with traditional constant constraints, this method is less dependent on a priori information and adaptive smoothing constraints is closer to the actual situation. Tomography experiments using simulated data show that reconstruction accuracy of ionospheric electron density using ALS-ART method is significantly improved. We also use the method to do the analysis of real observation data and compare the tomography results with ionosonde observation data. The results demonstrate the superiority and reliability of the proposed method compared to traditional constant constraints method which will further improve the capability of obtaining precious ionosphere TEC by using GNSS.

Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration.

Due to its importance in clinical science, the estimation of physiological states (e.g., the severity of pathological tremor) has aroused growing interest in machine learning community. While the physiological state is a continuous variable, its continuity is lost when the physiological state is quantized into a few discrete classes during recording and labeling. The discreteness introduces misalignment between the true value and its label, meaning that these labels are unfortunately imprecise and coarse-grained. Most previous work did not consider the inaccuracy and directly utilized the coarse labels to train the machine learning algorithms, whose predictions are also coarse-grained. In this work, we propose to learn a precise, fine-grained estimation of physiological states using these coarse-grained ground truths. Established on mathematical rigorous proof, we utilize imprecise labels to restore the probabilistic distribution of precise labels in an approximate order-preserving fashion, then the deep neural network learns from this distribution and offers fine-grained estimation. We demonstrate the effectiveness of our approach in assessing the pathological tremor in Parkinson's Disease and estimating the systolic blood pressure from bioelectrical signals.