Due to the irregular and disordered data structure in 3D point clouds, prior works have focused on designing more sophisticated local representation methods to capture these complex local patterns. However, the recognition performance has saturated over the past few years, indicating that increasingly complex and redundant designs no longer make improvements to local learning. This phenomenon prompts us to diverge from the trend in 3D vision and instead pursue an alternative and successful solution: deeper neural networks. In this paper, we propose DeepLA-Net, a series of very deep networks for point cloud analysis. The key insight of our approach is to exploit a small but mighty local learning block, which uses 10× fewer FLOPs, enabling the construction of very deep networks. Furthermore, we design a training supervision strategy to ensure smooth gradient backpropagation and optimization in very deep networks. We construct the DeepLA-Net family with a depth of up to 120 blocks — at least 5× deeper than recent methods — trained on a single RTX 3090. An ensemble of the DeepLA-Net achieves state-of-the-art performance on classification and segmentation tasks of S3DIS Area5 (+2.2% mIoU), ScanNet test set (+1.6% mIoU), ScanObjectNN (+2.1% OA), and ShapeNet-Part (+0.9% cls.mIoU). The code are released at https://github.com/zeng-ziyin/DeepLA-Net.

Given the prominence of 3D sensors in recent years, 3D point clouds are worthy to be further investigated for environment perception and scene understanding. Learning accurate local and global contexts in point clouds is pivotal for semantic segmentation, and neighbor aggregation and Transformers have achieved notable success in local and global perception in point cloud analysis, respectively. Nevertheless, studying each independently is far from the optimal solution for comprehensive feature learning. To address this, we take a novel step towards investigating and integrating the structures of neighbor aggregation and Transformers. In this paper, we introduce Point Neighbor Aggregation with Transformer (PointNAT), a conceptually straightforward and effective approach aiming to enhance the performance of 3D point cloud semantic segmentation. PointNAT consists of a Neighbor Aggregation Block (NAB) for local perception, a Point Transformer Block (PTB) for global modeling, and a Hybrid Block to connect NABs and PTBs. NABs effectively learn complex local features at varying scales through an improved neighbor aggregation operation and a multi-head mechanism. PTBs efficiently perform global attention using a small set of learnable key points. Hybrid Blocks serve as high-and-low frequency signal hybridizers, merging the strengths of these two blocks by adaptively assigning hybrid weights to local and global contexts. We have evaluated the performance of PointNAT with state-of-the-art networks on several benchmarks, including S3DIS, Toronto3D, and SensatUrban. PointNAT achieves mIoU scores of 77.8%, 84.7%, and 65.2% in these three dataset, respectively. Furthermore, it outperforms the baseline approach PointNeXt by 3.0%, 1.3%, and 4.2%, respectively, while utilizing only 59.9% of the parameters and 15.2% of the FLOPs. The results demonstrate PointNAT’s superior ability in accurately segmenting large-scale 3D point cloud scenes, emphasizing its potential to advance environment perception and scene understanding. Our code is available at https://github.com/zeng-ziyin/PointNAT.

Recent development of deep sequencing technologies has facilitated de novo genome sequencing projects, now conducted even by individual laboratories. However, this will yield more and more genome sequences that are not well assembled, and will hinder thorough annotation when no closely related reference genome is available. One of the challenging issues is the identification of protein-coding sequences split into multiple unassembled genomic segments, which can confound orthology assignment and various laboratory experiments requiring the identification of individual genes. In this study, using the genome of a cartilaginous fish, Callorhinchus milii, as test case, we performed gene prediction using a model specifically trained for this genome. We implemented an algorithm, designated ESPRIT, to identify possible linkages between multiple protein-coding portions derived from a single genomic locus split into multiple unassembled genomic segments. We developed a validation framework based on an artificially fragmented human genome, improvements between early and recent mouse genome assemblies, comparison with experimentally validated sequences from GenBank, and phylogenetic analyses. Our strategy provided insights into practical solutions for efficient annotation of only partially sequenced (low-coverage) genomes. To our knowledge, our study is the first formulation of a method to link unassembled genomic segments based on proteomes of relatively distantly related species as references.