Scholarlink

<p>Point clouds, as an unstructured set of points, have emerged as a crucial data format in modern 3D deep learning tasks, facilitating applications ranging from object recognition to scene understanding. However, traditional point cloud encoding methods grounded in voxelization or grouping strategies often suffer from inefficiencies and ambiguities during local point cloud processing. These limitations can hinder the extraction of fine-grained features and impact the overall performance of 3D learning models. Notably, compact representations, such as the neural field representation employed in 3D shape reconstruction, have demonstrated remarkable capabilities in capturing the structural integrity and intricate details of 3D objects. Nevertheless, the utilization of these advanced representations in discriminative tasks remains largely unexplored territory. In response to these challenges and opportunities, we propose <b>Point2Seq</b>, a novel point cloud encoding method. <b>Point2Seq</b> constructs a new representation of point clouds by leveraging serialized and discrete encoding techniques. This approach transforms point clouds into a grid-based format, which not only enables efficient spatial interpolation but also facilitates the expansion of the receptive field for downstream tasks, thereby enhancing the model’s ability to capture context and spatial relationships. To comprehensively assess the effectiveness of <b>Point2Seq</b>, we conduct extensive evaluations on a diverse set of canonical object-level point cloud benchmarks. Our experiments cover a wide spectrum of tasks, including low-level tasks like point cloud completion, high-level tasks such as classification and part segmentation, as well as few-shot learning scenarios. The results demonstrate that <b>Point2Seq</b> achieves state-of-the-art performance across these tasks. Additionally, the reduced noise in the input data allows our representation to converge more rapidly during downstream task training, further underscoring its superiority. The code for <b>Point2Seq</b> will be publicly released to promote reproducibility and further research in this area.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Point2Seq: Quantized Serialization Encoding for Object Point Cloud Pretraining

  • 期刊论文

  • 发表日期：

    2026年5月26日

查看全文
  • Xumin Yu,
  • Zuyan Liu,
  • Jie Zhou,
  • Jiwen Lu

摘要

Point clouds, as an unstructured set of points, have emerged as a crucial data format in modern 3D deep learning tasks, facilitating applications ranging from object recognition to scene understanding. However, traditional point cloud encoding methods grounded in voxelization or grouping strategies often suffer from inefficiencies and ambiguities during local point cloud processing. These limitations can hinder the extraction of fine-grained features and impact the overall performance of 3D learning models. Notably, compact representations, such as the neural field representation employed in 3D shape reconstruction, have demonstrated remarkable capabilities in capturing the structural integrity and intricate details of 3D objects. Nevertheless, the utilization of these advanced representations in discriminative tasks remains largely unexplored territory. In response to these challenges and opportunities, we propose Point2Seq, a novel point cloud encoding method. Point2Seq constructs a new representation of point clouds by leveraging serialized and discrete encoding techniques. This approach transforms point clouds into a grid-based format, which not only enables efficient spatial interpolation but also facilitates the expansion of the receptive field for downstream tasks, thereby enhancing the model’s ability to capture context and spatial relationships. To comprehensively assess the effectiveness of Point2Seq, we conduct extensive evaluations on a diverse set of canonical object-level point cloud benchmarks. Our experiments cover a wide spectrum of tasks, including low-level tasks like point cloud completion, high-level tasks such as classification and part segmentation, as well as few-shot learning scenarios. The results demonstrate that Point2Seq achieves state-of-the-art performance across these tasks. Additionally, the reduced noise in the input data allows our representation to converge more rapidly during downstream task training, further underscoring its superiority. The code for Point2Seq will be publicly released to promote reproducibility and further research in this area.