Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes

• URL: http://arxiv.org/abs/2503.24229v1
• Date: Mon, 31 Mar 2025 15:42:10 GMT
• Title: Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes
• Authors: Daichi Otsuka, Shinichi Mae, Ryosuke Yamada, Hirokatsu Kataoka,
• Abstract summary: We propose a pre-training with 3D synthetic data to train a 3D point cloud instance segmentation model.<n>We directly generate 3D point cloud data with Point-E for inserting a generated data into a 3D scene.<n>In the experimental section, we compare our pre-training method with baseline methods indicated improved performance.
• Score: 9.632798041899289
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the recent years, the research community has witnessed growing use of 3D point cloud data for the high applicability in various real-world applications. By means of 3D point cloud, this modality enables to consider the actual size and spatial understanding. The applied fields include mechanical control of robots, vehicles, or other real-world systems. Along this line, we would like to improve 3D point cloud instance segmentation which has emerged as a particularly promising approach for these applications. However, the creation of 3D point cloud datasets entails enormous costs compared to 2D image datasets. To train a model of 3D point cloud instance segmentation, it is necessary not only to assign categories but also to provide detailed annotations for each point in the large-scale 3D space. Meanwhile, the increase of recent proposals for generative models in 3D domain has spurred proposals for using a generative model to create 3D point cloud data. In this work, we propose a pre-training with 3D synthetic data to train a 3D point cloud instance segmentation model based on generative model for 3D scenes represented by point cloud data. We directly generate 3D point cloud data with Point-E for inserting a generated data into a 3D scene. More recently in 2025, although there are other accurate 3D generation models, even using the Point-E as an early 3D generative model can effectively support the pre-training with 3D synthetic data. In the experimental section, we compare our pre-training method with baseline methods indicated improved performance, demonstrating the efficacy of 3D generative models for 3D point cloud instance segmentation.

Related papers

• DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation [51.43837087865105]
  Vision foundation models (VFMs) trained on large-scale image datasets provide high-quality features that have significantly advanced 2D visual recognition. Their potential in 3D vision remains largely untapped, despite the common availability of 2D images alongside 3D point cloud datasets. We introduce DITR, a simple yet effective approach that extracts 2D foundation model features, projects them to 3D, and finally injects them into a 3D point cloud segmentation model.
  arXiv  Detail & Related papers  (2025-03-24T17:59:11Z)
• 3DSES: an indoor Lidar point cloud segmentation dataset with real and pseudo-labels from a 3D model [1.7249361224827533]
  We present 3DSES, a new dataset of indoor dense TLS colorized point clouds covering 427 m 2. 3DSES has a unique double annotation format: semantic labels annotated at the point level alongside a full 3D CAD model of the building. We show that our model-to-cloud alignment can produce pseudo-labels on our point clouds with a &gt; 95% accuracy, allowing us to train deep models with significant time savings.
  arXiv  Detail & Related papers  (2025-01-29T10:09:32Z)
• Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding [27.755532663325244]
  Textguided Geometric Augmentation (TeGA) is tailored for language-image-3D pretraining, which achieves SoTA in zero-shot 3D classification. We show that TeGA effectively bridges the 3D data gap, enabling robust zero-shot 3D classification even with limited real training data.
  arXiv  Detail & Related papers  (2025-01-16T03:54:06Z)
• DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data [50.164670363633704]
  We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets from text prompts. Our model is directly trained on extensive noisy and unaligned in-the-wild' 3D assets. We achieve state-of-the-art performance in both single-class generation and text-to-3D generation.
  arXiv  Detail & Related papers  (2024-06-06T17:58:15Z)
• DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields [68.94868475824575]
  This paper introduces a novel approach capable of generating infinite, high-quality 3D-consistent 2D annotations alongside 3D point cloud segmentations. We leverage the strong semantic prior within a 3D generative model to train a semantic decoder. Once trained, the decoder efficiently generalizes across the latent space, enabling the generation of infinite data.
  arXiv  Detail & Related papers  (2023-11-18T21:58:28Z)
• Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation [67.07112533415116]
  We present a novel framework that adapts various foundational models for the 3D point cloud segmentation task. Our approach involves making initial predictions of 2D semantic masks using different large vision models. To generate robust 3D semantic pseudo labels, we introduce a semantic label fusion strategy that effectively combines all the results via voting.
  arXiv  Detail & Related papers  (2023-11-03T15:41:15Z)
• Uni3D: Exploring Unified 3D Representation at Scale [66.26710717073372]
  We present Uni3D, a 3D foundation model to explore the unified 3D representation at scale. Uni3D uses a 2D ViT end-to-end pretrained to align the 3D point cloud features with the image-text aligned features. We show that the strong Uni3D representation also enables applications such as 3D painting and retrieval in the wild.
  arXiv  Detail & Related papers  (2023-10-10T16:49:21Z)
• A Convolutional Architecture for 3D Model Embedding [1.3858051019755282]
  We propose a deep learning architecture to handle 3D models as an input. We show that the embedding representation conveys semantic information that helps to deal with the similarity assessment of 3D objects.
  arXiv  Detail & Related papers  (2021-03-05T15:46:47Z)
• Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation [87.54570024320354]
  State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space. We develop a 3D cylinder partition and a 3D cylinder convolution based framework, termed as Cylinder3D, which exploits the 3D topology relations and structures of driving-scene point clouds.
  arXiv  Detail & Related papers  (2020-08-04T13:56:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.