PI3DETR: Parametric Instance Detection of 3D Point Cloud Edges with a Geometry-Aware 3DETR

• URL: http://arxiv.org/abs/2509.03262v1
• Date: Wed, 03 Sep 2025 12:24:25 GMT
• Title: PI3DETR: Parametric Instance Detection of 3D Point Cloud Edges with a Geometry-Aware 3DETR
• Authors: Fabio F. Oberweger, Michael Schwingshackl, Vanessa Staderini,
• Abstract summary: We present PI3DETR, an end-to-end framework that directly predicts 3D parametric curve instances from raw point clouds.<n> PI3DETR sets a new state-of-the-art on the ABC dataset and generalizes effectively to real sensor data, offering a simple yet powerful solution for 3D edge and curve estimation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We present PI3DETR, an end-to-end framework that directly predicts 3D parametric curve instances from raw point clouds, avoiding the intermediate representations and multi-stage processing common in prior work. Extending 3DETR, our model introduces a geometry-aware matching strategy and specialized loss functions that enable unified detection of differently parameterized curve types, including cubic B\'ezier curves, line segments, circles, and arcs, in a single forward pass. Optional post-processing steps further refine predictions without adding complexity. This streamlined design improves robustness to noise and varying sampling densities, addressing critical challenges in real world LiDAR and 3D sensing scenarios. PI3DETR sets a new state-of-the-art on the ABC dataset and generalizes effectively to real sensor data, offering a simple yet powerful solution for 3D edge and curve estimation.

Related papers

• PIRATR: Parametric Object Inference for Robotic Applications with Transformers in 3D Point Clouds [0.9134244356393665]
  We present PIRATR, an end-to-end 3D object detection framework for robotic use cases in point clouds.<n>Our method streamlines parametric 3D object detection by jointly estimating multi-class 6-DoF poses and class-specific parametric attributes.<n>PIRATR generalizes effectively to real outdoor LiDAR scans, achieving a detection mAP of 0.919 without additional fine-tuning.
  arXiv  Detail & Related papers  (2026-02-05T11:29:09Z)
• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis [51.37795317716487]
  We propose the Adaptive Point-Prompt Tuning (APPT) method, which fine-tunes pre-trained models with a modest number of parameters.<n>We convert raw point clouds into point embeddings by aggregating local geometry to capture spatial features followed by linear layers.<n>To calibrate self-attention across source domains of any modality to 3D, we introduce a prompt generator that shares weights with the point embedding module.
  arXiv  Detail & Related papers  (2025-08-30T06:02:21Z)
• Level-Set Parameters: Novel Representation for 3D Shape Analysis [70.23417107911567]
  Recent development of neural fields brings in level-set parameters from signed distance functions as a novel, continuous, and numerical representation of 3D shapes.<n>We establish correlations across different shapes by formulating them as a pseudo-normal distribution, and learn the distribution prior to the respective dataset.<n>To further explore the level-set parameters with shape transformations, we propose to condition a subset of these parameters on rotations and translations, and generate them with a hypernetwork.
  arXiv  Detail & Related papers  (2024-12-18T04:50:19Z)
• LineGS : 3D Line Segment Representation on 3D Gaussian Splatting [0.0]
  LineGS is a novel method that combines geometry-guided 3D line reconstruction with a 3D Gaussian splatting model.<n>The results show significant improvements in both geometric accuracy and model compactness compared to baseline methods.
  arXiv  Detail & Related papers  (2024-11-30T13:29:36Z)
• 3D Neural Edge Reconstruction [61.10201396044153]
  We introduce EMAP, a new method for learning 3D edge representations with a focus on both lines and curves. Our method implicitly encodes 3D edge distance and direction in Unsigned Distance Functions (UDF) from multi-view edge maps. On top of this neural representation, we propose an edge extraction algorithm that robustly abstracts 3D edges from the inferred edge points and their directions.
  arXiv  Detail & Related papers  (2024-05-29T17:23:51Z)
• ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds [52.03819676074455]
  ParaPoint is an unsupervised neural learning pipeline for achieving global free-boundary surface parameterization. This work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.
  arXiv  Detail & Related papers  (2024-03-15T14:35:05Z)
• SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes [16.355677959323426]
  We introduce SepicNet, a novel deep network for the detection and parametrization of sharp edges in 3D shapes as primitive curves. We develop an adaptive point cloud sampling technique that captures the sharp features better than uniform sampling.
  arXiv  Detail & Related papers  (2023-04-13T13:37:21Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception [122.53774221136193]
  State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution. A natural remedy is to utilize the 3D voxelization and 3D convolution network. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
  arXiv  Detail & Related papers  (2021-09-12T06:25:11Z)
• Reinforced Axial Refinement Network for Monocular 3D Object Detection [160.34246529816085]
  Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image. Conventional approaches sample 3D bounding boxes from the space and infer the relationship between the target object and each of them, however, the probability of effective samples is relatively small in the 3D space. We propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step. This requires designing a policy which gets a reward after several steps, and thus we adopt reinforcement learning to optimize it.
  arXiv  Detail & Related papers  (2020-08-31T17:10:48Z)

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.