NoPA: Non-Parametric Online 3D Scene Graph Generation

• URL: http://arxiv.org/abs/2607.00529v1
• Date: Wed, 01 Jul 2026 07:18:07 GMT
• Title: NoPA: Non-Parametric Online 3D Scene Graph Generation
• Abstract summary: NoPA represents each object as a separate non-parametric distribution.<n>We leverage maximum mean discrepancy on kernel density estimates to enable robust merging of object candidates.<n>NoPA substantially outperforms current methods without sacrificing real-time inference speed.
• Score: 57.15076373014265
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Classic 3D scene graph generation approaches fail to work in real-time due to the heavy computational cost of environment mapping and the need to generate intermediate point-cloud representations. To alleviate this issue, a recent work eschews point clouds in favor of a lightweight Gaussian distribution for each object. This approximation drastically speeds up inference and enables real-time 3D scene graph generation. However, the representation has two key weaknesses. \textbf{1)} Each object is approximated by a single 3D Gaussian, which causes a severe loss of 3D geometric detail. \textbf{2)} The discrepancy between this approximation and the true object geometry exacerbates the inaccurate merging of object candidates during online inference. To address these issues, we propose \textbf{NoPA}, which represents each object as a separate non-parametric distribution. This formulation retains 3D geometric information while preserving real-time inference of the parametric Gaussian formulation. To build upon our novel object representation, we propose a tailored merging strategy to recover coherent object instances. Specifically, we leverage maximum mean discrepancy on kernel density estimates to enable robust merging of object candidates during online exploration while minimizing added computational complexity. The key is to maintain a fixed particle set per object. Furthermore, to rectify the relation loss caused by misclassified objects, NoPA propagates relationships between objects with high affinity. Experiments show that NoPA substantially outperforms current methods without sacrificing real-time inference speed.

Related papers

• DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors [22.5705525097147]
  Existing methods often struggle to construct reliable 3D scene graphs due to unstable 3D object representations and missing relations caused by frame-wise inference.<n>DeWorldSG addresses these issues by instance estimating geometric-level 3D Gaussian distributions through depth-guided filtering.<n> Experiments on the 3DSSG and ReplicaSSSG datasets demonstrate state-of-the-art (SoTA) performance in both object and prediction.
  arXiv  Detail & Related papers  (2026-07-01T12:55:09Z)
• DVMNet++: Rethinking Relative Pose Estimation for Unseen Objects [59.51874686414509]
  Existing approaches typically predict 3D translation utilizing the ground-truth object bounding box and approximate 3D rotation with a large number of discrete hypotheses.<n>We present a Deep Voxel Matching Network (DVMNet++) that computes the relative object pose in a single pass.<n>Our approach delivers more accurate relative pose estimates for novel objects at a lower computational cost compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-20T15:41:32Z)
• Explicit3D: Graph Network with Spatial Inference for Single Image 3D Object Detection [35.85544715234846]
  We propose a dynamic sparse graph pipeline named Explicit3D based on object geometry and semantics features. Our experimental results on the SUN RGB-D dataset demonstrate that our Explicit3D achieves better performance balance than the-state-of-the-art.
  arXiv  Detail & Related papers  (2023-02-13T16:19:54Z)
• DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction [51.96971077984869]
  Self-supervised depth learning from monocular images normally relies on the 2D pixel-wise photometric relation between temporally adjacent image frames. This work proposes Density Volume Construction Network (DevNet), a novel self-supervised monocular depth learning framework.
  arXiv  Detail & Related papers  (2022-09-14T00:08:44Z)
• Homography Loss for Monocular 3D Object Detection [54.04870007473932]
  A differentiable loss function, termed as Homography Loss, is proposed to achieve the goal, which exploits both 2D and 3D information. Our method yields the best performance compared with the other state-of-the-arts by a large margin on KITTI 3D datasets.
  arXiv  Detail & Related papers  (2022-04-02T03:48:03Z)
• IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment [58.8330387551499]
  We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) We propose IDEA-Net, an end-to-end deep learning framework, which disentangles the problem under the assistance of the explicitly learned temporal consistency. We demonstrate the effectiveness of our method on various point cloud sequences and observe large improvement over state-of-the-art methods both quantitatively and visually.
  arXiv  Detail & Related papers  (2022-03-22T10:14:08Z)
• Robust Extrinsic Symmetry Estimation in 3D Point Clouds [4.416484585765027]
  Detecting the reflection symmetry plane of an object represented by a 3D point cloud is a fundamental problem in 3D computer vision and geometry processing. We propose a statistical estimator-based approach for the plane of reflection symmetry that is robust to outliers and missing parts.
  arXiv  Detail & Related papers  (2021-09-21T03:09:51Z)
• Factor Graph based 3D Multi-Object Tracking in Point Clouds [8.411514688735183]
  We propose a novel optimization-based approach that does not rely on explicit and fixed assignments. We demonstrate its performance on the real world KITTI tracking dataset and achieve better results than many state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2020-08-12T13:34:46Z)
• Robust 6D Object Pose Estimation by Learning RGB-D Features [59.580366107770764]
  We propose a novel discrete-continuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-02-29T06:24:55Z)

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.