Distill, Diffuse, and Semanticize (DDS): Annotation-Free 3D Scene Understanding Based on Multi-Granularity Distillation and Graph-Diffusion-Based Segmentation

• URL: http://arxiv.org/abs/2605.08293v2
• Date: Wed, 13 May 2026 09:48:13 GMT
• Title: Distill, Diffuse, and Semanticize (DDS): Annotation-Free 3D Scene Understanding Based on Multi-Granularity Distillation and Graph-Diffusion-Based Segmentation
• Abstract summary: 3D semantic scene understanding is essential for digital twins, autonomous driving, smart agriculture, and embodied perception.<n>Existing annotation-free methods often face a trade-off between semantic recognition and structural efficiency.<n>We propose a resource-efficient structure-oriented framework for region-consistent and semanticized 3D scene understanding.
• Score: 6.093743600103449
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D semantic scene understanding is essential for digital twins, autonomous driving, smart agriculture, and embodied perception, yet dense point-wise annotation for point clouds remains expensive and difficult to scale. Existing annotation-free methods often face a trade-off between semantic recognition and structural efficiency: open-vocabulary and foundation-model-driven methods provide strong semantic priors, but often come with substantial computational costs, while structure-oriented methods based on superpoints, clustering, and graph reasoning are lightweight but often produce category-agnostic regions. We propose DDS, a resource-efficient structure-oriented framework for region-consistent and semanticized annotation-free 3D scene understanding. DDS preserves the lightweight superpoint-based organization paradigm while incorporating visual semantic cues from projected features and segmentation-derived masks. It first performs multi-granularity distillation to guide the 3D backbone at the point, mask-prototype, and inter-prototype levels, then applies graph diffusion over superpoints to propagate semantic information directly in 3D, producing coherent region representations without costly spectral decomposition or dense open-vocabulary 3D feature fields. Finally, DDS uses segmentation-cluster association to assign interpretable semantic names to category-agnostic 3D clusters. Experiments on real-world datasets show that DDS achieves the best performance among representative structure-oriented annotation-free baselines, improving oAcc, mAcc, and mIoU by up to 5.9%, 8.1%, and 2.4%, respectively. These results demonstrate that DDS improves region consistency and lightweight semantic recognition, providing a scalable and interpretable solution for annotation-free 3D scene understanding.

Related papers

• EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation [92.9295124221522]
  EPS3D is an end-to-end feed-forward framework for open-vocabulary 3D panoptic segmentation.<n>It predicts semantic and instance features from multi-view images, improving 3D consistency and avoiding error accumulation.<n>It supports tasks like robotic manipulation and 3D scene editing.
  arXiv  Detail & Related papers  (2026-06-08T03:26:54Z)
• LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding [9.377694035678948]
  We present a novel framework that leverages Sparse Voxel Rasterization (SVRaster) as a structured, disjoint geometry representation.<n>This enables a deterministic, confidence-aware feature registration process and suppresses the semantic bleeding artifact common in 3DGS.<n>Our approach achieves state-of-the-art performance on Open Vocabulary 3D Object Retrieval and Point Cloud Understanding benchmarks.
  arXiv  Detail & Related papers  (2026-04-01T20:48:06Z)
• Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds [53.82500407523346]
  PointINS is an instance-oriented self-supervised framework that enriches point cloud representations through geometry-aware learning.<n>PointINS achieves on average +3.5% mAP improvement for indoor instance segmentation and +4.1% PQ gain for outdoor panoptic segmentation.
  arXiv  Detail & Related papers  (2026-03-26T08:31:06Z)
• Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model [51.02616473941499]
  3D object segmentation with Large Language Models (LLMs) has become a prevailing paradigm due to its broad semantics, task flexibility, and strong generalization.<n>However, this paradigm is hindered by representation misalignment: LLMs process high-level semantic tokens, whereas 3D point clouds convey only dense geometric structures.<n>We present the Point Linguist Model (PLM), a general framework that bridges the representation gap between LLMs and dense 3D point clouds.
  arXiv  Detail & Related papers  (2025-09-09T15:01:28Z)
• Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation [66.65719382619538]
  Current methods for 3D semantic segmentation propose training models with limited annotations to address the difficulty of annotating large, irregular, and unordered 3D point cloud data.<n>We present a novel approach that maximizes the utility of sparsely available 3D annotations incorporating segmentation masks generated by 2D foundation models.
  arXiv  Detail & Related papers  (2025-08-27T14:13:01Z)
• Semantic-aware DropSplat: Adaptive Pruning of Redundant Gaussians for 3D Aerial-View Segmentation [15.196083762043004]
  We propose a novel 3D-AVS-SS approach named SAD-Splat to address semantic ambiguity in aerial images.<n>Our method integrates semantic confidence estimation with a learnable sparsity mechanism based on the Hard Concrete distribution.<n>It achieves an excellent balance between segmentation accuracy and representation compactness.
  arXiv  Detail & Related papers  (2025-08-13T08:57:38Z)
• Segment Any 3D-Part in a Scene from a Sentence [50.46950922754459]
  This paper aims to achieve the segmentation of any 3D part in a scene based on natural language descriptions.<n>We introduce the 3D-PU dataset, the first large-scale 3D dataset with dense part annotations.<n>On the methodological side, we propose OpenPart3D, a 3D-input-only framework to tackle the challenges of part-level segmentation.
  arXiv  Detail & Related papers  (2025-06-24T05:51:22Z)
• LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds [5.636411923613415]
  We introduce LogoSP to learn 3D semantics from both local and global point features.<n>Our approach is to discover 3D semantic information by grouping superpoints according to their global patterns in the frequency domain.
  arXiv  Detail & Related papers  (2025-06-09T15:21:37Z)
• BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis [33.53327976669034]
  We revisit 3D semantic segmentation through a more granular lens, shedding light on subtle complexities that are typically overshadowed by broader performance metrics.<n>We introduce an innovative 3D semantic segmentation network called BFANet that incorporates detailed analysis of semantic boundary features.
  arXiv  Detail & Related papers  (2025-03-16T15:13:11Z)
• 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds [81.14476072159049]
  3D Affordance detection is a challenging problem with broad applications on various robotic tasks.<n>We reformulate the traditional affordance detection paradigm into textit Reasoning Affordance (IRAS) task.<n>We propose 3D-ADLLM, a framework designed for reasoning affordance detection in 3D open-scene.
  arXiv  Detail & Related papers  (2025-02-27T12:29:44Z)
• Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding [59.51535163599723]
  FreeGS is an unsupervised semantic-embedded 3DGS framework that achieves view-consistent 3D scene understanding without the need for 2D labels.<n>FreeGS performs comparably to state-of-the-art methods while avoiding the complex data preprocessing workload.
  arXiv  Detail & Related papers  (2024-11-29T08:52:32Z)
• Bayesian Self-Training for Semi-Supervised 3D Segmentation [59.544558398992386]
  3D segmentation is a core problem in computer vision. densely labeling 3D point clouds to employ fully-supervised training remains too labor intensive and expensive. Semi-supervised training provides a more practical alternative, where only a small set of labeled data is given, accompanied by a larger unlabeled set.
  arXiv  Detail & Related papers  (2024-09-12T14:54:31Z)
• Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignment [55.11291053011696]
  This work presents a framework for dealing with 3D scene understanding when the labeled scenes are quite limited.<n>To extract knowledge for novel categories from the pre-trained vision-language models, we propose a hierarchical feature-aligned pre-training and knowledge distillation strategy.<n>In the limited reconstruction case, our proposed approach, termed WS3D++, ranks 1st on the large-scale ScanNet benchmark.
  arXiv  Detail & Related papers  (2023-12-01T15:47:04Z)
• Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding [57.47315482494805]
  Open-world instance-level scene understanding aims to locate and recognize unseen object categories that are not present in the annotated dataset. This task is challenging because the model needs to both localize novel 3D objects and infer their semantic categories. We propose to harness pre-trained vision-language (VL) foundation models that encode extensive knowledge from image-text pairs to generate captions for 3D scenes.
  arXiv  Detail & Related papers  (2023-08-01T07:50:14Z)
• Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision [65.19589997822155]
  We introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision. We show that the proposed network can be trained with cheap, or even off-the-shelf bounding box-level annotations and subcloud-level tags.
  arXiv  Detail & Related papers  (2022-01-09T09:07:48Z)
• 3D Segmentation Learning from Sparse Annotations and Hierarchical Descriptors [7.161067294394475]
  GIDSeg is a novel approach that can simultaneously learn segmentation from sparse annotations. GIDSeg depicts global- and individual- relation via a dynamic edge convolution network. An adversarial learning module is also designed to further enhance the conditional constraint of identity descriptors.
  arXiv  Detail & Related papers  (2021-05-27T00:31:37Z)
• S3Net: 3D LiDAR Sparse Semantic Segmentation Network [1.330528227599978]
  S3Net is a novel convolutional neural network for LiDAR point cloud semantic segmentation. It adopts an encoder-decoder backbone that consists of Sparse Intra-channel Attention Module (SIntraAM) and Sparse Inter-channel Attention Module (SInterAM)
  arXiv  Detail & Related papers  (2021-03-15T22:15:24Z)

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.