mlsanityData to 13 Oct 2026

An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models

arXiv 2411.16308 ↗First posted 25 Nov 2024cs.CVcited by 22

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Existing conditional Denoising Diffusion Probabilistic Models (DDPMs) with a Noise-Conditional Framework (NCF) remain challenging for 3D scene understanding tasks, as the complex geometric details in scenes increase the difficulty of fitting the gradients of the data distribution (the scores) from semantic labels. This also results in longer training and inference time for DDPMs compared to non-DDPMs. From a different perspective, we delve deeply into the model paradigm dominated by the Conditional Network. In this paper, we propose an end-to-end robust semantic Segmentation Network based on a Conditional-Noise Framework (CNF) of DDPMs, named CDSegNet. Specifically, CDSegNet models the Noise Network (NN) as a learnable noise-feature generator. This enables the Conditional Network (CN) to understand 3D scene semantics under multi-level feature perturbations, enhancing the generalization in unseen scenes. Meanwhile, benefiting from the noise system of DDPMs, CDSegNet exhibits strong noise and sparsity robustness in experiments. Moreover, thanks to CNF, CDSegNet can generate the semantic labels in a single-step inference like non-DDPMs, due to avoiding directly fitting the scores from semantic labels in the dominant network of CDSegNet. On public indoor and outdoor benchmarks, CDSegNet significantly outperforms existing methods, achieving state-of-the-art performance.

Key facts. Cited by 22 papers in the map (data through 13 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 63 of its 77 references that are in the map. First posted on arXiv 25 Nov 2024.

Builds on

63 of 77 references.

References · 63

  1. 2017Attention Is All You Needcited by 60,106
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,777
  4. 2020Denoising Diffusion Implicit Modelscited by 9,718
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,028
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,213
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,231
  8. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,498
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,389
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,751
  11. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,096
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,889
38 more
  1. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,974
  2. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,685
  3. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,622
  4. 2021Image Super-Resolution via Iterative Refinementcited by 1,509
  5. 2020Point Transformercited by 1,465
  6. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,348
  7. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,288
  8. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,205
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,203
  10. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  11. 2020PCT: Point cloud transformercited by 731
  12. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  13. 2023Point Transformer V3: Simpler, Faster, Strongercited by 584
  14. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  15. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  16. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 385
  17. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  18. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 288
  19. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noisecited by 275
  20. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  21. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 244
  22. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  23. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 208
  24. 2023FreeU: Free Lunch in Diffusion U-Netcited by 196
  25. 2021Data Augmentation Can Improve Robustnesscited by 193
  26. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  27. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 165
  28. 2018Generating 3D Adversarial Point Cloudscited by 144
  29. 2023Denoising Diffusion Autoencoders are Unified Self-supervised Learnerscited by 130
  30. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  31. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 118
  32. 2020Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Reviewcited by 115
  33. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 111
  34. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 107
  35. 2021Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learningcited by 101
  36. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  37. 2020AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentationcited by 87
  38. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 9; 2026: 13.

22 papers.

Sort:

By area:

  1. 2025Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusioncited by 11
  2. 2025SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge Distillationcited by 9
  3. 2025A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generationcited by 4
  4. 2026PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentationcited by 4
  5. 2025Deep Neural Watermarking for Robust Copyright Protection in 3D Point Cloudscited by 3
  6. 2025PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentationcited by 2
  7. 2025OmniPlantSeg: Species Agnostic 3D Point Cloud Organ Segmentation for High-Resolution Plant Phenotyping Across Modalitiescited by 1
  8. 2026AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videoscited by 1
  9. 2026Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosiscited by 1
  10. 2026CNMBI: Determining the Number of Clusters Using Center Pairwise Matching and Boundary Filteringcited by 1
  11. 2026Unlocking Diffusion Hierarchies: Adaptive Timestep Selection for Zero-Shot Segmentationcited by 1
  12. 2025PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modelingcited by 0
10 more
  1. 2025DoReMi: Bridging 3D Domains via Topology-Aware Domain-Representation Mixture of Expertscited by 0
  2. 2025LAHNet: Local Attentive Hashing Network for Point Cloud Registrationcited by 0
  3. 2026Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3Dcited by 0
  4. 2026PiCo: Active Manifold Canonicalization for Robust Robotic Visual Anomaly Detectioncited by 0
  5. 2026Learnable Instance Attention Filtering for Adaptive Detector Distillationcited by 0
  6. 2026The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discoverycited by 0
  7. 2026TowerDataset: A Heterogeneous Benchmark for Transmission Corridor Segmentation with a Global-Local Fusion Frameworkcited by 0
  8. 2026UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decompositioncited by 0
  9. 2026B'ezier Degradation Modeling for LiDAR-based Human Motion Capturecited by 0
  10. 2026T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Denoising Diffusion Semantic Segmentation with Mask Prior Modeling
  2. 2021Label-Efficient Semantic Segmentation with Diffusion Models
  3. 2025Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation
  4. 2023Stochastic Segmentation with Conditional Categorical Diffusion Models
  5. 2023Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation
  6. 2024Latent Diffusion for Medical Image Segmentation: End to end learning for fast sampling and accuracy
  7. 2025SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation
  8. 2023Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data