mlsanityData to 14 Oct 2026

SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization

arXiv 2503.14558 ↗First posted 18 Mar 2025cs.CV cs.ROcited by 21

On the map: World models → World modeling from LiDAR generation

also in 1 more
Abstract (arXiv)

Point cloud (PC) processing tasks-such as completion, upsampling, denoising, and colorization-are crucial in applications like autonomous driving and 3D reconstruction. Despite substantial advancements, prior approaches often address each of these tasks independently, with separate models focused on individual issues. However, this isolated approach fails to account for the fact that defects like incompleteness, low resolution, noise, and lack of color frequently coexist, with each defect influencing and correlating with the others. Simply applying these models sequentially can lead to error accumulation from each model, along with increased computational costs. To address these challenges, we introduce SuperPC, the first unified diffusion model capable of concurrently handling all four tasks. Our approach employs a three-level-conditioned diffusion framework, enhanced by a novel spatial-mix-fusion strategy, to leverage the correlations among these four defects for simultaneous, efficient processing. We show that SuperPC outperforms the state-of-the-art specialized models as well as their combination on all four individual tasks.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Placed in World modeling from LiDAR generation, one of 11 directions in World models. Builds on 52 of its 79 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

52 of 79 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion20 Mar
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space7 Jun

Other references · 50

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  7. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  8. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  9. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  10. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  11. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  12. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
38 more
  1. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  2. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
  3. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  4. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  5. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  6. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  7. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  8. 2018PCN: Point Completion Networkcited by 384
  9. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 336
  10. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 333
  11. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  12. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  13. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  14. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  15. 2020CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detectioncited by 147
  16. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  17. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 112
  18. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111
  19. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  20. 2020Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systemscited by 100
  21. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  22. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  23. 2023PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstructioncited by 84
  24. 2021Score-Based Point Cloud Denoisingcited by 83
  25. 2022Multi-modal Sensor Fusion for Auto Driving Perception: A Surveycited by 76
  26. 2023ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detectioncited by 76
  27. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  28. 2023AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformerscited by 67
  29. 2019PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Modulecited by 56
  30. 2021Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsamplingcited by 48
  31. 2021View-Guided Point Cloud Completioncited by 46
  32. 2023Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functionscited by 43
  33. 2022Cross-modal Learning for Image-Guided Point Cloud Shape Completioncited by 36
  34. 2019Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Cloudscited by 35
  35. 2023A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsamplingcited by 28
  36. 2021Denoise and Contrast for Category Agnostic Shape Completioncited by 17
  37. 2021Deep Point Cloud Reconstructioncited by 15
  38. 2020MAFF-Net: Filter False Positive for 3D Vehicle Detection with Multi-modal Adaptive Feature Fusioncited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 12.

21 papers.

Sort:

By area:

  1. 20253D and 4D World Modeling: A Surveycited by 67
  2. 2025Register Any Point: Scaling 3D Point Cloud Registration by Flow Matchingcited by 9
  3. 2026MoRe: Motion-aware Feed-forward 4D Reconstruction Transformercited by 9
  4. 2026AnchoredDream: Zero-Shot 360deg Indoor Scene Generation from a Single View via Geometric Groundingcited by 5
  5. 2025U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matchingcited by 3
  6. 2025LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architecturescited by 2
  7. 2025HeartFormer: Semantic-Aware Dual-Structure Transformers for 3D Four-Chamber Cardiac Point Cloud Reconstructioncited by 1
  8. 2025GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstructioncited by 1
  9. 2026Learning Latent Proxies for Controllable Single-Image Relightingcited by 1
  10. 2026MedPCFM: Improving Medical Point Cloud Completion by Integrating Point Transformers and Flow Matchingcited by 1
  11. 2025A Survey of Deep Learning-based Point Cloud Denoisingcited by 0
  12. 2025Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completioncited by 0
9 more
  1. 2025PUFM++: Point Cloud Upsampling via Enhanced Flow Matchingcited by 0
  2. 2026PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restorationcited by 0
  3. 2026PrintAnything: Learning an Intermediate Representation for 3D printing G-code Generationcited by 0
  4. 2026SUMI: Scalable Unified Model for 3D Point Cloud Inferencecited by 0
  5. 2026GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generationcited by 0
  6. 2026DARP: A Calibrated Dual-Arm RGB-D-IR Dataset for Multi-View Robotic Perceptioncited by 0
  7. 2026GSComplete: Gaussian Splat Completion with 2D Diffusion Priorscited by 0
  8. 2026UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasoundcited by 0
  9. 2026A Three-Dimensional Reverse-Projection Method for Sparse Point Cloud Completion and Its Application to High-Speed Train Nose Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Fast Point Cloud Generation with Straight Flows
  2. 2024ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors
  3. 2024PointInfinity: Resolution-Invariant Point Diffusion Models
  4. 2024Point Cloud Resampling with Learnable Heat Diffusion
  5. 2024Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models
  6. 2023GECCO: Geometrically-Conditioned Point Diffusion Models
  7. 2025DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud Completion
  8. 2024Fixed Point Diffusion Models