mlsanityData to 7 Oct 2026

Positional Prompt Tuning for Efficient 3D Representation Learning

arXiv 2408.11567 ↗First posted 21 Aug 2024cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

We rethink the role of positional encoding in 3D representation learning and fine-tuning. We argue that using positional encoding in point Transformer-based methods serves to aggregate multi-scale features of point clouds. Additionally, we explore parameter-efficient fine-tuning (PEFT) through the lens of prompts and adapters, introducing a straightforward yet effective method called PPT for point cloud analysis. PPT incorporates increased patch tokens and trainable positional encoding while keeping most pre-trained model parameters frozen. Extensive experiments validate that PPT is both effective and efficient. Our proposed method of PEFT tasks, namely PPT, with only 1.05M of parameters for training, gets state-of-the-art results in several mainstream datasets, such as 95.01% accuracy in the ScanObjectNN OBJ_BG dataset. Codes and weights will be released at https://github.com/zsc000722/PPT.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 56 of its 89 references that are in the map. First posted on arXiv 21 Aug 2024.

Builds on

56 of 89 references.

References · 56

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  8. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  9. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  10. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  12. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
38 more
  1. 2020Point Transformercited by 1,462
  2. 2020PCT: Point cloud transformercited by 730
  3. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  4. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  5. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  6. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  9. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  10. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  11. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  12. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  13. 2023DreamLLM: Synergistic Multimodal Comprehension and Creationcited by 296
  14. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  15. 2021Voxel Transformer for 3D Object Detectioncited by 247
  16. 2021Group-Free 3D Object Detection via Transformerscited by 215
  17. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 206
  18. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  19. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 183
  20. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 162
  21. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 143
  22. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  23. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  24. 2024DreamBench++: A Human-Aligned Benchmark for Personalized Image Generationcited by 131
  25. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 121
  26. 2023CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIPcited by 89
  27. 2016SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentationcited by 70
  28. 2023Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Modelscited by 67
  29. 2023Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Modelscited by 42
  30. 2023Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoderscited by 42
  31. 2022PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detectioncited by 33
  32. 2024SUGAR: Pre-training 3D Visual Representations for Roboticscited by 26
  33. 2024PCP-MAE: Learning to Predict Centers for Point Masked Autoencoderscited by 23
  34. 2024PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learningcited by 21
  35. 2024ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretrainingcited by 21
  36. 2024Parameter-efficient Prompt Learning for 3D Point Cloud Understandingcited by 16
  37. 2023Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrastcited by 14
  38. 2024Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Visioncited by 13

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 6.

15 papers.

Sort:

By area:

  1. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  2. 2025OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Modelscited by 105
  3. 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulationcited by 46
  4. 2025Prompt-based Adaptation in Large-scale Vision Models: A Surveycited by 21
  5. 2025PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learningcited by 13
  6. 2025MoST: Efficient Monarch Sparse Tuning for 3D Representation Learningcited by 6
  7. 2025On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentationcited by 4
  8. 2025Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformerscited by 2
  9. 2025MS-DGCNN++: Multi-Scale Dynamic Graph Convolution with Scale-Dependent Normalization for Robust LiDAR Tree Species Classificationcited by 1
  10. 2026An Adapter-free Fine-tuning Approach for Tuning 3D Foundation Modelscited by 1
  11. 2026VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detectioncited by 0
  12. 2026Point Ladder Tuning: Parameter-Efficient Hierarchical Adaptation for 3D Point Cloud Understandingcited by 0
3 more
  1. 2026UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interactioncited by 0
  2. 2026Position Anchor Tuning: Towards Efficient Adaptation of Pre-Trained Point Cloud Transformerscited by 0
  3. 2026GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Modelcited by 0