TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/3D Point Cloud Reconstruction/ScanObjectNN

3D Point Cloud Reconstruction on ScanObjectNN

Metric: OBJ-ONLY (OA) (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕OBJ-ONLY (OA)▼Extra DataPaperDate↕Code
1PointGST97.76YesParameter-Efficient Fine-Tuning in Spectral Doma...2024-10-10Code
2ReCon++97.59YesShapeLLM: Universal 3D Object Understanding for ...2024-02-27Code
3PointGPT96.6YesPointGPT: Auto-regressively Generative Pre-train...2023-05-19Code
43D-JEPA94.49Yes3D-JEPA: A Joint Embedding Predictive Architectu...2024-09-24-
5AsymDSD-B* (no voting)94.32YesAsymmetric Dual Self-Distillation for 3D Self-Su...2025-06-26Code
6PCP-MAE94.32NoPCP-MAE: Learning to Predict Centers for Point M...2024-08-16Code
7ReCon93.8YesContrast with Reconstruct: Contrastive 3D Repres...2023-02-05Code
8Point-RAE (no voting)93.63YesRegress Before Construct: Regress Autoencoder fo...2023-09-25Code
9ReCon (no voting)93.29YesContrast with Reconstruct: Contrastive 3D Repres...2023-02-05Code
10Point-FEMAE93.29YesTowards Compact 3D Representations via Point Fea...2023-12-17Code
11ReCon+PPT93.28NoPositional Prompt Tuning for Efficient 3D Repres...2024-08-21Code
12Mamba3D92.43NoMamba3D: Enhancing Local Features for 3D Point C...2024-04-23Code
13OTMae3D92.3Yes--Code
14MVTN92.3NoMVTN: Multi-View Transformation Network for 3D S...2020-11-26Code
15Mamba3D (no voting)92.08NoMamba3D: Enhancing Local Features for 3D Point C...2024-04-23Code
16AsymDSD-S (no voting)91.91YesAsymmetric Dual Self-Distillation for 3D Self-Su...2025-06-26Code
17ACT (no voting)91.91YesAutoencoders as Cross-Modal Teachers: Can Pretra...2022-12-16Code
18I2P-MAE (no voting)91.57YesLearning 3D Representations from 2D Pre-trained ...2022-12-13Code
19point2vec90.4YesPoint2Vec for Self-Supervised Representation Lea...2023-03-29Code
20ExpPoint-MAE90.02YesExpPoint-MAE: Better interpretability and perfor...2023-06-19Code
21Point-LGMask89.3Yes--Code
22Point-M2AE88.81YesPoint-M2AE: Multi-scale Masked Autoencoders for ...2022-05-28Code
23Point-MAE88.29YesMasked Autoencoders for Point Cloud Self-supervi...2022-03-13Code
24Point-BERT88.12YesPoint-BERT: Pre-training 3D Point Cloud Transfor...2021-11-29Code
25DGCNN86.2NoDynamic Graph CNN for Learning on Point Clouds2018-01-24Code
26PointCNN85.5NoPointCNN: Convolution On $\mathcal{X}$-Transform...2018-01-23Code
27PointNet++84.3NoPointNet++: Deep Hierarchical Feature Learning o...2017-06-07Code