Dual-Branch Center-Surrounding Contrast: Rethinking Contrastive Learning for 3D Point Clouds

• URL: http://arxiv.org/abs/2512.08673v1
• Date: Tue, 09 Dec 2025 14:56:35 GMT
• Title: Dual-Branch Center-Surrounding Contrast: Rethinking Contrastive Learning for 3D Point Clouds
• Authors: Shaofeng Zhang, Xuanqi Chen, Xiangdong Zhang, Sitong Wu, Junchi Yan,
• Abstract summary: We propose a novel DualBranch textbfCentertextbfSurrounding textbfContrast (CSCon) framework for 3D point clouds.<n>Under the FULL and ALL protocols, CSCon achieves performance comparable to generative methods.<n>Our method attains state-of-the-art results, even surpassing cross-modal approaches.
• Score: 55.5576033344795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most existing self-supervised learning (SSL) approaches for 3D point clouds are dominated by generative methods based on Masked Autoencoders (MAE). However, these generative methods have been proven to struggle to capture high-level discriminative features effectively, leading to poor performance on linear probing and other downstream tasks. In contrast, contrastive methods excel in discriminative feature representation and generalization ability on image data. Despite this, contrastive learning (CL) in 3D data remains scarce. Besides, simply applying CL methods designed for 2D data to 3D fails to effectively learn 3D local details. To address these challenges, we propose a novel Dual-Branch \textbf{C}enter-\textbf{S}urrounding \textbf{Con}trast (CSCon) framework. Specifically, we apply masking to the center and surrounding parts separately, constructing dual-branch inputs with center-biased and surrounding-biased representations to better capture rich geometric information. Meanwhile, we introduce a patch-level contrastive loss to further enhance both high-level information and local sensitivity. Under the FULL and ALL protocols, CSCon achieves performance comparable to generative methods; under the MLP-LINEAR, MLP-3, and ONLY-NEW protocols, our method attains state-of-the-art results, even surpassing cross-modal approaches. In particular, under the MLP-LINEAR protocol, our method outperforms the baseline (Point-MAE) by \textbf{7.9\%}, \textbf{6.7\%}, and \textbf{10.3\%} on the three variants of ScanObjectNN, respectively. The code will be made publicly available.

Related papers

• UniC-Lift: Unified 3D Instance Segmentation via Contrastive Learning [6.502142457981839]
  3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have advanced novel-view synthesis.<n>Recent methods extend multi-view 2D segmentation to 3D, enabling instance/semantic segmentation for better scene understanding.<n>Key challenge is the inconsistency of 2D instance labels across views, leading to poor 3D predictions.<n>We propose a unified framework that merges these steps, reducing training time and improving performance by introducing a learnable feature embedding for segmentation in Gaussian primitives.
  arXiv  Detail & Related papers  (2025-12-31T10:20:01Z)
• PointDico: Contrastive 3D Representation Learning Guided by Diffusion Models [5.077352707415241]
  textitPointDico learns from both denoising generative modeling and cross-modal contrastive learning through knowledge distillation.<n>textitPointDico achieves a new state-of-the-art in 3D representation learning, textite.g., textbf94.32% accuracy on ScanObjectNN, textbf86.5% Inst. mIoU on ShapeNetPart.
  arXiv  Detail & Related papers  (2025-12-09T07:57:56Z)
• GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency [50.11520458252128]
  Existing 3D affordance learning methods struggle with generalization and robustness due to limited annotated data.<n>We propose GEAL, a novel framework designed to enhance the generalization and robustness of 3D affordance learning by leveraging large-scale pre-trained 2D models.<n>GEAL consistently outperforms existing methods across seen and novel object categories, as well as corrupted data.
  arXiv  Detail & Related papers  (2024-12-12T17:59:03Z)
• CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning [43.7594705101778]
  We propose a joint unsupervised differentiable-rendering-based pre-training method for images and point clouds, termed CLAP.<n>Our method overcomes the computational hurdle by Curvature Sampling to select the more informative points/pixels for pre-training.<n>Experiments show that CLAP achieves up to 100% more performance gain as compared to previous SOTA pre-training methods.
  arXiv  Detail & Related papers  (2024-12-04T06:26:12Z)
• Pic@Point: Cross-Modal Learning by Local and Global Point-Picture Correspondence [0.0]
  We present Pic@Point, an effective contrastive learning method based on structural 2D-3D correspondences. We leverage image cues rich in semantic and contextual knowledge to provide a guiding signal for point cloud representations.
  arXiv  Detail & Related papers  (2024-10-12T12:43:41Z)
• Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization [64.36097398869774]
  Semi-supervised learning (SSL) has been an active research topic for large-scale 3D scene understanding. The existing SSL-based methods suffer from severe training bias due to class imbalance and long-tail distributions of the point cloud data. We introduce a new decoupling optimization framework, which disentangles feature representation learning and classifier in an alternative optimization manner to shift the bias decision boundary effectively.
  arXiv  Detail & Related papers  (2024-01-13T04:16:40Z)
• Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders [52.66195794216989]
  We propose Point Feature Enhancement Masked Autoencoders (Point-FEMAE) to learn compact 3D representations. Point-FEMAE consists of a global branch and a local branch to capture latent semantic features. Our method significantly improves the pre-training efficiency compared to cross-modal alternatives.
  arXiv  Detail & Related papers  (2023-12-17T14:17:05Z)
• Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation [17.914290294935427]
  Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set. Large-scale visual-language pre-trained models, such as CLIP, have shown their generalization ability in the zero-shot 2D vision tasks. We propose a simple yet effective baseline to transfer the visual-linguistic knowledge implied in CLIP to point cloud encoder.
  arXiv  Detail & Related papers  (2023-12-12T12:35:59Z)
• 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation [92.17700318483745]
  We propose an image-guidance network (IGNet) which builds upon the idea of distilling high level feature information from a domain adapted synthetically trained 2D semantic segmentation network. IGNet achieves state-of-the-art results for weakly-supervised LiDAR semantic segmentation on ScribbleKITTI, boasting up to 98% relative performance to fully supervised training with only 8% labeled points.
  arXiv  Detail & Related papers  (2023-11-27T07:57:29Z)
• SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings [12.79344668998054]
  We propose SwIPE (Segmentation with Implicit Patch Embeddings) to enable accurate local boundary delineation and global shape coherence. We show that SwIPE significantly improves over recent implicit approaches and outperforms state-of-the-art discrete methods with over 10x fewer parameters.
  arXiv  Detail & Related papers  (2023-07-23T20:55:11Z)
• CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP [55.864132158596206]
  Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D zero-shot and few-shot learning. We make the first attempt to investigate how CLIP knowledge benefits 3D scene understanding. We propose CLIP2Scene, a framework that transfers CLIP knowledge from 2D image-text pre-trained models to a 3D point cloud network.
  arXiv  Detail & Related papers  (2023-01-12T10:42:39Z)
• GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds [72.60362979456035]
  Masked Autoencoders (MAE) are challenging to explore in large-scale 3D point clouds. We propose a textbfGenerative textbfDecoder for MAE (GD-MAE) to automatically merges the surrounding context. We demonstrate the efficacy of the proposed method on several large-scale benchmarks: KITTI, and ONCE.
  arXiv  Detail & Related papers  (2022-12-06T14:32:55Z)
• Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding [62.17020485045456]
  It is commonly assumed in semi-supervised learning (SSL) that the unlabeled data are drawn from the same distribution as that of the labeled ones. We propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized.
  arXiv  Detail & Related papers  (2022-05-02T16:09:17Z)

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.