# 3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance

arXiv: https://arxiv.org/abs/2407.09826 · HTML: https://mlsanity.com/paper/2407.09826/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 46 of its 58 references that are in the map.
- First posted on arXiv 13 Jul 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 46)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/1906.00817/) (2019)
- [A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model](https://mlsanity.com/paper/2112.14757/) (2021)
- [CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP](https://mlsanity.com/paper/2301.04926/) (2023)
- [Tangent Convolutions for Dense Prediction in 3D](https://mlsanity.com/paper/1807.02443/) (2018)
- [PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation](https://mlsanity.com/paper/1711.10871/) (2017)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders](https://mlsanity.com/paper/2212.06785/) (2022)
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2203.11139/) (2022)
- [Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision](https://mlsanity.com/paper/2301.09121/) (2023)
- [Bidirectional Projection Network for Cross Dimension Scene Understanding](https://mlsanity.com/paper/2103.14326/) (2021)
- [CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition](https://mlsanity.com/paper/2303.11313/) (2023)
- [Multi-view PointNet for 3D Scene Understanding](https://mlsanity.com/paper/1909.13603/) (2019)
- [RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2301.10222/) (2023)
- [Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds](https://mlsanity.com/paper/2003.13035/) (2020)

## Built on by (most cited first, 12 of 12)

- [Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2503.16707/) (2025)
- [LESS: Label-Efficient and Single-Stage Referring 3D Segmentation](https://mlsanity.com/paper/2410.13294/) (2024)
- [OVI-MAP:Open-Vocabulary Instance-Semantic Mapping](https://mlsanity.com/paper/2603.26541/) (2026)
- [CDSeg: A Renderable Gaussian Carrier for Image-to-3D Label Transfer](https://mlsanity.com/paper/2608.05482/) (2026)
- [Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation](https://mlsanity.com/paper/2506.19022/) (2025)
- [High-quality Pseudo-labeling for Point Cloud Segmentation with Scene-level Annotation](https://mlsanity.com/paper/2506.23227/) (2025)
- [3D Weakly Supervised Semantic Segmentation via Class-Aware and Geometry-Guided Pseudo-Label Refinement](https://mlsanity.com/paper/2510.17875/) (2025)
- [Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling](https://mlsanity.com/paper/2508.06805/) (2025)
- [DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentation](https://mlsanity.com/paper/2508.06816/) (2025)
- [VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagation](https://mlsanity.com/paper/2508.06819/) (2025)
- [DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2511.10003/) (2025)
- [Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2603.06374/) (2026)

## Abstract (arXiv)

In this paper, we propose 3DSS-VLG, a weakly supervised approach for 3D Semantic Segmentation with 2D Vision-Language Guidance, an alternative approach that a 3D model predicts dense-embedding for each point which is co-embedded with both the aligned image and text spaces from the 2D vision-language model. Specifically, our method exploits the superior generalization ability of the 2D vision-language models and proposes the Embeddings Soft-Guidance Stage to utilize it to implicitly align 3D embeddings and text embeddings. Moreover, we introduce the Embeddings Specialization Stage to purify the feature representation with the help of a given scene-level label, specifying a better feature supervised by the corresponding text embedding. Thus, the 3D model is able to gain informative supervisions both from the image embedding and text embedding, leading to competitive segmentation performances. To the best of our knowledge, this is the first work to investigate 3D weakly supervised semantic segmentation by using the textual semantic information of text category labels. Moreover, with extensive quantitative and qualitative experiments, we present that our 3DSS-VLG is able not only to achieve the state-of-the-art performance on both S3DIS and ScanNet datasets, but also to maintain strong generalization capability.