# Towards Label-free Scene Understanding by Vision Foundation Models

arXiv: https://arxiv.org/abs/2306.03899 · HTML: https://mlsanity.com/paper/2306.03899/

## Key facts

- Cited by 54 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 69 of its 94 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## 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 69)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)

## Built on by (most cited first, 30 of 54)

- [UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase](https://mlsanity.com/paper/2309.05573/) (2023)
- [IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection](https://mlsanity.com/paper/2403.15241/) (2024)
- [Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2405.05258/) (2024)
- [FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation](https://mlsanity.com/paper/2312.04484/) (2023)
- [Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving](https://mlsanity.com/paper/2405.17426/) (2024)
- [OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2405.05259/) (2024)
- [On the Foundations of Earth and Climate Foundation Models](https://mlsanity.com/paper/2405.04285/) (2024)
- [4D Contrastive Superflows are Dense 3D Representation Learners](https://mlsanity.com/paper/2407.06190/) (2024)
- [Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future](https://mlsanity.com/paper/2512.16760/) (2025)
- [Is Your LiDAR Placement Optimized for 3D Scene Understanding?](https://mlsanity.com/paper/2403.17009/) (2024)
- [Multi-Space Alignments Towards Universal LiDAR Segmentation](https://mlsanity.com/paper/2405.01538/) (2024)
- [Embodied AI: From LLMs to World Models](https://mlsanity.com/paper/2509.20021/) (2025)
- [See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data](https://mlsanity.com/paper/2307.10782/) (2023)
- [Learning to Adapt SAM for Segmenting Cross-domain Point Clouds](https://mlsanity.com/paper/2310.08820/) (2023)
- [Perspective-Invariant 3D Object Detection](https://mlsanity.com/paper/2507.17665/) (2025)
- [Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation](https://mlsanity.com/paper/2407.13362/) (2024)
- [ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Images](https://mlsanity.com/paper/2410.24001/) (2024)
- [MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation](https://mlsanity.com/paper/2503.18135/) (2025)
- [Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D](https://mlsanity.com/paper/2403.18922/) (2024)
- [The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation](https://mlsanity.com/paper/2307.15061/) (2023)
- [Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2503.16707/) (2025)
- [An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models](https://mlsanity.com/paper/2405.14870/) (2024)
- [3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance](https://mlsanity.com/paper/2407.09826/) (2024)
- [Part2Object: Hierarchical Unsupervised 3D Instance Segmentation](https://mlsanity.com/paper/2407.10084/) (2024)
- [Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding](https://mlsanity.com/paper/2403.17010/) (2024)
- [SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes](https://mlsanity.com/paper/2507.07781/) (2025)
- [MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2401.16305/) (2024)
- [Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors](https://mlsanity.com/paper/2505.24103/) (2025)
- [Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations](https://mlsanity.com/paper/2507.05260/) (2025)
- [U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences](https://mlsanity.com/paper/2512.02982/) (2025)

## Abstract (arXiv)

Vision foundation models such as Contrastive Vision-Language Pre-training (CLIP) and Segment Anything (SAM) have demonstrated impressive zero-shot performance on image classification and segmentation tasks. However, the incorporation of CLIP and SAM for label-free scene understanding has yet to be explored. In this paper, we investigate the potential of vision foundation models in enabling networks to comprehend 2D and 3D worlds without labelled data. The primary challenge lies in effectively supervising networks under extremely noisy pseudo labels, which are generated by CLIP and further exacerbated during the propagation from the 2D to the 3D domain. To tackle these challenges, we propose a novel Cross-modality Noisy Supervision (CNS) method that leverages the strengths of CLIP and SAM to supervise 2D and 3D networks simultaneously. In particular, we introduce a prediction consistency regularization to co-train 2D and 3D networks, then further impose the networks' latent space consistency using the SAM's robust feature representation. Experiments conducted on diverse indoor and outdoor datasets demonstrate the superior performance of our method in understanding 2D and 3D open environments. Our 2D and 3D network achieves label-free semantic segmentation with 28.4% and 33.5% mIoU on ScanNet, improving 4.7% and 7.9%, respectively. For nuImages and nuScenes datasets, the performance is 22.1% and 26.8% with improvements of 3.5% and 6.0%, respectively. Code is available. (https://github.com/runnanchen/Label-Free-Scene-Understanding).