| --- |
| pipeline_tag: graph-ml |
| library_name: pytorch |
| license: cc-by-nc-4.0 |
| tags: |
| - 3d |
| - point-cloud |
| - self-supervised-learning |
| --- |
| |
| # Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations |
|
|
| This repository contains the model weights for **Concerto**, a novel approach for learning robust spatial representations presented in the paper [Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations](https://huggingface.co/papers/2510.23607). |
|
|
| - **Paper:** [Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations](https://huggingface.co/papers/2510.23607) |
| - **Project Page:** [https://pointcept.github.io/Concerto/](https://pointcept.github.io/Concerto) |
| - **Codebase:** [https://github.com/Pointcept/Pointcept](https://github.com/Pointcept/Pointcept) |
| - **Inference:** [https://github.com/Pointcept/Concerto](https://github.com/Pointcept/Concerto) |
|
|
| ## Models |
| The default models(concerto_large/base/small/tiny) are the pre-release version of our next work, which can deal with input without color and normal. If colors and normals are not available, please set them to zeros. We pre-release these for general public use because many tasks lack such information. The original Concerto model is `concerto_base_origin.pth`. |
| | Model Size | Channels | Depths | Head nums | |
| | --- | --- | --- | --- | |
| | Tiny | (16, 32, 64, 128, 256) | (1, 1, 1, 3, 1) | (1, 2, 4, 8, 16) | |
| | Small | (32, 64, 128, 256, 512) | (2, 2, 2, 6, 2) | (2, 4, 8, 16, 32) | |
| | Base | (48, 96, 192, 384, 512) | (3, 3, 3, 12, 3) | (3, 6, 12, 24, 32) | |
| | Large | (64, 128, 256, 512, 768) | (3, 3, 3, 12, 3) | (4, 8, 16, 32, 48) | |
| |
| |
| ## Abstract |
| Humans learn abstract concepts through multisensory synergy, and once formed, such representations can often be recalled from a single modality. Inspired by this principle, we introduce Concerto, a minimalist simulation of human concept learning for spatial cognition, combining 3D intra-modal self-distillation with 2D-3D cross-modal joint embedding. Despite its simplicity, Concerto learns more coherent and informative spatial features, as demonstrated by zero-shot visualizations. It outperforms both standalone SOTA 2D and 3D self-supervised models by 14.2% and 4.8%, respectively, as well as their feature concatenation, in linear probing for 3D scene perception. With full fine-tuning, Concerto sets new SOTA results across multiple scene understanding benchmarks (e.g., 80.7% mIoU on ScanNet). We further present a variant of Concerto tailored for video-lifted point cloud spatial understanding, and a translator that linearly projects Concerto representations into CLIP's language space, enabling open-world perception. These results highlight that Concerto emerges spatial representations with superior fine-grained geometric and semantic consistency. |
| |
| ## Usage |
| For detailed installation, data preparation, training, and testing instructions, please refer to the [official codebase](https://github.com/Pointcept/Pointcept) and [inference demo](https://github.com/Pointcept/Concerto). |
| |
| ## Citation |
| If you find Concerto or the Pointcept codebase useful in your research, please cite the following papers: |
| |
| ```bibtex |
| @misc{pointcept2023, |
| title={Pointcept: A Codebase for Point Cloud Perception Research}, |
| author={Pointcept Contributors}, |
| howpublished = {\url{https://github.com/Pointcept/Pointcept}}, |
| year={2023} |
| } |
| |
| @article{zhang2025concerto, |
| title={Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations}, |
| author={Zhang, Yujia and Wu, Xiaoyang and Lao, Yixing and Wang, Chengyao and Tian, Zhuotao and Wang, Naiyan and Zhao, Hengshuang}, |
| journal={Conference on Neural Information Processing Systems}, |
| year={2025}, |
| } |
| ``` |
