# Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features

arXiv: https://arxiv.org/abs/2311.18113 · HTML: https://mlsanity.com/paper/2311.18113/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 51 references that are in the map.
- First posted on arXiv 29 Nov 2023.

## Builds on (most cited first, 30 of 37)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [Text2Mesh: Text-Driven Neural Stylization for Meshes](https://mlsanity.com/paper/2112.03221/) (2021)
- [ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding](https://mlsanity.com/paper/2212.05171/) (2022)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://mlsanity.com/paper/2003.03164/) (2020)
- [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://mlsanity.com/paper/2212.01558/) (2022)
- [TextDeformer: Geometry Manipulation using Text Guidance](https://mlsanity.com/paper/2304.13348/) (2023)
- [CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition](https://mlsanity.com/paper/2303.11313/) (2023)
- [USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds](https://mlsanity.com/paper/1904.00229/) (2019)
- [CLIP2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data](https://mlsanity.com/paper/2303.12417/) (2023)
- [SATR: Zero-Shot Semantic Segmentation of 3D Shapes](https://mlsanity.com/paper/2304.04909/) (2023)
- [KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations](https://mlsanity.com/paper/2002.12687/) (2020)
- [KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control](https://mlsanity.com/paper/2104.11224/) (2021)
- [ManifoldPlus: A Robust and Scalable Watertight Manifold Surface Generation Method for Triangle Soups](https://mlsanity.com/paper/2005.11621/) (2020)
- [Zero-Shot 3D Shape Correspondence](https://mlsanity.com/paper/2306.03253/) (2023)
- [3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions](https://mlsanity.com/paper/2212.11263/) (2022)

## Built on by (most cited first, 17 of 17)

- [Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels](https://mlsanity.com/paper/2506.05312/) (2025)
- [SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation](https://mlsanity.com/paper/2409.11682/) (2024)
- [Beyond Complete Shapes: A Benchmark for Quantitative Evaluation of 3D Shape Surface Matching Algorithms](https://mlsanity.com/paper/2411.03511/) (2024)
- [DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Features](https://mlsanity.com/paper/2408.08568/) (2024)
- [Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence](https://mlsanity.com/paper/2506.08220/) (2025)
- [PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding](https://mlsanity.com/paper/2601.02457/) (2026)
- [Surface-Aware Distilled 3D Semantic Features](https://mlsanity.com/paper/2503.18254/) (2025)
- [RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning](https://mlsanity.com/paper/2507.19950/) (2025)
- [A dataset-free approach for self-supervised learning of 3D reflectional symmetries](https://mlsanity.com/paper/2503.02660/) (2025)
- [WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction](https://mlsanity.com/paper/2505.04813/) (2025)
- [Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors](https://mlsanity.com/paper/2509.21263/) (2025)
- [Channel-adaptive Cross-modal Generative Semantic Communication for Point Cloud Transmission](https://mlsanity.com/paper/2506.03211/) (2025)
- [Deep Feature Deformation Weights](https://mlsanity.com/paper/2601.12527/) (2026)
- [GLASS: Graph and Vision-Language Assisted Semantic Shape Correspondence](https://mlsanity.com/paper/2603.07652/) (2026)
- [Training-free zero-shot 3D symmetry detection with visual features back-projected to geometry](https://mlsanity.com/paper/2505.24162/) (2025)
- [Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection](https://mlsanity.com/paper/2507.07994/) (2025)
- [PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views](https://mlsanity.com/paper/2604.22658/) (2026)

## Abstract (arXiv)

With the immense growth of dataset sizes and computing resources in recent years, so-called foundation models have become popular in NLP and vision tasks. In this work, we propose to explore foundation models for the task of keypoint detection on 3D shapes. A unique characteristic of keypoint detection is that it requires semantic and geometric awareness while demanding high localization accuracy. To address this problem, we propose, first, to back-project features from large pre-trained 2D vision models onto 3D shapes and employ them for this task. We show that we obtain robust 3D features that contain rich semantic information and analyze multiple candidate features stemming from different 2D foundation models. Second, we employ a keypoint candidate optimization module which aims to match the average observed distribution of keypoints on the shape and is guided by the back-projected features. The resulting approach achieves a new state of the art for few-shot keypoint detection on the KeyPointNet dataset, almost doubling the performance of the previous best methods.