# TeDA: Boosting Vision-Lanuage Models for Zero-Shot 3D Object Retrieval via Testing-time Distribution Alignment

arXiv: https://arxiv.org/abs/2505.02325 · HTML: https://mlsanity.com/paper/2505.02325/

## Key facts

- Cited by 2 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 31 of its 57 references that are in the map.
- First posted on arXiv 5 May 2025.

## 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 31)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [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)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://mlsanity.com/paper/1904.07601/) (2019)
- [Uni3D: Exploring Unified 3D Representation at Scale](https://mlsanity.com/paper/2310.06773/) (2023)
- [ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding](https://mlsanity.com/paper/2305.08275/) (2023)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding](https://mlsanity.com/paper/2305.10764/) (2023)
- [Adaptive Risk Minimization: Learning to Adapt to Domain Shift](https://mlsanity.com/paper/2007.02931/) (2020)
- [Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning](https://mlsanity.com/paper/2308.06038/) (2023)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [Learning Placeholders for Open-Set Recognition](https://mlsanity.com/paper/2103.15086/) (2021)
- [MeshNet: Mesh Neural Network for 3D Shape Representation](https://mlsanity.com/paper/1811.11424/) (2018)
- [Triplet-Center Loss for Multi-View 3D Object Retrieval](https://mlsanity.com/paper/1803.06189/) (2018)
- [PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2112.04903/) (2021)
- [Equivariant Multi-View Networks](https://mlsanity.com/paper/1904.00993/) (2019)
- [Test-time Unsupervised Domain Adaptation](https://mlsanity.com/paper/2010.01926/) (2020)
- [PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition](https://mlsanity.com/paper/1808.07659/) (2018)
- [MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis](https://mlsanity.com/paper/2207.10228/) (2022)
- [Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP](https://mlsanity.com/paper/2310.19752/) (2023)
- [View N-gram Network for 3D Object Retrieval](https://mlsanity.com/paper/1908.01958/) (2019)

## Built on by (most cited first, 2 of 2)

- [Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval](https://mlsanity.com/paper/2507.21489/) (2025)
- [DINO Eats CLIP: Adapting Beyond Knowns for Open-set 3D Object Retrieval](https://mlsanity.com/paper/2604.19432/) (2026)

## Abstract (arXiv)

Learning discriminative 3D representations that generalize well to unknown testing categories is an emerging requirement for many real-world 3D applications. Existing well-established methods often struggle to attain this goal due to insufficient 3D training data from broader concepts. Meanwhile, pre-trained large vision-language models (e.g., CLIP) have shown remarkable zero-shot generalization capabilities. Yet, they are limited in extracting suitable 3D representations due to substantial gaps between their 2D training and 3D testing distributions. To address these challenges, we propose Testing-time Distribution Alignment (TeDA), a novel framework that adapts a pretrained 2D vision-language model CLIP for unknown 3D object retrieval at test time. To our knowledge, it is the first work that studies the test-time adaptation of a vision-language model for 3D feature learning. TeDA projects 3D objects into multi-view images, extracts features using CLIP, and refines 3D query embeddings with an iterative optimization strategy by confident query-target sample pairs in a self-boosting manner. Additionally, TeDA integrates textual descriptions generated by a multimodal language model (InternVL) to enhance 3D object understanding, leveraging CLIP's aligned feature space to fuse visual and textual cues. Extensive experiments on four open-set 3D object retrieval benchmarks demonstrate that TeDA greatly outperforms state-of-the-art methods, even those requiring extensive training. We also experimented with depth maps on Objaverse-LVIS, further validating its effectiveness. Code is available at https://github.com/wangzhichuan123/TeDA.