3D-MRL: Nested Multimodal 3D Representations via Matryoshka Representation Learning

• URL: http://arxiv.org/abs/2608.29285v1
• Date: Sat, 29 Aug 2026 14:14:32 GMT
• Title: 3D-MRL: Nested Multimodal 3D Representations via Matryoshka Representation Learning
• Abstract summary: We propose 3D Matryoshka Representation Learning (3D-MRL), a multimodal 3D pre-training framework based on Matryoshka Representation Learning.<n>3D-MRL learns nested 3D representations by aligning point clouds with frozen CLIP image and text embeddings while applying contrastive supervision across multiple embedding dimensions.
• Score: 0.5249805590164902
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language Models align point clouds with image and text embeddings, enabling zero-shot recognition, retrieval, and open-vocabulary understanding of 3D shapes. Existing multimodal 3D pre-training methods produce fixed-dimensional embeddings, requiring separate models for different computational budgets. We propose 3D Matryoshka Representation Learning (3D-MRL), a multimodal 3D pre-training framework based on Matryoshka Representation Learning. 3D-MRL learns nested 3D representations by aligning point clouds with frozen CLIP image and text embeddings while applying contrastive supervision across multiple embedding dimensions. The Matryoshka objective is applied only to the 3D encoder, allowing a single model to produce representations at different dimensionalities without retraining. Experiments on the Objaverse-LVIS, ModelNet40, and ScanNet datasets show that 3D-MRL achieves competitive performance on zero-shot and few-shot 3D recognition tasks. In addition, the learned representations support retrieval across different embedding dimensions within a single model. On Objaverse-LVIS, 3D-MRL improves Top-1 accuracy from 46.8% to 50.9%. Retrieval experiments further show that different embedding dimensions yield varying levels of semantic and geometric specificity.

Related papers

• Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment [50.02189698630855]
  We propose a Proxy3D method with compact yet comprehensive 3D proxy representations for the vision modality.<n>Our method achieves competitive or state-of-the-art performance in 3D visual question answering, visual grounding and general spatial intelligence benchmarks.
  arXiv  Detail & Related papers  (2026-05-08T17:50:47Z)
• Abstract 3D Perception for Spatial Intelligence in Vision-Language Models [100.13033631690114]
  Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding.<n>We introduce SandboxVLM, a framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM.<n>Our approach consistently improves spatial intelligence, achieving an 8.3% gain on SAT Real compared with baseline methods.
  arXiv  Detail & Related papers  (2025-11-14T04:16:09Z)
• Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy [4.1703677379815565]
  We propose Vid-LLM, a video-based 3D-MLLM that directly processes video inputs without requiring external 3D data.<n>In our method, the geometric prior are directly used to improve the performance of the sceen perception.<n>Experiments across diverse benchmarks verified the effectiveness of our method on 3D Question Answering, 3D Captioning and 3D Visual Grounding tasks.
  arXiv  Detail & Related papers  (2025-09-29T07:34:18Z)
• TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP [52.79100775328595]
  3D visual grounding allows an embodied agent to understand visual information in real-world 3D environments based on human instructions.<n>Existing 3D visual grounding methods rely on separate encoders for different modalities.<n>We propose a unified 2D pre-trained multi-modal network to process all three modalities.
  arXiv  Detail & Related papers  (2025-07-20T10:28:06Z)
• Matrix3D: Large Photogrammetry Model All-in-One [31.034664725331073]
  Matrix3D is a unified model that performs several photogrammetry subtasks.<n>These include pose estimation, depth prediction, and view synthesis.<n>It offers fine-grained control through multi-round interactions.
  arXiv  Detail & Related papers  (2025-02-11T16:36:55Z)
• TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding [28.112402580426174]
  TriAdapter Multi-Modal Learning (TAMM) is a novel two-stage learning approach based on three synergistic adapters. TAMM consistently enhances 3D representations for a wide range of 3D encoder architectures, pre-training datasets, and downstream tasks.
  arXiv  Detail & Related papers  (2024-02-28T17:18:38Z)
• Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training [51.632418297156605]
  We introduce MixCon3D, a method aiming to sculpt holistic 3D representation in contrastive language-image-3D pre-training. We develop the 3D object-level representation from complementary perspectives, e.g., multi-view rendered images with the point cloud. Then, MixCon3D performs language-3D contrastive learning, comprehensively depicting real-world 3D objects and bolstering text alignment.
  arXiv  Detail & Related papers  (2023-11-03T06:05:36Z)
• Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation [72.94143731623117]
  Existing methods simply align 3D representations with single-view 2D images and coarse-grained parent category text. Insufficient synergy neglects the idea that a robust 3D representation should align with the joint vision-language space. We propose a multi-view joint modality modeling approach, termed JM3D, to obtain a unified representation for point cloud, text, and image.
  arXiv  Detail & Related papers  (2023-08-06T01:11:40Z)
• Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training [65.75399500494343]
  Masked Autoencoders (MAE) have shown promising performance in self-supervised learning for 2D and 3D computer vision. We propose Joint-MAE, a 2D-3D joint MAE framework for self-supervised 3D point cloud pre-training.
  arXiv  Detail & Related papers  (2023-02-27T17:56:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.