3D-MoE: A Mixture-of-Experts Multi-modal LLM for 3D Vision and Pose Diffusion via Rectified Flow

• URL: http://arxiv.org/abs/2501.16698v1
• Date: Tue, 28 Jan 2025 04:31:19 GMT
• Title: 3D-MoE: A Mixture-of-Experts Multi-modal LLM for 3D Vision and Pose Diffusion via Rectified Flow
• Authors: Yueen Ma, Yuzheng Zhuang, Jianye Hao, Irwin King,
• Abstract summary: 3D vision and spatial reasoning have long been recognized as preferable for accurately perceiving our three-dimensional world.<n>Due to the difficulties in collecting high-quality 3D data, research in this area has only recently gained momentum.<n>We propose converting existing densely activated LLMs into mixture-of-experts (MoE) models, which have proven effective for multi-modal data processing.
• Score: 69.94527569577295
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D vision and spatial reasoning have long been recognized as preferable for accurately perceiving our three-dimensional world, especially when compared with traditional visual reasoning based on 2D images. Due to the difficulties in collecting high-quality 3D data, research in this area has only recently gained momentum. With the advent of powerful large language models (LLMs), multi-modal LLMs for 3D vision have been developed over the past few years. However, most of these models focus primarily on the vision encoder for 3D data. In this paper, we propose converting existing densely activated LLMs into mixture-of-experts (MoE) models, which have proven effective for multi-modal data processing. In addition to leveraging these models' instruction-following capabilities, we further enable embodied task planning by attaching a diffusion head, Pose-DiT, that employs a novel rectified flow diffusion scheduler. Experimental results on 3D question answering and task-planning tasks demonstrate that our 3D-MoE framework achieves improved performance with fewer activated parameters.

Related papers

• Empowering Large Language Models with 3D Situation Awareness [84.12071023036636]
  A key difference between 3D and 2D is that the situation of an egocentric observer in 3D scenes can change, resulting in different descriptions. We propose a novel approach to automatically generate a situation-aware dataset by leveraging the scanning trajectory during data collection. We introduce a situation grounding module to explicitly predict the position and orientation of observer's viewpoint, thereby enabling LLMs to ground situation description in 3D scenes.
  arXiv  Detail & Related papers  (2025-03-29T09:34:16Z)
• DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation [51.43837087865105]
  Vision foundation models (VFMs) trained on large-scale image datasets provide high-quality features that have significantly advanced 2D visual recognition. Their potential in 3D vision remains largely untapped, despite the common availability of 2D images alongside 3D point cloud datasets. We introduce DITR, a simple yet effective approach that extracts 2D foundation model features, projects them to 3D, and finally injects them into a 3D point cloud segmentation model.
  arXiv  Detail & Related papers  (2025-03-24T17:59:11Z)
• Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding [19.382210260928776]
  Video-3D LLM treats 3D scenes as dynamic videos and incorporates 3D position encoding into these representations.<n>Our model achieves state-of-the-art performance on several 3D scene understanding benchmarks.
  arXiv  Detail & Related papers  (2024-11-30T14:28:53Z)
• Diffusion Models in 3D Vision: A Survey [11.116658321394755]
  We review the state-of-the-art approaches that leverage diffusion models for 3D visual tasks. These approaches include 3D object generation, shape completion, point cloud reconstruction, and scene understanding. We discuss potential solutions, including improving computational efficiency, enhancing multimodal fusion, and exploring the use of large-scale pretraining.
  arXiv  Detail & Related papers  (2024-10-07T04:12:23Z)
• LLMI3D: Empowering LLM with 3D Perception from a Single 2D Image [72.14973729674995]
  Current 3D perception methods, particularly small models, struggle with processing logical reasoning, question-answering, and handling open scenario categories. We propose solutions: Spatial-Enhanced Local Feature Mining for better spatial feature extraction, 3D Query Token-Derived Info Decoding for precise geometric regression, and Geometry Projection-Based 3D Reasoning for handling camera focal length variations.
  arXiv  Detail & Related papers  (2024-08-14T10:00:16Z)
• LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation [73.36690511083894]
  This paper introduces a novel framework called LN3Diff to address a unified 3D diffusion pipeline. Our approach harnesses a 3D-aware architecture and variational autoencoder to encode the input image into a structured, compact, and 3D latent space. It achieves state-of-the-art performance on ShapeNet for 3D generation and demonstrates superior performance in monocular 3D reconstruction and conditional 3D generation.
  arXiv  Detail & Related papers  (2024-03-18T17:54:34Z)
• M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts [30.571811801090224]
  We introduce a comprehensive 3D instructionfollowing dataset called M3DBench. It supports general multimodal instructions interleaved with text, images, 3D objects, and other visual prompts. It unifies diverse 3D tasks at both region and scene levels, covering a variety of fundamental abilities in real-world 3D environments.
  arXiv  Detail & Related papers  (2023-12-17T16:53:30Z)
• An Embodied Generalist Agent in 3D World [67.16935110789528]
  We introduce LEO, an embodied multi-modal generalist agent that excels in perceiving, grounding, reasoning, planning, and acting in the 3D world. We collect large-scale datasets comprising diverse object-level and scene-level tasks, which require considerable understanding of and interaction with the 3D world. Through extensive experiments, we demonstrate LEO's remarkable proficiency across a wide spectrum of tasks, including 3D captioning, question answering, embodied reasoning, navigation and manipulation.
  arXiv  Detail & Related papers  (2023-11-18T01:21:38Z)
• 3D-LLM: Injecting the 3D World into Large Language Models [60.43823088804661]
  Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. We propose to inject the 3D world into large language models and introduce a new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks.
  arXiv  Detail & Related papers  (2023-07-24T17:59:02Z)

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.