SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE

• URL: http://arxiv.org/abs/2411.16856v2
• Date: Wed, 27 Nov 2024 10:33:32 GMT
• Title: SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE
• Authors: Yongwei Chen, Yushi Lan, Shangchen Zhou, Tengfei Wang, Xingang Pan,
• Abstract summary: This paper introduces Scale AutoRegressive 3D (SAR3D), a novel framework that leverages a multi-scale 3D vector-quantized variational autoencoder (VQVAE) to tokenize 3D objects. By predicting the next scale in a multi-scale latent representation instead of the next single token, SAR3D reduces generation time significantly. Our experiments show that SAR3D surpasses current 3D generation methods in both speed and quality.
• Score: 28.597376637565123
• License:
• Abstract: Autoregressive models have demonstrated remarkable success across various fields, from large language models (LLMs) to large multimodal models (LMMs) and 2D content generation, moving closer to artificial general intelligence (AGI). Despite these advances, applying autoregressive approaches to 3D object generation and understanding remains largely unexplored. This paper introduces Scale AutoRegressive 3D (SAR3D), a novel framework that leverages a multi-scale 3D vector-quantized variational autoencoder (VQVAE) to tokenize 3D objects for efficient autoregressive generation and detailed understanding. By predicting the next scale in a multi-scale latent representation instead of the next single token, SAR3D reduces generation time significantly, achieving fast 3D object generation in just 0.82 seconds on an A6000 GPU. Additionally, given the tokens enriched with hierarchical 3D-aware information, we finetune a pretrained LLM on them, enabling multimodal comprehension of 3D content. Our experiments show that SAR3D surpasses current 3D generation methods in both speed and quality and allows LLMs to interpret and caption 3D models comprehensively.

Related papers

• 3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding [49.15555885075644]
  We develop pipeline based on open-source 2D MLLMs and LLMs to generate high-quality 3D-text pairs. We introduce the 3UR-LLM model, an end-to-end 3D MLLM designed for precise interpretation of 3D scenes.
  arXiv  Detail & Related papers  (2025-01-14T03:50:23Z)
• You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale [42.67300636733286]
  We present See3D, a visual-conditional multi-view diffusion model trained on large-scale Internet videos for open-world 3D creation. The model aims to Get 3D knowledge by solely Seeing the visual contents from the vast and rapidly growing video data. Our numerical and visual comparisons on single and sparse reconstruction benchmarks show that See3D, trained on cost-effective and scalable video data, achieves notable zero-shot and open-world generation capabilities.
  arXiv  Detail & Related papers  (2024-12-09T17:44:56Z)
• DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data [50.164670363633704]
  We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets from text prompts. Our model is directly trained on extensive noisy and unaligned in-the-wild' 3D assets. We achieve state-of-the-art performance in both single-class generation and text-to-3D generation.
  arXiv  Detail & Related papers  (2024-06-06T17:58:15Z)
• DiffTF++: 3D-aware Diffusion Transformer for Large-Vocabulary 3D Generation [53.20147419879056]
  We introduce a diffusion-based feed-forward framework to address challenges with a single model. Building upon our 3D-aware Diffusion model with TransFormer, we propose a stronger version for 3D generation, i.e., DiffTF++. Experiments on ShapeNet and OmniObject3D convincingly demonstrate the effectiveness of our proposed modules.
  arXiv  Detail & Related papers  (2024-05-13T17:59:51Z)
• Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs [13.360196679265226]
  We argue that current 3D AIGC methods do not fully unleash human creativity. In this paper, we explore a novel 3D AIGC approach: generating 3D content from IDEAs. We propose the new framework Idea23D, which combines three agents based on large multimodal models (LMMs) and existing algorithmic tools.
  arXiv  Detail & Related papers  (2024-04-05T19:16:30Z)
• 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)
• Large-Vocabulary 3D Diffusion Model with Transformer [57.076986347047]
  We introduce a diffusion-based feed-forward framework for synthesizing massive categories of real-world 3D objects with a single generative model. We propose a novel triplane-based 3D-aware Diffusion model with TransFormer, DiffTF, for handling challenges via three aspects. Experiments on ShapeNet and OmniObject3D convincingly demonstrate that a single DiffTF model achieves state-of-the-art large-vocabulary 3D object generation performance.
  arXiv  Detail & Related papers  (2023-09-14T17:59:53Z)
• 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.