LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework

• URL: http://arxiv.org/abs/2505.24245v1
• Date: Fri, 30 May 2025 06:08:45 GMT
• Title: LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework
• Authors: Xin Kang, Zihan Zheng, Lei Chu, Yue Gao, Jiahao Li, Hao Pan, Xuejin Chen, Yan Lu,
• Abstract summary: LTM3D is a Latent Token space Modeling framework for conditional 3D shape generation.<n>It integrates the strengths of diffusion and auto-regressive (AR) models.<n>LTM3D offers a generalizable framework for multi-modal, multi-representation 3D generation.
• Score: 40.17218893870908
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present LTM3D, a Latent Token space Modeling framework for conditional 3D shape generation that integrates the strengths of diffusion and auto-regressive (AR) models. While diffusion-based methods effectively model continuous latent spaces and AR models excel at capturing inter-token dependencies, combining these paradigms for 3D shape generation remains a challenge. To address this, LTM3D features a Conditional Distribution Modeling backbone, leveraging a masked autoencoder and a diffusion model to enhance token dependency learning. Additionally, we introduce Prefix Learning, which aligns condition tokens with shape latent tokens during generation, improving flexibility across modalities. We further propose a Latent Token Reconstruction module with Reconstruction-Guided Sampling to reduce uncertainty and enhance structural fidelity in generated shapes. Our approach operates in token space, enabling support for multiple 3D representations, including signed distance fields, point clouds, meshes, and 3D Gaussian Splatting. Extensive experiments on image- and text-conditioned shape generation tasks demonstrate that LTM3D outperforms existing methods in prompt fidelity and structural accuracy while offering a generalizable framework for multi-modal, multi-representation 3D generation.

Related papers

• Taming Feed-forward Reconstruction Models as Latent Encoders for 3D Generative Models [7.485139478358133]
  Recent AI-based 3D content creation has largely evolved along two paths: feed-forward image-to-3D reconstruction approaches and 3D generative models trained with 2D or 3D supervision.<n>We show that existing feed-forward reconstruction methods can serve as effective latent encoders for training 3D generative models, thereby bridging these two paradigms.
  arXiv  Detail & Related papers  (2024-12-31T21:23:08Z)
• GaussianAnything: Interactive Point Cloud Flow Matching For 3D Object Generation [75.39457097832113]
  This paper introduces a novel 3D generation framework, offering scalable, high-quality 3D generation with an interactive Point Cloud-structured Latent space.<n>Our framework employs a Variational Autoencoder with multi-view posed RGB-D(epth)-N(ormal) renderings as input, using a unique latent space design that preserves 3D shape information.<n>The proposed method, GaussianAnything, supports multi-modal conditional 3D generation, allowing for point cloud, caption, and single image inputs.
  arXiv  Detail & Related papers  (2024-11-12T18:59:32Z)
• Masked Generative Extractor for Synergistic Representation and 3D Generation of Point Clouds [6.69660410213287]
  We propose an innovative framework called Point-MGE to explore the benefits of deeply integrating 3D representation learning and generative learning. In shape classification, Point-MGE achieved an accuracy of 94.2% (+1.0%) on the ModelNet40 dataset and 92.9% (+5.5%) on the ScanObjectNN dataset. Experimental results also confirmed that Point-MGE can generate high-quality 3D shapes in both unconditional and conditional settings.
  arXiv  Detail & Related papers  (2024-06-25T07:57:03Z)
• NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation [52.772319840580074]
  3D shape generation aims to produce innovative 3D content adhering to specific conditions and constraints. Existing methods often decompose 3D shapes into a sequence of localized components, treating each element in isolation. We introduce a novel spatial-aware 3D shape generation framework that leverages 2D plane representations for enhanced 3D shape modeling.
  arXiv  Detail & Related papers  (2024-03-27T04:09:34Z)
• Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability [118.26563926533517]
  Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. We extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
  arXiv  Detail & Related papers  (2024-02-19T15:33:09Z)
• Learning Versatile 3D Shape Generation with Improved AR Models [91.87115744375052]
  Auto-regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space. We propose the Improved Auto-regressive Model (ImAM) for 3D shape generation, which applies discrete representation learning based on a latent vector instead of volumetric grids.
  arXiv  Detail & Related papers  (2023-03-26T12:03:18Z)
• 3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process [32.3773514247982]
  We develop a generalized 3D shape generation prior model tailored for multiple 3D tasks. Designs jointly equip our proposed 3D shape prior model with high-fidelity, diverse features as well as the capability of cross-modality alignment.
  arXiv  Detail & Related papers  (2023-03-18T12:50:29Z)
• Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generation [66.21121745446345]
  We propose a conditional GNeRF model that integrates specific attribute labels as input, thus amplifying the controllability and disentanglement capabilities of 3D-aware generative models. Our approach builds upon a pre-trained 3D-aware face model, and we introduce a Training as Init and fidelity for Tuning (TRIOT) method to train a conditional normalized flow module. Our experiments substantiate the efficacy of our model, showcasing its ability to generate high-quality edits with enhanced view consistency.
  arXiv  Detail & Related papers  (2022-08-26T10:05:39Z)

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.