PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and Generation

• URL: http://arxiv.org/abs/2602.03533v1
• Date: Tue, 03 Feb 2026 13:49:23 GMT
• Title: PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and Generation
• Authors: Yongwei Chen, Tianyi Wei, Yushi Lan, Zhaoyang Lyu, Shangchen Zhou, Xudong Xu, Xingang Pan,
• Abstract summary: We present the first unified framework for 3D understanding and generation that combines autoregression with diffusion.<n>A lightweight transformer bridges the feature space of large language models and the conditional space of 3D diffusion models.<n>Our framework achieves state-of-the-art performance across diverse 3D understanding and generation benchmarks, while also excelling in 3D editing tasks.
• Score: 45.72473673810981
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid progress of large multimodal models has inspired efforts toward unified frameworks that couple understanding and generation. While such paradigms have shown remarkable success in 2D, extending them to 3D remains largely underexplored. Existing attempts to unify 3D tasks under a single autoregressive (AR) paradigm lead to significant performance degradation due to forced signal quantization and prohibitive training cost. Our key insight is that the essential challenge lies not in enforcing a unified autoregressive paradigm, but in enabling effective information interaction between generation and understanding while minimally compromising their inherent capabilities and leveraging pretrained models to reduce training cost. Guided by this perspective, we present the first unified framework for 3D understanding and generation that combines autoregression with diffusion. Specifically, we adopt an autoregressive next-token prediction paradigm for 3D understanding, and a continuous diffusion paradigm for 3D generation. A lightweight transformer bridges the feature space of large language models and the conditional space of 3D diffusion models, enabling effective cross-modal information exchange while preserving the priors learned by standalone models. Extensive experiments demonstrate that our framework achieves state-of-the-art performance across diverse 3D understanding and generation benchmarks, while also excelling in 3D editing tasks. These results highlight the potential of unified AR+diffusion models as a promising direction for building more general-purpose 3D intelligence.

Related papers

• LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework [40.17218893870908]
  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.
  arXiv  Detail & Related papers  (2025-05-30T06:08:45Z)
• MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation [44.94438766074643]
  We introduce MAR-3D, which integrates a pyramid variational autoencoder with a cascaded masked auto-regressive transformer.<n>Our architecture employs random masking during training and auto-regressive denoising in random order during inference, naturally accommodating the unordered property of 3D latent tokens.
  arXiv  Detail & Related papers  (2025-03-26T13:00:51Z)
• TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models [69.0220314849478]
  TripoSG is a new streamlined shape diffusion paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images.<n>The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images.<n>To foster progress and innovation in the field of 3D generation, we will make our model publicly available.
  arXiv  Detail & Related papers  (2025-02-10T16:07:54Z)
• DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation [33.62074896816882]
  DiffSplat is a novel 3D generative framework that generates 3D Gaussian splats by taming large-scale text-to-image diffusion models.<n>It differs from previous 3D generative models by effectively utilizing web-scale 2D priors while maintaining 3D consistency in a unified model.<n>In conjunction with the regular diffusion loss on these grids, a 3D rendering loss is introduced to facilitate 3D coherence across arbitrary views.
  arXiv  Detail & Related papers  (2025-01-28T07:38:59Z)
• Diffusion Models in 3D Vision: A Survey [18.805222552728225]
  3D vision has become a crucial field within computer vision, powering a range of applications such as autonomous driving, robotics, augmented reality, and medical imaging.<n>We review the state-of-the-art methods that use diffusion models for 3D visual tasks, including but not limited to 3D object generation, shape completion, point-cloud reconstruction, and scene construction.<n>We discuss potential solutions, including improving computational efficiency, enhancing multimodal fusion, and exploring the use of large-scale pretraining for better generalization across 3D tasks.
  arXiv  Detail & Related papers  (2024-10-07T04:12:23Z)
• 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)
• 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)
• CAD: Photorealistic 3D Generation via Adversarial Distillation [28.07049413820128]
  We propose a novel learning paradigm for 3D synthesis that utilizes pre-trained diffusion models. Our method unlocks the generation of high-fidelity and photorealistic 3D content conditioned on a single image and prompt.
  arXiv  Detail & Related papers  (2023-12-11T18:59:58Z)
• Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting [60.393072253444934]
  We propose a unified framework aimed at enhancing the diffusion priors for 3D generation tasks. We identify a divergence between the diffusion priors and the training procedures of diffusion models that substantially impairs the quality of 3D generation.
  arXiv  Detail & Related papers  (2023-12-08T03:55:34Z)
• Spice-E : Structural Priors in 3D Diffusion using Cross-Entity Attention [9.52027244702166]
  Spice-E is a neural network that adds structural guidance to 3D diffusion models. We show that our approach supports a variety of applications, including 3D stylization, semantic shape editing and text-conditional abstraction-to-3D.
  arXiv  Detail & Related papers  (2023-11-29T17:36:49Z)
• IT3D: Improved Text-to-3D Generation with Explicit View Synthesis [71.68595192524843]
  This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues. Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images. For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data.
  arXiv  Detail & Related papers  (2023-08-22T14:39:17Z)

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.