Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale

• URL: http://arxiv.org/abs/2604.11331v1
• Date: Mon, 13 Apr 2026 11:32:36 GMT
• Title: Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
• Abstract summary: 3D scene generation has long been dominated by 2D multi-view or video diffusion models.<n>In this paper, we propose to perform 3D scene generation directly within an implicit 3D latent space.
• Score: 47.551405833477986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D scene generation has long been dominated by 2D multi-view or video diffusion models. This is due not only to the lack of scene-level 3D latent representation, but also to the fact that most scene-level 3D visual data exists in the form of multi-view images or videos, which are naturally compatible with 2D diffusion architectures. Typically, these 2D-based approaches degrade 3D spatial extrapolation to 2D temporal extension, which introduces two fundamental issues: (i) representing 3D scenes via 2D views leads to significant representation redundancy, and (ii) latent space rooted in 2D inherently limits the spatial consistency of the generated 3D scenes. In this paper, we propose, for the first time, to perform 3D scene generation directly within an implicit 3D latent space to address these limitations. First, we repurpose frozen 2D representation encoders to construct our 3D Representation Autoencoder (3DRAE), which grounds view-coupled 2D semantic representations into a view-decoupled 3D latent representation. This enables representing 3D scenes observed from arbitrary numbers of views--at any resolution and aspect ratio--with fixed complexity and rich semantics. Then we introduce 3D Diffusion Transformer (3DDiT), which performs diffusion modeling in this 3D latent space, achieving remarkably efficient and spatially consistent 3D scene generation while supporting diverse conditioning configurations. Moreover, since our approach directly generates a 3D scene representation, it can be decoded to images and optional point maps along arbitrary camera trajectories without requiring per-trajectory diffusion sampling pass, which is common in 2D-based approaches.

Related papers

• OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder [90.8453349494245]
  We present OneWorld, a framework that performs diffusion directly within a coherent 3D representation space.<n>OneWorld generates high-quality 3D scenes with superior cross-view consistency compared to state-of-the-art 2D-based methods.
  arXiv  Detail & Related papers  (2026-03-17T03:43:37Z)
• 3D Aware Region Prompted Vision Language Model [99.4106711584584]
  SR-3D connects single-view 2D images and multi-view 3D data through a shared visual token space.<n> SR-3D supports flexible region prompting, allowing users to annotate regions with bounding boxes, segmentation masks on any frame, or directly in 3D.
  arXiv  Detail & Related papers  (2025-09-16T17:59:06Z)
• Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs [72.11701578308804]
  This paper categorizes recent 3D Vision-Language Models into 3D object-centric, 2D image-based, and 3D scene-centric approaches.<n>Despite the architectural similarity of 3D scene-centric VLMs to their 2D counterparts, they have exhibited comparatively lower performance compared with the latest 3D object-centric and 2D image-based approaches.<n>Our investigation suggests that while these models possess cross-modal alignment capabilities, they tend to over-rely on linguistic cues and overfit to frequent answer distributions.
  arXiv  Detail & Related papers  (2025-06-05T17:56:12Z)
• Bolt3D: Generating 3D Scenes in Seconds [82.68347112021756]
  Given one or more images, our model Bolt3D directly samples a 3D scene representation in less than seven seconds on a single GPU.<n>Compared to prior multiview generative models that require per-scene optimization for 3D reconstruction, Bolt3D reduces the inference cost by a factor of up to 300 times.
  arXiv  Detail & Related papers  (2025-03-18T17:24:19Z)
• Latent Radiance Fields with 3D-aware 2D Representations [13.527653704258121]
  We propose a novel framework that integrates 3D awareness into the 2D latent space.<n>The framework consists of three stages: (1) a correspondence-aware autoencoding method that enhances the 3D consistency of 2D latent representations, (2) a latent radiance field (LRF) that lifts these 3D-aware 2D representations into 3D space, and (3) a VAE-Radiance Field (VAE-RF) alignment strategy that improves image decoding from the rendered 2D representations.
  arXiv  Detail & Related papers  (2025-02-13T18:59:09Z)
• ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images [47.682942867405224]
  ConDense is a framework for 3D pre-training utilizing existing 2D networks and large-scale multi-view datasets. We propose a novel 2D-3D joint training scheme to extract co-embedded 2D and 3D features in an end-to-end pipeline.
  arXiv  Detail & Related papers  (2024-08-30T05:57:01Z)
• BUOL: A Bottom-Up Framework with Occupancy-aware Lifting for Panoptic 3D Scene Reconstruction From A Single Image [33.126045619754365]
  BUOL is a framework with Occupancy-aware Lifting to address the two issues for panoptic 3D scene reconstruction from a single image. Our method shows a tremendous performance advantage over state-of-the-art methods on synthetic dataset 3D-Front and real-world dataset Matterport3D.
  arXiv  Detail & Related papers  (2023-06-01T17:56:49Z)
• RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation [68.06991943974195]
  We present RenderDiffusion, the first diffusion model for 3D generation and inference, trained using only monocular 2D supervision. We evaluate RenderDiffusion on FFHQ, AFHQ, ShapeNet and CLEVR datasets, showing competitive performance for generation of 3D scenes and inference of 3D scenes from 2D images.
  arXiv  Detail & Related papers  (2022-11-17T20:17:04Z)

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.