Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration

• URL: http://arxiv.org/abs/2504.00387v2
• Date: Mon, 21 Apr 2025 02:40:21 GMT
• Title: Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration
• Authors: Zilong Huang, Jun He, Junyan Ye, Lihan Jiang, Weijia Li, Yiping Chen, Ting Han,
• Abstract summary: We propose a novel layered 3D scene reconstruction framework from panoramic image, named Scene4U.<n>Specifically, Scene4U integrates an open-vocabulary segmentation model with a large language model to decompose a real panorama into multiple layers.<n>We then employ a layered repair module based on diffusion model to restore occluded regions using visual cues and depth information, generating a hierarchical representation of the scene.<n>Scene4U outperforms state-of-the-art method, improving by 24.24% in LPIPS and 24.40% in BRISQUE, while also achieving the fastest training speed.
• Score: 18.23983135970619
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The reconstruction of immersive and realistic 3D scenes holds significant practical importance in various fields of computer vision and computer graphics. Typically, immersive and realistic scenes should be free from obstructions by dynamic objects, maintain global texture consistency, and allow for unrestricted exploration. The current mainstream methods for image-driven scene construction involves iteratively refining the initial image using a moving virtual camera to generate the scene. However, previous methods struggle with visual discontinuities due to global texture inconsistencies under varying camera poses, and they frequently exhibit scene voids caused by foreground-background occlusions. To this end, we propose a novel layered 3D scene reconstruction framework from panoramic image, named Scene4U. Specifically, Scene4U integrates an open-vocabulary segmentation model with a large language model to decompose a real panorama into multiple layers. Then, we employs a layered repair module based on diffusion model to restore occluded regions using visual cues and depth information, generating a hierarchical representation of the scene. The multi-layer panorama is then initialized as a 3D Gaussian Splatting representation, followed by layered optimization, which ultimately produces an immersive 3D scene with semantic and structural consistency that supports free exploration. Scene4U outperforms state-of-the-art method, improving by 24.24% in LPIPS and 24.40% in BRISQUE, while also achieving the fastest training speed. Additionally, to demonstrate the robustness of Scene4U and allow users to experience immersive scenes from various landmarks, we build WorldVista3D dataset for 3D scene reconstruction, which contains panoramic images of globally renowned sites. The implementation code and dataset will be released at https://github.com/LongHZ140516/Scene4U .

Related papers

• HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation [29.579493980120173]
  HoloTime is a framework that integrates video diffusion models to generate panoramic videos from a single prompt or reference image. 360World dataset is the first comprehensive collection of panoramic videos suitable for downstream 4D scene reconstruction tasks. Panoramic Animator is a two-stage image-to-video diffusion model that can convert panoramic images into high-quality panoramic videos. Panoramic Space-Time Reconstruction uses a space-time depth estimation method to transform the generated panoramic videos into 4D point clouds.
  arXiv  Detail & Related papers  (2025-04-30T13:55:28Z)
• PaintScene4D: Consistent 4D Scene Generation from Text Prompts [29.075849524496707]
  PaintScene4D is a novel text-to-4D scene generation framework.<n>It harnesses video generative models trained on diverse real-world datasets.<n>It produces realistic 4D scenes that can be viewed from arbitrary trajectories.
  arXiv  Detail & Related papers  (2024-12-05T18:59:57Z)
• LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation [105.52153675890408]
  3D immersive scene generation is a challenging yet critical task in computer vision and graphics.<n>Layerpano3D is a novel framework for full-view, explorable panoramic 3D scene generation from a single text prompt.
  arXiv  Detail & Related papers  (2024-08-23T17:50:23Z)
• HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions [31.342899807980654]
  3D scene generation is in high demand across various domains, including virtual reality, gaming, and the film industry. We introduce HoloDreamer, a framework that first generates high-definition panorama as a holistic initialization of the full 3D scene. We then leverage 3D Gaussian Splatting (3D-GS) to quickly reconstruct the 3D scene, thereby facilitating the creation of view-consistent and fully enclosed 3D scenes.
  arXiv  Detail & Related papers  (2024-07-21T14:52:51Z)
• 4K4DGen: Panoramic 4D Generation at 4K Resolution [67.98105958108503]
  We tackle the challenging task of elevating a single panorama to an immersive 4D experience. For the first time, we demonstrate the capability to generate omnidirectional dynamic scenes with 360$circ$ views at 4K resolution. We achieve high-quality Panorama-to-4D generation at a resolution of 4K for the first time.
  arXiv  Detail & Related papers  (2024-06-19T13:11:02Z)
• Comp4D: LLM-Guided Compositional 4D Scene Generation [65.5810466788355]
  We present Comp4D, a novel framework for Compositional 4D Generation. Unlike conventional methods that generate a singular 4D representation of the entire scene, Comp4D innovatively constructs each 4D object within the scene separately. Our method employs a compositional score distillation technique guided by the pre-defined trajectories.
  arXiv  Detail & Related papers  (2024-03-25T17:55:52Z)
• Zero-Shot Multi-Object Scene Completion [59.325611678171974]
  We present a 3D scene completion method that recovers the complete geometry of multiple unseen objects in complex scenes from a single RGB-D image. Our method outperforms the current state-of-the-art on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-03-21T17:59:59Z)
• Denoising Diffusion via Image-Based Rendering [54.20828696348574]
  We introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes. First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes. Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images.
  arXiv  Detail & Related papers  (2024-02-05T19:00:45Z)
• SceneWiz3D: Towards Text-guided 3D Scene Composition [134.71933134180782]
  Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets. We introduce SceneWiz3D, a novel approach to synthesize high-fidelity 3D scenes from text.
  arXiv  Detail & Related papers  (2023-12-13T18:59:30Z)
• UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene [52.21184153832739]
  We propose a novel neural rendering system called UE4-NeRF, specifically designed for real-time rendering of large-scale scenes. Our approach combines with the Unrealization pipeline in Unreal Engine 4 (UE4), achieving real-time rendering of large-scale scenes at 4K resolution with a frame rate of up to 43 FPS.
  arXiv  Detail & Related papers  (2023-10-20T04:01:35Z)

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.