Video Perception Models for 3D Scene Synthesis

• URL: http://arxiv.org/abs/2506.20601v1
• Date: Wed, 25 Jun 2025 16:40:17 GMT
• Title: Video Perception Models for 3D Scene Synthesis
• Authors: Rui Huang, Guangyao Zhai, Zuria Bauer, Marc Pollefeys, Federico Tombari, Leonidas Guibas, Gao Huang, Francis Engelmann,
• Abstract summary: VIPScene is a novel framework that exploits the encoded commonsense knowledge of the 3D physical world in video generation models.<n>VIPScene seamlessly integrates video generation, feedforward 3D reconstruction, and open-vocabulary perception models to semantically and geometrically analyze each object in a scene.
• Score: 109.5543506037003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditionally, 3D scene synthesis requires expert knowledge and significant manual effort. Automating this process could greatly benefit fields such as architectural design, robotics simulation, virtual reality, and gaming. Recent approaches to 3D scene synthesis often rely on the commonsense reasoning of large language models (LLMs) or strong visual priors of modern image generation models. However, current LLMs demonstrate limited 3D spatial reasoning ability, which restricts their ability to generate realistic and coherent 3D scenes. Meanwhile, image generation-based methods often suffer from constraints in viewpoint selection and multi-view inconsistencies. In this work, we present Video Perception models for 3D Scene synthesis (VIPScene), a novel framework that exploits the encoded commonsense knowledge of the 3D physical world in video generation models to ensure coherent scene layouts and consistent object placements across views. VIPScene accepts both text and image prompts and seamlessly integrates video generation, feedforward 3D reconstruction, and open-vocabulary perception models to semantically and geometrically analyze each object in a scene. This enables flexible scene synthesis with high realism and structural consistency. For more precise analysis, we further introduce First-Person View Score (FPVScore) for coherence and plausibility evaluation, utilizing continuous first-person perspective to capitalize on the reasoning ability of multimodal large language models. Extensive experiments show that VIPScene significantly outperforms existing methods and generalizes well across diverse scenarios. The code will be released.

Related papers

• ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary [37.41274496314127]
  ArtiScene is a training-free automated pipeline for scene design.<n>It generates 2D images from a scene description, then extract the shape and appearance of objects to create 3D models.<n>It outperforms state-of-the-art benchmarks by a large margin in layout and aesthetic quality by quantitative metrics.
  arXiv  Detail & Related papers  (2025-05-31T23:03:54Z)
• Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation [36.44409268300039]
  Scenethesis is a framework that integrates text-based scene planning with vision-guided layout refinement.<n>It generates diverse, realistic, and physically plausible 3D interactive scenes, making it valuable for virtual content creation, simulation environments, and embodied AI research.
  arXiv  Detail & Related papers  (2025-05-05T17:59:58Z)
• MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling [21.1274747033854]
  Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes.<n>Milo is a novel framework which can synthesize character videos with controllable attributes.<n>Milo achieves advanced scalability to arbitrary characters, generality to novel 3D motions, and applicability to interactive real-world scenes.
  arXiv  Detail & Related papers  (2024-09-24T15:00:07Z)
• ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis [63.169364481672915]
  We propose textbfViewCrafter, a novel method for synthesizing high-fidelity novel views of generic scenes from single or sparse images. Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames.
  arXiv  Detail & Related papers  (2024-09-03T16:53:19Z)
• Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models [57.30913211264333]
  We present Story3D-Agent, a pioneering approach that transforms provided narratives into 3D-rendered visualizations. By integrating procedural modeling, our approach enables precise control over multi-character actions and motions, as well as diverse decorative elements. We have thoroughly evaluated our Story3D-Agent to validate its effectiveness, offering a basic framework to advance 3D story representation.
  arXiv  Detail & Related papers  (2024-08-21T17:43:15Z)
• Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis [43.02778060969546]
  We propose a controllable monocular dynamic view synthesis pipeline. Our model does not require depth as input, and does not explicitly model 3D scene geometry. We believe our framework can potentially unlock powerful applications in rich dynamic scene understanding, perception for robotics, and interactive 3D video viewing experiences for virtual reality.
  arXiv  Detail & Related papers  (2024-05-23T17:59:52Z)
• 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)
• DORSal: Diffusion for Object-centric Representations of Scenes et al [28.181157214966493]
  Recent progress in 3D scene understanding enables scalable learning of representations across large datasets of diverse scenes. We propose DORSal, which adapts a video diffusion architecture for 3D scene generation conditioned on frozen object-centric slot-based representations of scenes.
  arXiv  Detail & Related papers  (2023-06-13T18:32:35Z)
• 3D Neural Scene Representations for Visuomotor Control [78.79583457239836]
  We learn models for dynamic 3D scenes purely from 2D visual observations. A dynamics model, constructed over the learned representation space, enables visuomotor control for challenging manipulation tasks.
  arXiv  Detail & Related papers  (2021-07-08T17:49:37Z)

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.