VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling

• URL: http://arxiv.org/abs/2503.15855v1
• Date: Thu, 20 Mar 2025 05:26:09 GMT
• Title: VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling
• Authors: Hyojun Go, Byeongjun Park, Hyelin Nam, Byung-Hoon Kim, Hyungjin Chung, Changick Kim,
• Abstract summary: We propose VideoRFSplat, a text-to-3D model leveraging a video generation model to generate realistic 3D Gaussian Splatting (3DGS) for unbounded real-world scenes.<n>VideoRFSplat outperforms existing text-to-3D direct generation methods that heavily depend on post-hoc refinement via score distillation sampling.
• Score: 20.329392012132885
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose VideoRFSplat, a direct text-to-3D model leveraging a video generation model to generate realistic 3D Gaussian Splatting (3DGS) for unbounded real-world scenes. To generate diverse camera poses and unbounded spatial extent of real-world scenes, while ensuring generalization to arbitrary text prompts, previous methods fine-tune 2D generative models to jointly model camera poses and multi-view images. However, these methods suffer from instability when extending 2D generative models to joint modeling due to the modality gap, which necessitates additional models to stabilize training and inference. In this work, we propose an architecture and a sampling strategy to jointly model multi-view images and camera poses when fine-tuning a video generation model. Our core idea is a dual-stream architecture that attaches a dedicated pose generation model alongside a pre-trained video generation model via communication blocks, generating multi-view images and camera poses through separate streams. This design reduces interference between the pose and image modalities. Additionally, we propose an asynchronous sampling strategy that denoises camera poses faster than multi-view images, allowing rapidly denoised poses to condition multi-view generation, reducing mutual ambiguity and enhancing cross-modal consistency. Trained on multiple large-scale real-world datasets (RealEstate10K, MVImgNet, DL3DV-10K, ACID), VideoRFSplat outperforms existing text-to-3D direct generation methods that heavily depend on post-hoc refinement via score distillation sampling, achieving superior results without such refinement.

Related papers

• CDI3D: Cross-guided Dense-view Interpolation for 3D Reconstruction [25.468907201804093]
  Large Reconstruction Models (LRMs) have shown great promise in leveraging multi-view images generated by 2D diffusion models to extract 3D content.<n>However, 2D diffusion models often struggle to produce dense images with strong multi-view consistency.<n>We present CDI3D, a feed-forward framework designed for efficient, high-quality image-to-3D generation with view.
  arXiv  Detail & Related papers  (2025-03-11T03:08:43Z)
• Wonderland: Navigating 3D Scenes from a Single Image [43.99037613068823]
  We introduce a large-scale reconstruction model that uses latents from a video diffusion model to predict 3D Gaussian Splattings for the scenes.<n>We train the 3D reconstruction model to operate on the video latent space with a progressive training strategy, enabling the efficient generation of high-quality, wide-scope, and generic 3D scenes.
  arXiv  Detail & Related papers  (2024-12-16T18:58:17Z)
• World-consistent Video Diffusion with Explicit 3D Modeling [67.39618291644673]
  World-consistent Video Diffusion (WVD) is a novel framework that incorporates explicit 3D supervision using XYZ images.<n>We train a diffusion transformer to learn the joint distribution of RGB and XYZ frames.<n>WVD unifies tasks like single-image-to-3D generation, multi-view stereo, and camera-controlled video generation.
  arXiv  Detail & Related papers  (2024-12-02T18:58:23Z)
• MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model [87.71060849866093]
  We introduce MVGenMaster, a multi-view diffusion model enhanced with 3D priors to address versatile Novel View Synthesis (NVS) tasks.<n>Our model features a simple yet effective pipeline that can generate up to 100 novel views conditioned on variable reference views and camera poses.<n>We present several training and model modifications to strengthen the model with scaled-up datasets.
  arXiv  Detail & Related papers  (2024-11-25T07:34:23Z)
• Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation [61.040832373015014]
  We propose Flex3D, a novel framework for generating high-quality 3D content from text, single images, or sparse view images. We employ a fine-tuned multi-view image diffusion model and a video diffusion model to generate a pool of candidate views, enabling a rich representation of the target 3D object. In the second stage, the curated views are fed into a Flexible Reconstruction Model (FlexRM), built upon a transformer architecture that can effectively process an arbitrary number of inputs.
  arXiv  Detail & Related papers  (2024-10-01T17:29:43Z)
• MVGamba: Unify 3D Content Generation as State Space Sequence Modeling [150.80564081817786]
  We introduce MVGamba, a general and lightweight Gaussian reconstruction model featuring a multi-view Gaussian reconstructor.<n>With off-the-detail multi-view diffusion models integrated, MVGamba unifies 3D generation tasks from a single image, sparse images, or text prompts.<n>Experiments demonstrate that MVGamba outperforms state-of-the-art baselines in all 3D content generation scenarios with approximately only $0.1times$ of the model size.
  arXiv  Detail & Related papers  (2024-06-10T15:26:48Z)
• Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data [80.92268916571712]
  A critical bottleneck is the scarcity of high-quality 3D objects with detailed captions. We propose Bootstrap3D, a novel framework that automatically generates an arbitrary quantity of multi-view images. We have generated 1 million high-quality synthetic multi-view images with dense descriptive captions.
  arXiv  Detail & Related papers  (2024-05-31T17:59:56Z)
• MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-View [0.0]
  This paper proposes a general framework to generate consistent multi-view images from single image or leveraging scene representation transformer and view-conditioned diffusion model. Our model is able to generate 3D meshes surpassing baselines methods in evaluation metrics, including PSNR, SSIM and LPIPS.
  arXiv  Detail & Related papers  (2024-05-06T22:55:53Z)
• VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model [34.35449902855767]
  Two fundamental questions are what data we use for training and how to ensure multi-view consistency. We propose a dense consistent multi-view generation model that is fine-tuned from off-the-shelf video generative models. Our approach can generate 24 dense views and converges much faster in training than state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-03-18T17:48:15Z)
• 3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation [51.64796781728106]
  We propose a generative refinement network to synthesize new contents with higher quality by exploiting the natural image prior to 2D diffusion model and the global 3D information of the current scene. Our approach supports wide variety of scene generation and arbitrary camera trajectories with improved visual quality and 3D consistency.
  arXiv  Detail & Related papers  (2024-03-14T14:31:22Z)
• ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models [65.22994156658918]
  We present a method that learns to generate multi-view images in a single denoising process from real-world data. We design an autoregressive generation that renders more 3D-consistent images at any viewpoint.
  arXiv  Detail & Related papers  (2024-03-04T07:57:05Z)

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.