GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting

• URL: http://arxiv.org/abs/2504.10001v3
• Date: Wed, 16 Apr 2025 07:43:01 GMT
• Title: GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting
• Authors: Junlin Hao, Peiheng Wang, Haoyang Wang, Xinggong Zhang, Zongming Guo,
• Abstract summary: GaussVideoDreamer advances generative multimedia approaches by bridging the gap between image, video, and 3D generation.<n>Our approach achieves 32% higher LLaVA-IQA scores and at least 2x speedup compared to existing methods.
• Score: 17.17292309504131
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Single-image 3D scene reconstruction presents significant challenges due to its inherently ill-posed nature and limited input constraints. Recent advances have explored two promising directions: multiview generative models that train on 3D consistent datasets but struggle with out-of-distribution generalization, and 3D scene inpainting and completion frameworks that suffer from cross-view inconsistency and suboptimal error handling, as they depend exclusively on depth data or 3D smoothness, which ultimately degrades output quality and computational performance. Building upon these approaches, we present GaussVideoDreamer, which advances generative multimedia approaches by bridging the gap between image, video, and 3D generation, integrating their strengths through two key innovations: (1) A progressive video inpainting strategy that harnesses temporal coherence for improved multiview consistency and faster convergence. (2) A 3D Gaussian Splatting consistency mask to guide the video diffusion with 3D consistent multiview evidence. Our pipeline combines three core components: a geometry-aware initialization protocol, Inconsistency-Aware Gaussian Splatting, and a progressive video inpainting strategy. Experimental results demonstrate that our approach achieves 32% higher LLaVA-IQA scores and at least 2x speedup compared to existing methods while maintaining robust performance across diverse scenes.

Related papers

• DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer [56.98400572837792]
  DiVE produces high-fidelity, temporally coherent, and cross-view consistent multi-view videos. These innovations collectively achieve a 2.62x speedup with minimal quality degradation.
  arXiv  Detail & Related papers  (2025-04-28T09:20:50Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation [24.255633621887988]
  We propose a method that leverages 2D diffusion models' implicit 3D reasoning ability while ensuring 3D consistency.<n>Specifically, the proposed Gaussian Splatting Decoder enforces 3D consistency by transforming SV3D latent outputs into an explicit 3D representation.<n>As a result, our approach simultaneously generates high-quality, multi-view-consistent images and accurate 3D models.
  arXiv  Detail & Related papers  (2025-03-08T09:10:31Z)
• F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Aggregative Gaussian Splatting [35.625593119642424]
  This paper tackles the problem of generalizable 3D-aware generation from monocular datasets.<n>We propose a novel feed-forward pipeline based on pixel-aligned Gaussian Splatting.<n>We also introduce a self-supervised cycle-aggregative constraint to enforce cross-view consistency in the learned 3D representation.
  arXiv  Detail & Related papers  (2025-01-12T04:44:44Z)
• LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors [107.83398512719981]
  Single-image 3D reconstruction remains a fundamental challenge in computer vision.<n>Recent advances in Latent Video Diffusion Models offer promising 3D priors learned from large-scale video data.<n>We propose LiftImage3D, a framework that effectively releases LVDMs' generative priors while ensuring 3D consistency.
  arXiv  Detail & Related papers  (2024-12-12T18:58:42Z)
• 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. We train a diffusion transformer to learn the joint distribution of RGB and XYZ frames. 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)
• 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)
• Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting [94.84688557937123]
  Video-3DGS is a 3D Gaussian Splatting (3DGS)-based video refiner designed to enhance temporal consistency in zero-shot video editors.<n>Our approach utilizes a two-stage 3D Gaussian optimizing process tailored for editing dynamic monocular videos.<n>It enhances video editing by ensuring temporal consistency across 58 dynamic monocular videos.
  arXiv  Detail & Related papers  (2024-06-04T17:57:37Z)
• Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers [37.14235383028582]
  We introduce a novel approach for single-view reconstruction that efficiently generates a 3D model from a single image via feed-forward inference. Our method utilizes two transformer-based networks, namely a point decoder and a triplane decoder, to reconstruct 3D objects using a hybrid Triplane-Gaussian intermediate representation.
  arXiv  Detail & Related papers  (2023-12-14T17:18:34Z)

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.