World-consistent Video Diffusion with Explicit 3D Modeling

• URL: http://arxiv.org/abs/2412.01821v1
• Date: Mon, 02 Dec 2024 18:58:23 GMT
• Title: World-consistent Video Diffusion with Explicit 3D Modeling
• Authors: Qihang Zhang, Shuangfei Zhai, Miguel Angel Bautista, Kevin Miao, Alexander Toshev, Joshua Susskind, Jiatao Gu,
• Abstract summary: 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.
• Score: 67.39618291644673
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in diffusion models have set new benchmarks in image and video generation, enabling realistic visual synthesis across single- and multi-frame contexts. However, these models still struggle with efficiently and explicitly generating 3D-consistent content. To address this, we propose World-consistent Video Diffusion (WVD), a novel framework that incorporates explicit 3D supervision using XYZ images, which encode global 3D coordinates for each image pixel. More specifically, we train a diffusion transformer to learn the joint distribution of RGB and XYZ frames. This approach supports multi-task adaptability via a flexible inpainting strategy. For example, WVD can estimate XYZ frames from ground-truth RGB or generate novel RGB frames using XYZ projections along a specified camera trajectory. In doing so, WVD unifies tasks like single-image-to-3D generation, multi-view stereo, and camera-controlled video generation. Our approach demonstrates competitive performance across multiple benchmarks, providing a scalable solution for 3D-consistent video and image generation with a single pretrained model.

Related papers

• VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling [20.329392012132885]
  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. VideoRFSplat outperforms existing text-to-3D direct generation methods that heavily depend on post-hoc refinement via score distillation sampling.
  arXiv  Detail & Related papers  (2025-03-20T05:26:09Z)
• 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. Specifically, the proposed Gaussian Splatting Decoder enforces 3D consistency by transforming SV3D latent outputs into an explicit 3D representation. 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)
• Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation [56.862552362223425]
  This report presents a comprehensive framework for generating high-quality 3D shapes and textures from diverse input prompts. The framework consists of 3D shape generation and texture generation. This report details the system architecture, experimental results, and potential future directions to improve and expand the framework.
  arXiv  Detail & Related papers  (2025-02-20T04:22:30Z)
• 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. We propose a novel feed-forward pipeline based on pixel-aligned Gaussian Splatting. 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)
• Wonderland: Navigating 3D Scenes from a Single Image [43.99037613068823]
  We introduce a large-scale reconstruction model that leverages latents from a video diffusion model to predict 3D Gaussian Splattings of scenes in a feed-forward manner. We train the 3D reconstruction model to operate on the video latent space with a progressive learning strategy, enabling the efficient generation of high-quality, wide-scope, and generic 3D scenes.
  arXiv  Detail & Related papers  (2024-12-16T18:58:17Z)
• 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)
• Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models [112.2625368640425]
  High-resolution Image-to-3D model (Hi3D) is a new video diffusion based paradigm that redefines a single image to multi-view images as 3D-aware sequential image generation. Hi3D first empowers the pre-trained video diffusion model with 3D-aware prior, yielding multi-view images with low-resolution texture details.
  arXiv  Detail & Related papers  (2024-09-11T17:58:57Z)
• 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)
• X-Ray: A Sequential 3D Representation For Generation [54.160173837582796]
  We introduce X-Ray, a novel 3D sequential representation inspired by x-ray scans. X-Ray transforms a 3D object into a series of surface frames at different layers, making it suitable for generating 3D models from images.
  arXiv  Detail & Related papers  (2024-04-22T16:40:11Z)
• MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation [54.27399121779011]
  We present MVD-Fusion: a method for single-view 3D inference via generative modeling of multi-view-consistent RGB-D images. We show that our approach can yield more accurate synthesis compared to recent state-of-the-art, including distillation-based 3D inference and prior multi-view generation methods.
  arXiv  Detail & Related papers  (2024-04-04T17:59:57Z)
• Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models [6.738732514502613]
  Diffusion$2$ is a novel framework for dynamic 3D content creation. It reconciles the knowledge about geometric consistency and temporal smoothness from 3D models to directly sample dense multi-view images. Experiments demonstrate the efficacy of our proposed framework in generating highly seamless and consistent 4D assets.
  arXiv  Detail & Related papers  (2024-04-02T17:58:03Z)
• Envision3D: One Image to 3D with Anchor Views Interpolation [18.31796952040799]
  We present Envision3D, a novel method for efficiently generating high-quality 3D content from a single image. It is capable of generating high-quality 3D content in terms of texture and geometry, surpassing previous image-to-3D baseline methods.
  arXiv  Detail & Related papers  (2024-03-13T18:46:33Z)
• Guide3D: Create 3D Avatars from Text and Image Guidance [55.71306021041785]
  Guide3D is a text-and-image-guided generative model for 3D avatar generation based on diffusion models. Our framework produces topologically and structurally correct geometry and high-resolution textures.
  arXiv  Detail & Related papers  (2023-08-18T17:55:47Z)

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.