VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model

• URL: http://arxiv.org/abs/2403.12010v1
• Date: Mon, 18 Mar 2024 17:48:15 GMT
• Title: VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model
• Authors: Qi Zuo, Xiaodong Gu, Lingteng Qiu, Yuan Dong, Zhengyi Zhao, Weihao Yuan, Rui Peng, Siyu Zhu, Zilong Dong, Liefeng Bo, Qixing Huang,
• Abstract summary: 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.
• Score: 34.35449902855767
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating multi-view images based on text or single-image prompts is a critical capability for the creation of 3D content. Two fundamental questions on this topic are what data we use for training and how to ensure multi-view consistency. This paper introduces a novel framework that makes fundamental contributions to both questions. Unlike leveraging images from 2D diffusion models for training, we propose a dense consistent multi-view generation model that is fine-tuned from off-the-shelf video generative models. Images from video generative models are more suitable for multi-view generation because the underlying network architecture that generates them employs a temporal module to enforce frame consistency. Moreover, the video data sets used to train these models are abundant and diverse, leading to a reduced train-finetuning domain gap. To enhance multi-view consistency, we introduce a 3D-Aware Denoising Sampling, which first employs a feed-forward reconstruction module to get an explicit global 3D model, and then adopts a sampling strategy that effectively involves images rendered from the global 3D model into the denoising sampling loop to improve the multi-view consistency of the final images. As a by-product, this module also provides a fast way to create 3D assets represented by 3D Gaussians within a few seconds. Our approach can generate 24 dense views and converges much faster in training than state-of-the-art approaches (4 GPU hours versus many thousand GPU hours) with comparable visual quality and consistency. By further fine-tuning, our approach outperforms existing state-of-the-art methods in both quantitative metrics and visual effects. Our project page is aigc3d.github.io/VideoMV.

Related papers

• 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)
• Vivid-ZOO: Multi-View Video Generation with Diffusion Model [76.96449336578286]
  New challenges lie in the lack of massive captioned multi-view videos and the complexity of modeling such multi-dimensional distribution. We propose a novel diffusion-based pipeline that generates high-quality multi-view videos centered around a dynamic 3D object from text.
  arXiv  Detail & Related papers  (2024-06-12T21:44:04Z)
• 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)
• 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)
• 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)
• LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation [51.19871052619077]
  We introduce Large Multi-View Gaussian Model (LGM), a novel framework designed to generate high-resolution 3D models from text prompts or single-view images. We maintain the fast speed to generate 3D objects within 5 seconds while boosting the training resolution to 512, thereby achieving high-resolution 3D content generation.
  arXiv  Detail & Related papers  (2024-02-07T17:57:03Z)
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets [36.95521842177614]
  We present Stable Video Diffusion - a latent video diffusion model for high-resolution, state-of-the-art text-to-video and image-to-video generation. We identify and evaluate three different stages for successful training of video LDMs: text-to-image pretraining, video pretraining, and high-quality video finetuning.
  arXiv  Detail & Related papers  (2023-11-25T22:28:38Z)
• ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion [61.37481051263816]
  Given a single image of a 3D object, this paper proposes a method (named ConsistNet) that is able to generate multiple images of the same object. Our method effectively learns 3D consistency over a frozen Zero123 backbone and can generate 16 surrounding views of the object within 40 seconds on a single A100 GPU.
  arXiv  Detail & Related papers  (2023-10-16T12:29:29Z)

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.