4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation

TL;DR

4DVD introduces a cascaded diffusion model that decouples 4D content generation into layout prediction and structure-aware refinement, achieving high-quality 4D video synthesis with superior consistency and practical applicability.

Contribution

The paper proposes a novel cascaded diffusion approach for 4D content generation that separates layout prediction from detailed synthesis, improving quality and consistency over prior methods.

Findings

Achieves state-of-the-art results in 4D video synthesis.

Demonstrates superior cross-view and temporal consistency.

Introduces a new dataset, D-Objaverse, for training and evaluation.

Abstract

Given the high complexity of directly generating high-dimensional data such as 4D, we present 4DVD, a cascaded video diffusion model that generates 4D content in a decoupled manner. Unlike previous multi-view video methods that directly model 3D space and temporal features simultaneously with stacked cross view/temporal attention modules, 4DVD decouples this into two subtasks: coarse multi-view layout generation and structure-aware conditional generation, and effectively unifies them. Specifically, given a monocular video, 4DVD first predicts the dense view content of its layout with superior cross-view and temporal consistency. Based on the produced layout priors, a structure-aware spatio-temporal generation branch is developed, combining these coarse structural priors with the exquisite appearance content of input monocular video to generate final high-quality dense-view videos. Benefit from this, explicit 4D representation~(such as 4D Gaussian) can be optimized accurately, enabling wider practical application. To train 4DVD, we collect a dynamic 3D object dataset, called D-Objaverse, from the Objaverse benchmark and render 16 videos with 21 frames for each object. Extensive experiments demonstrate our state-of-the-art performance on both novel view synthesis and 4D generation. Our project page is https://4dvd.github.io/