Abstract
Recent approaches to controllable 4D video generation often rely on fine-tuning pre-trained Video Diffusion Models (VDMs). This dominant paradigm is computationally expensive, requiring large-scale datasets and architectural modifications, and frequently suffers from catastrophic forgetting of the model's original generative priors. Here, we propose InverseCrafter, an efficient inpainting inverse solver that reformulates the 4D generation task as an inpainting problem solved in the latent space. The core of our method is a principled mechanism to encode the pixel space degradation operator into a continuous, multi-channel latent mask, thereby bypassing the costly bottleneck of repeated VAE operations and backpropagation. InverseCrafter not only achieves comparable novel view generation and superior measurement consistency in camera control tasks with near-zero computational overhead, but also excels at general-purpose video inpainting with editing. Code is available at this https URL.
Abstract (translated)
最近的可控4D视频生成方法通常依赖于微调预训练的视频扩散模型（VDMs）。这一主流范式在计算上成本高昂，需要大规模的数据集和架构修改，并且常常会导致模型原始生成先验知识的灾难性遗忘。为此，我们提出了InverseCrafter，这是一种高效的修复逆向求解器，它将4D生成任务重新表述为一种在潜在空间中解决的修补问题。我们的方法核心是一个有原则的机制，用于将像素空间退化算子编码成一个连续的、多通道的潜在掩模，从而绕过了重复VAE操作和反向传播的成本高昂瓶颈。 InverseCrafter不仅实现了与现有方法相当的新视角生成能力，并且在相机控制任务中表现出更优的测量一致性，同时几乎不增加计算开销。此外，在通用视频修补和编辑方面也表现优异。代码可在提供的链接地址获取。
URL
https://arxiv.org/abs/2512.05672
