MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing

• URL: http://arxiv.org/abs/2607.05376v1
• Date: Mon, 06 Jul 2026 17:54:16 GMT
• Title: MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing
• Abstract summary: We present MV-Forcing, a framework that composes temporal and view-wise autoregression within a single diffusion model.<n>We show that MV-Forcing produces geometrically consistent multi-view videos of dynamic scenes at arbitrary lengths.
• Score: 25.612425628475705
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in video diffusion models have enabled either long single-view generation through temporal autoregression, or short multi-view synthesis through bidirectional attention. However, generating long, multi-view consistent videos of dynamic scenes remains unsolved. In this work, we present MV-Forcing, a framework that composes temporal and view-wise autoregression within a single diffusion model by introducing a 4D geometric bridge between sequentially generated views. Our key insight is that an autoregressive 3D reconstruction model naturally interfaces between autoregressively generated views. Given a completed source view, we reconstruct its 3D structure and render a geometric prior of the next target viewpoint, which the diffusion model refines into a high-quality video. To extend generation beyond the teacher's fixed temporal window, we introduce a joint denoising regime where both view slots are initialized from noise during training, enabling temporally unbounded generation. We distill the model via Distribution Matching Distillation with Spatio-Temporal Self-Forcing, closing the train-inference exposure bias gap for both temporal and view-sequential autoregression. Extensive experiments on both synthetic and real-world data demonstrate that MV-Forcing produces geometrically consistent multi-view videos of dynamic scenes at arbitrary lengths and viewpoint counts using a single few-step student model.

Related papers

• Diff-VF: Training-free High-quality Long Video Generation via Diffusion Model [33.214927542512555]
  Diff-VF is a framework that converts short-video diffusion backbones into long-video generators without modifying or fine-tuning the base model.<n>VBench-Long evaluation results show that Diff-VF achieves a more favorable balance between temporal coherence and motion diversity than base models.
  arXiv  Detail & Related papers  (2026-08-06T12:53:46Z)
• FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching [68.01498128172214]
  We propose a novel but simple inference-time approach for long video generation that is architecture-agnostic and requires no additional training.<n>Our method generates long videos via overlapping sliding windows, where predicted clean samples from adjacent windows are blended via emphTweedie matching to enforce both textbfmanifold constraint and temporal consistency across overlap regions.<n>Our method generates videos several times longer than the native window length while outperforming both training-free and autoregressive baselines in temporal consistency and visual quality, and further extends to audio-video joint generation and text-to-3DGS without any
  arXiv  Detail & Related papers  (2026-05-20T08:55:37Z)
• Human Video Generation from a Single Image with 3D Pose and View Control [62.676151243249556]
  We present Human Video Generation in 4D (HVG), a latent video diffusion model capable of generating high-quality multi-view,temporally coherent human videos from a single image.<n>HVG achieves this through three key designs: (i) Articulated Pose Modulation, which captures the anatomical relationships of 3D joints via a novel dual-dimensional bone map and resolves self-occlusions across views by introducing 3D information; (ii) View and Temporal Alignment, which ensures multi-view consistency and alignment between a reference image and pose sequences for frame-to-frame stability; and (iii)
  arXiv  Detail & Related papers  (2026-02-24T18:42:20Z)
• RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space [51.441415833480505]
  RAYNOVA is a multiview world model for driving scenarios that employs a dual-causal autoregressive framework.<n>It constructs an isotropic-temporal representation across views, frames, and scales based on relative Plcker-ray positional encoding.
  arXiv  Detail & Related papers  (2026-02-24T08:41:40Z)
• MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis [34.793258395288895]
  We present MV-Performer, an innovative framework for creating novel view videos from monocular full-body captures.<n>To achieve a 360-degree synthesis, we extensively leverage the MVHumanNet dataset and incorporate an informative condition signal.<n>To maintain synchronization in the generated videos, we propose a multi-view human-centric video diffusion model.
  arXiv  Detail & Related papers  (2025-10-08T16:24:22Z)
• Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models [83.76517697509156]
  This paper addresses the challenge of high-fidelity view synthesis of humans with sparse-view videos as input.<n>We propose a novel iterative sliding denoising process to enhance view-temporal consistency of the 4D diffusion model.<n>Our method is able to synthesize high-quality and consistent novel-view videos and significantly outperforms the existing approaches.
  arXiv  Detail & Related papers  (2025-07-17T17:59:17Z)
• 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)
• RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks [93.18404922542702]
  We present a novel video generative model designed to address long-term spatial and temporal dependencies. Our approach incorporates a hybrid explicit-implicit tri-plane representation inspired by 3D-aware generative frameworks. Our model synthesizes high-fidelity video clips at a resolution of $256times256$ pixels, with durations extending to more than $5$ seconds at a frame rate of 30 fps.
  arXiv  Detail & Related papers  (2024-01-11T16:48:44Z)
• Spatio-Temporal Self-Attention Network for Video Saliency Prediction [13.873682190242365]
  3D convolutional neural networks have achieved promising results for video tasks in computer vision. We propose a novel Spatio-Temporal Self-Temporal Self-Attention 3 Network (STSANet) for video saliency prediction.
  arXiv  Detail & Related papers  (2021-08-24T12:52:47Z)

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.