Generative View Stitching

• URL: http://arxiv.org/abs/2510.24718v2
• Date: Wed, 05 Nov 2025 17:59:23 GMT
• Title: Generative View Stitching
• Abstract summary: We propose Generative View Stitching (GVS) for camera-guided video generation.<n>GVS samples the entire sequence in parallel so that the generated scene is faithful to every part of the predefined camera trajectory.<n>GVS achieves camera-guided video generation that is stable, collision-free, frame-to-frame consistent, and closes loops for a variety of predefined camera paths.
• Score: 14.38845535978026
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive video diffusion models are capable of long rollouts that are stable and consistent with history, but they are unable to guide the current generation with conditioning from the future. In camera-guided video generation with a predefined camera trajectory, this limitation leads to collisions with the generated scene, after which autoregression quickly collapses. To address this, we propose Generative View Stitching (GVS), which samples the entire sequence in parallel such that the generated scene is faithful to every part of the predefined camera trajectory. Our main contribution is a sampling algorithm that extends prior work on diffusion stitching for robot planning to video generation. While such stitching methods usually require a specially trained model, GVS is compatible with any off-the-shelf video model trained with Diffusion Forcing, a prevalent sequence diffusion framework that we show already provides the affordances necessary for stitching. We then introduce Omni Guidance, a technique that enhances the temporal consistency in stitching by conditioning on both the past and future, and that enables our proposed loop-closing mechanism for delivering long-range coherence. Overall, GVS achieves camera-guided video generation that is stable, collision-free, frame-to-frame consistent, and closes loops for a variety of predefined camera paths, including Oscar Reutersv\"ard's Impossible Staircase. Results are best viewed as videos at https://andrewsonga.github.io/gvs.

Related papers

• CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytelling [111.28808966759613]
  We propose a unified framework named CineWeaver to achieve reference-controllable multi-shot long-video generation without retraining.<n> Experimental results demonstrate that CineWeaver produces high-quality cinematic videos of long durations with consistent identities, stable global appearance, and clear shot transitions.
  arXiv  Detail & Related papers  (2026-07-29T06:48:11Z)
• CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping [81.58057192696843]
  Existing methods that directly inject numerical camera parameters into the diffusion backbone often fail to bridge the gap between abstract coordinates and visual content.<n>We propose CameraNoise, a flow-to-noise warping method that encodes camera motion into a temporally coherent representation.<n>By integrating CameraNoise into the diffusion process, our framework delivers stable, high-fidelity videos.
  arXiv  Detail & Related papers  (2026-05-29T03:02:50Z)
• CamDirector: Towards Long-Term Coherent Video Trajectory Editing [25.122236629305032]
  Video (camera) trajectory editing aims to synthesize new videos that follow user-defined camera paths.<n>We present a new VTE framework that explicitly aggregates information across the entire source video via a hybrid warping scheme.<n>We also present iPhone-PTZ, a new VTE benchmark with diverse camera motions and large trajectory variations.
  arXiv  Detail & Related papers  (2026-02-27T19:23:18Z)
• Plenoptic Video Generation [80.3116444692858]
  We introduce PlenopticDreamer, a framework that synchronizes generative hallucinations to maintain synchronization-temporal memory.<n>The core idea is to train a multi-in-out video-conditioned model in an autoregressive manner.<n>Our training incorporates context-scaling to improve convergence, self-conditioning to hallucinations caused by error accumulation, and a long-video conditioning mechanism to support extended video generation.
  arXiv  Detail & Related papers  (2026-01-08T18:58:32Z)
• Inference-based GAN Video Generation [47.53991869205973]
  We propose a new type of video generator by enabling adversarial-based unconditional video generators with a variational encoder.<n>Existing models struggle with the temporal scaling of the generated videos.<n>We employ a novel, memory-efficient approach to generate long videos composed of hundreds or thousands of frames.
  arXiv  Detail & Related papers  (2025-12-25T20:14:38Z)
• Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation [49.12018869332346]
  InfCam is a camera-controlled video-to-video generation framework with high pose fidelity.<n>The framework integrates two key components: (1) infinite homography warping, which encodes 3D camera rotations directly within the 2D latent space of a video diffusion model.
  arXiv  Detail & Related papers  (2025-12-18T20:03:05Z)
• FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion [46.67733869872552]
  textbfFilmWeaver is a framework designed to generate consistent, multi-shot videos of arbitrary length.<n>Our key insight is to decouple the problem into inter-shot consistency and intra-shot coherence.<n>Our method surpasses existing approaches on metrics for both consistency and aesthetic quality.
  arXiv  Detail & Related papers  (2025-12-12T04:34:53Z)
• Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion [2.5479056464266994]
  Novel view synthesis (NVS) from a single image is highly illposed due to large unobserved regions.<n>We propose a model that addresses this by decomposing single-view NVS into a 360-degree scene extrapolation followed by novel view.<n>Our approach outperforms existing methods in generating coherent views along user-defined trajectories.
  arXiv  Detail & Related papers  (2025-08-31T13:27:15Z)
• Stable Virtual Camera: Generative View Synthesis with Diffusion Models [51.71244310522393]
  We present Stable Virtual Camera (Seva), a generalist diffusion model that creates novel views of a scene.<n>Our approach overcomes these limitations through simple model design, optimized training recipe, and flexible sampling strategy.<n>Our method can generate high-quality videos lasting up to half a minute with seamless loop closure.
  arXiv  Detail & Related papers  (2025-03-18T17:57:22Z)
• Latent-Reframe: Enabling Camera Control for Video Diffusion Model without Training [51.851390459940646]
  We introduce Latent-Reframe, which enables camera control in a pre-trained video diffusion model without fine-tuning.<n>Latent-Reframe operates during the sampling stage, maintaining efficiency while preserving the original model distribution.<n>Our approach reframes the latent code of video frames to align with the input camera trajectory through time-aware point clouds.
  arXiv  Detail & Related papers  (2024-12-08T18:59:54Z)
• Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention [62.2447324481159]
  Cavia is a novel framework for camera-controllable, multi-view video generation. Our framework extends the spatial and temporal attention modules, improving both viewpoint and temporal consistency. Cavia is the first of its kind that allows the user to specify distinct camera motion while obtaining object motion.
  arXiv  Detail & Related papers  (2024-10-14T17:46:32Z)
• ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models [66.84478240757038]
  A majority of video diffusion models (VDMs) generate long videos in an autoregressive manner, i.e., generating subsequent clips conditioned on last frames of previous clip. We introduce causal (i.e., unidirectional) generation into VDMs, and use past frames as prompt to generate future frames. Our ViD-GPT achieves state-of-the-art performance both quantitatively and qualitatively on long video generation.
  arXiv  Detail & Related papers  (2024-06-16T15:37:22Z)
• Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control [70.17137528953953]
  Collaborative video diffusion (CVD) is trained on top of a state-of-the-art camera-control module for video generation. CVD generates multiple videos rendered from different camera trajectories with significantly better consistency than baselines.
  arXiv  Detail & Related papers  (2024-05-27T17:58:01Z)
• Explorative Inbetweening of Time and Space [46.77750028273578]
  We introduce bounded generation to control video generation based only on a given start and end frame. Time Reversal Fusion fuses the temporally forward and backward denoising paths conditioned on the start and end frame. We find that Time Reversal Fusion outperforms related work on all subtasks.
  arXiv  Detail & Related papers  (2024-03-21T17:57:31Z)
• Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image [73.56631858393148]
  We introduce the problem of perpetual view generation -- long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image. We take a hybrid approach that integrates both geometry and image synthesis in an iterative render, refine, and repeat framework. Our approach can be trained from a set of monocular video sequences without any manual annotation.
  arXiv  Detail & Related papers  (2020-12-17T18:59:57Z)

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.