GeoStream: Toward Precise Camera Controlled Streaming Video Generation

• URL: http://arxiv.org/abs/2606.15162v1
• Date: Sat, 13 Jun 2026 07:18:04 GMT
• Title: GeoStream: Toward Precise Camera Controlled Streaming Video Generation
• Abstract summary: Existing approaches learn camera motion implicitly, leading to inaccurate control under out-of-distribution trajectories.<n>Explicit geometric conditioning improves controllability, but existing methods are non-autoregressive.<n>We propose GeoStream, a framework that enables precise metric-scale camera control in autoregressive streaming video generation.
• Score: 85.01823220801256
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate interactive camera control is essential for video-based world models, but most existing approaches learn camera motion implicitly, leading to inaccurate control under out-of-distribution trajectories. Explicit geometric conditioning improves controllability, but existing methods are non-autoregressive and rely on a static 3D cache built from an initial frame, which becomes ineffective once the viewpoint moves beyond the original frustum. We propose GeoStream, a framework that enables precise metric-scale camera control in autoregressive streaming video generation. Our method maintains a self-refreshing 3D cache that is periodically updated online from the model's own outputs: we estimate depth from the most recently generated frame, unproject to 3D, and reproject into the target view to produce point reprojections as geometric conditioning for subsequent synthesis. By the same principle, the conditioning seen during training is also rendered from the student's own generated frames, yielding a fully on-policy distillation that naturally aligns the train and inference conditioning distributions. Unlike prior work that uses off-policy condition noising, our approach trains the model against the exact error distribution it encounters at inference, mitigating both standard autoregressive drift and the second-order geometric feedback loop that arises when the cache itself is derived from generated outputs. Quantitative and qualitative results show that our approach substantially improves camera controllability.

Related papers

• Geo-Align: Video Generation Alignment via Metric Geometry Reward [53.65904111864641]
  Geo-Align is the first Reinforcement Learning framework specifically designed for camera-controlled video re-rendering.<n>Built upon a pretrained model, we optimize the model through a scale-aware perceptual reward mechanism.<n>Experiments demonstrate that Geo-Align consistently outperforms existing supervised learning baselines in both precise camera controllability and visual fidelity.
  arXiv  Detail & Related papers  (2026-05-22T17:59:43Z)
• Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting [3.1328424544428852]
  We create a framework capable of leveraging internet-scale monocular videos.<n>Our core contribution is the generation of pseudo multi-view training triplets, consisting of a source video, a geometric anchor, and a target video.<n>At inference, our diffusion transformer utilizes a 4D point-cloud derived anchor to achieve state-of-the-art temporal consistency.
  arXiv  Detail & Related papers  (2026-04-23T15:32:56Z)
• 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)
• GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering [54.489285024494855]
  Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent.<n>Existing approaches, depending on the domain they operate, suffer from several issues that degrade the user experience.<n>We introduce textbfGaVS, a novel 3D-grounded approach that reformulates video stabilization as a temporally-consistent local reconstruction and rendering' paradigm.
  arXiv  Detail & Related papers  (2025-06-30T15:24:27Z)
• 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)
• VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control [74.5434726968562]
  We show how to tame transformers video for 3D camera control using a ControlNet-like conditioning mechanism.<n>Our work is the first to enable camera control for transformer-based video diffusion models.
  arXiv  Detail & Related papers  (2024-07-17T17:59:05Z)
• 3D Scene Geometry-Aware Constraint for Camera Localization with Deep Learning [11.599633757222406]
  Recently end-to-end approaches based on convolutional neural network have been much studied to achieve or even exceed 3D-geometry based traditional methods. In this work, we propose a compact network for absolute camera pose regression. Inspired from those traditional methods, a 3D scene geometry-aware constraint is also introduced by exploiting all available information including motion, depth and image contents.
  arXiv  Detail & Related papers  (2020-05-13T04:15:14Z)

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.