GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation

• URL: http://arxiv.org/abs/2605.18365v1
• Date: Mon, 18 May 2026 13:17:08 GMT
• Title: GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation
• Abstract summary: We introduce a geometry-consistency reward that measures whether motion in a generated video is compatible with a coherent scene.<n>We operationalize this using optical flow, depth--pose predictions, and feature-based correspondence to separate rigid and dynamic regions.<n>Experiments show substantial reductions in temporal geometric artifacts over strong baselines while preserving perceptual quality.
• Score: 46.507099021313074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object deformation, texture drift, and non-rigid backgrounds under camera motion. Existing solutions either improve consistency as a byproduct, apply only to static scenes or realign the latent space of the model completely. We introduce a geometry-consistency reward that directly measures whether motion in a generated video is compatible with a coherent scene. Our key insight is that in physically consistent videos, background motion should be explainable by rigid camera-induced flow, while independently moving objects should preserve appearance identity along motion trajectories. We operationalize this using optical flow, depth--pose predictions, and feature-based correspondence to separate rigid and dynamic regions and evaluate their respective consistency. Integrating this reward with reinforcement fine-tuning transforms geometric consistency from an emergent property into an explicit optimization objective for video generators. The approach is model agnostic and applies to diverse dynamic scenes containing both camera and object motion. Experiments show substantial reductions in temporal geometric artifacts over strong baselines while preserving perceptual quality. Code and model weights are published.

Related papers

• VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modeling [49.98112719317813]
  Video diffusion models often fail to preserve 3D structure over time.<n>Existing methods usually enforce geometric consistency by using explicit geometry reconstructions.<n>We propose VideoWeave, a latent-space post-training framework that uses implicit geometry-model features to constrain the generative distribution.
  arXiv  Detail & Related papers  (2026-06-12T06:41:13Z)
• R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow [50.93811008612562]
  Video-guided 3D animation holds immense potential for content creation, offering intuitive and precise control over dynamic assets.<n>In real-world scenarios, the initial pose of a user-provided video rarely aligns with the starting frame of a reference video.<n>We propose R-DMesh, a framework designed to generate high-fidelity 4D meshes that align with video context.
  arXiv  Detail & Related papers  (2026-05-13T17:58:13Z)
• Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes [32.40228197424996]
  We present Kinematics-GS, a kinematics-aware framework that models blur as motion-aligned deformation.<n>To stabilize optimization, we decompose scenes into dynamic and static components using temporal deformation variance.<n>We also introduce a challenging real-world dataset of deformable and elastic objects exhibiting non-rigid motion.
  arXiv  Detail & Related papers  (2026-05-09T03:01:17Z)
• Measuring 3D Spatial Geometric Consistency in Dynamic Generated Videos [67.7364297817535]
  We introduce SGC, a metric for evaluating 3D textbfSpatial textbfGeometric textbfConsistency in videos.<n>SGC robustly quantifies geometric inconsistencies, effectively identifying critical failures missed by existing metrics.
  arXiv  Detail & Related papers  (2026-03-19T15:44:39Z)
• GeoVideo: Introducing Geometric Regularization into Video Generation Model [46.38507581500745]
  We introduce geometric regularization losses into video generation by augmenting latent diffusion models with per-frame depth prediction.<n>Our method bridges the gap between appearance generation and 3D structure modeling, leading to improved structural coherence-temporal shape, consistency, and physical plausibility.
  arXiv  Detail & Related papers  (2025-12-03T05:11:57Z)
• Epipolar Geometry Improves Video Generation Models [73.44978239787501]
  3D-consistent video generation could significantly impact numerous downstream applications in generation and reconstruction tasks.<n>We explore how epipolar geometry constraints improve modern video diffusion models.<n>By bridging data-driven deep learning with classical geometric computer vision, we present a practical method for generating spatially consistent videos.
  arXiv  Detail & Related papers  (2025-10-24T16:21:37Z)
• UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation [63.90470530428842]
  In this work, we demonstrate that, through appropriate design and fine-tuning, the intrinsic consistency of video generation models can be effectively harnessed for consistent geometric estimation.<n>Our results achieve superior performance in predicting global geometric attributes in videos and can be directly applied to reconstruction tasks.
  arXiv  Detail & Related papers  (2025-05-30T12:31:59Z)
• Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation [47.203483017875726]
  We introduce a novel approach for creating controllable dynamics in 3D-generated Gaussians using casually captured reference videos. Our method transfers the motion of objects from reference videos to a variety of generated 3D Gaussians across different categories. Our technique offers specific and high-quality motion transfer, maintaining both shape integrity and temporal consistency.
  arXiv  Detail & Related papers  (2024-05-27T05:49:12Z)

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.