arXiv Computer Vision
Did You Steal My Shot? Pioneering Camera Motion Plagiarism Detection in Generative Videos
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 22
VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos
arXiv:2510.24904v2 Announce Type: replace Abstract: Although recent video generative models are getting more capable of following external camera controls, imposed by either text descriptions or came...
arXiv Computer Vision
Aug 24
MotionPhys: Detecting AI-Generated Videos via Physical Consistency of Optical-Flow Trajectories
arXiv:2608.20770v1 Announce Type: new Abstract: Modern AI video generation models can produce videos with high visual fidelity and seemingly smooth temporal transitions. However, visual realism does...
arXiv AI
Jul 7
Motion Attribution for Video Generation
arXiv:2601. 08828v2 Announce Type: replace-cross Abstract: Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood.
arXiv Computer Vision
Oct 19
Learning to Correct Geometry in Generated Videos
arXiv:2610.23856v1 Announce Type: new Abstract: Generated videos often lose geometric consistency under camera motion: structures warp under viewpoint change, parallax becomes inconsistent, and smoot...
arXiv AI
Oct 1
Unveiling the Value of Motion for Cinematic Camera Trajectories
arXiv:2609.38683v1 Announce Type: cross Abstract: Cinematic camera motion is a fundamental storytelling tool, defined not only by where the camera is positioned in the scene, but also by how it moves...
arXiv Computer Vision
Oct 19
Erase the Mark, Preserve the Motion: Temporally Consistent Removal of Video Watermarks
PoseRegen is a new framework for removing video watermarks while maintaining temporal consistency and motion fidelity. It first applies a shared viewpoint transformation to break watermark patterns, then reconstructs the sequence with a pose‑conditioned video model and Flow Matching supervision to preserve identity and background. The method also includes a Pose‑Conditioned Motion Consistency Adapter to keep body‑part trajectories stable, achieving near‑random watermark bit accuracy and outperforming baselines on motion metrics.