ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number

• URL: http://arxiv.org/abs/2606.19805v1
• Date: Thu, 18 Jun 2026 05:19:17 GMT
• Title: ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number
• Abstract summary: Transferring the camera motion of a reference video to a freshly generated one lets creators reuse cinematic moves.<n>We trace this to a geometric fact: translation-induced image motion scales as T||Z, so a monocular trajectory is meaningful only up to a depth-scale gauge.<n>We distill this into the Parallax Number Pi =Delta T|| / Zbar, a dimensionless, gauge-invariant descriptor of how strongly a camera move is felt.<n>ParaScale is a plug-and-play module that reads Pi off any reference video and re-realizes it against the target scene's own
• Score: 0.4790056963046066
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transferring the camera motion of a reference video to a freshly generated one lets creators reuse cinematic moves. Yet reference and target often live at incompatible scales -- a sweep across a galaxy versus a nudge across a desk -- and naively reusing the recovered trajectory yields either imperceptible or violently exaggerated motion. We trace this to a geometric fact: translation-induced image motion scales as ||T||/Z, so a monocular trajectory is meaningful only up to a depth-scale gauge. We distill this into the Parallax Number Pi = ||Delta T|| / Zbar, a dimensionless, gauge-invariant descriptor of how strongly a camera move is felt, and prove that it -- not the raw trajectory -- is the quantity that scale-faithful transfer must preserve. ParaScale is a plug-and-play module that reads Pi off any reference video and re-realizes it against the target scene's own depth, per frame, leaving rotation untouched. Sitting between pose extraction and pose injection, it requires no retraining and drops into any pose-conditioned generator. We further introduce the Parallax Consistency Error (PCE), a scale-symmetric metric that -- unlike the similarity-aligned TransErr -- exposes scene-scale mismatch. Across scale regimes spanning four orders of magnitude and multiple backbones, ParaScale keeps the realized parallax on the identity line and cuts PCE by more than 3x over uncalibrated transfer with no loss of visual fidelity.

Related papers

• OmniPoint: Universal Monocular Metric Pointcloud from Any Camera [79.24417597712802]
  We present OmniPoint, a unified framework designed to generalize metric reconstruction across diverse imaging sensors.<n>To overcome projection rigidity, OmniPoint abandons conventional planar depth regression.<n>It instead adopts a decoupled ray and distance representation alongside a decoupled training objective.
  arXiv  Detail & Related papers  (2026-09-08T19:45:58Z)
• Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentation [42.33906056027883]
  Representing manipulation actions as 2D trajectories in the camera plane provides a compact and interpretable basis for learning complex 3D manipulation policies.<n>We propose Pix2Act, an imitation learning method that addresses these challenges by generating continuous image-space keypoint trajectories in each camera plane.<n>This reformulates high-dimensional 3D control as a simpler, more learnable 2D prediction problem.
  arXiv  Detail & Related papers  (2026-07-13T07:03:29Z)
• OrthoMotion:Disentangling Camera and Subject Motion via Geometry Semantics Orthogonal Attention [0.4790056963046066]
  Controllable video generation demands independent command of the camera and the subject.<n> OrthoMotion routes camera motion into a geometric channel, a norm-preserving rotation of the rotary position embedding (RoPE) phase, and subject motion into a semantic channel.<n>To our knowledge OrthoMotion is the first method to guarantee disentanglement by construction rather than hope for it to emerge.
  arXiv  Detail & Related papers  (2026-06-22T04:15:14Z)
• Detailed Geometry and Appearance from Opportunistic Motion [44.38825288921379]
  Reconstructing 3D geometry and appearance from a sparse set of fixed cameras is a foundational task with broad applications.<n>We show that the static cameras effectively orbit'' the object in its local coordinate frame, providing additional virtual viewpoints.<n> Harnessing this object motion, however, poses two challenges: the tight coupling of object pose and geometry estimation and the complex appearance variations of a moving object under static illumination.
  arXiv  Detail & Related papers  (2026-03-27T17:59:16Z)
• Dynamic View Synthesis from Small Camera Motion Videos [56.359460602781304]
  We present a novel view synthesis for dynamic $3$D scenes based on distribution-based depth regularization.<n>We also introduce constraints that enforce the volume density of spatial points before the object boundary along the ray to be near zero, ensuring that our model learns the correct geometry of the scene.<n>We conduct extensive experiments to demonstrate the effectiveness of our approach in representing scenes with small camera motion input, and our results compare favorably to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-06-29T09:17:55Z)
• PoseTraj: Pose-Aware Trajectory Control in Video Diffusion [17.0187150041712]
  We introduce PoseTraj, a pose-aware video dragging model for generating 3D-aligned motion from 2D trajectories.<n>Our method adopts a novel two-stage pose-aware pretraining framework, improving 3D understanding across diverse trajectories.
  arXiv  Detail & Related papers  (2025-03-20T12:01:43Z)
• LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis [80.2461057573121]
  In this work, we augment the interaction with a new dimension, i.e., the depth dimension, such that users are allowed to assign a relative depth for each point on the trajectory.<n>We propose a pioneering method for 3D trajectory control in image-to-video by abstracting object masks into a few cluster points.<n>Experiments validate the effectiveness of our approach, dubbed LeviTor, in precisely manipulating the object movements when producing photo-realistic videos from static images.
  arXiv  Detail & Related papers  (2024-12-19T18:59:56Z)
• Pose-Free Generalizable Rendering Transformer [72.47072706742065]
  PF-GRT is a Pose-Free framework for Generalizable Rendering Transformer. PF-GRT is parameterized using a local relative coordinate system. Experiments with zero-shot rendering on datasets reveal that it produces superior quality in generating photo-realistic images.
  arXiv  Detail & Related papers  (2023-10-05T17:24:36Z)
• RePAST: Relative Pose Attention Scene Representation Transformer [78.33038881681018]
  Scene Representation Transformer (SRT) is a recent method to render novel views at interactive rates. We propose Relative Pose Attention SRT (RePAST): Instead of fixing a reference frame at the input, we inject pairwise relative camera pose information directly into the attention mechanism of the Transformers.
  arXiv  Detail & Related papers  (2023-04-03T13:13:12Z)
• Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos [115.71874459429381]
  We propose a method for jointly estimating the 3D motion, 3D shape, and appearance of highly motion-blurred objects from a video. Experiments on benchmark datasets demonstrate that our method outperforms previous methods for fast moving object deblurring and 3D reconstruction.
  arXiv  Detail & Related papers  (2021-11-29T11:25:14Z)

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.