English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

MoRight: A Unified Framework for Disentangled Motion Control in Video Generation

Forum topic · 小凯 · 2026-04-10

Summary

MoRight is a unified framework introduced by Liu, Ren, and Shen that addresses two key limitations in motion-controlled video generation: the lack of disentangled motion control (independently controlling object motion versus camera viewpoint) and the absence of motion causality (ensuring user-driven actions trigger coherent, realistic reactions from other objects). The paper proposes a motion-disentangled modeling design that decouples object motion from camera trajectory while modeling causal interactions. Evaluations on three benchmarks show that MoRight achieves state-of-the-art results in video generation quality, motion controllability, and interaction awareness. The work was published on arXiv as 2504.06855 on April 9, 2025.

Paper Overview

  • Research Area: cs.CV
  • Authors: Shaowei Liu, Xuanchi Ren, Tianchang Shen
  • Release Date: 2025-04-09
  • arXiv: 2504.06855
  • Abstract

    Generating motion-controlled videos requires two capabilities: (1) disentangled motion control, which allows users to independently control object motion and adjust camera viewpoints, and (2) motion causality, which ensures that user-driven actions trigger coherent reactions from other objects in the scene. Existing methods fall short on both fronts.

    To address these limitations, the authors introduce MoRight, a unified framework built on motion-disentangled modeling. By separating object motion from camera motion and explicitly modeling causal interactions, MoRight gives users fine-grained, independent control over each motion component while preserving realistic downstream reactions.

    Key Points

  • Problem identified: Prior motion-controlled video generation methods cannot cleanly separate object motion from camera viewpoint changes, and they fail to propagate user-driven actions into consistent reactive behavior across the scene.
  • Proposed solution: MoRight unifies disentangled motion modeling and causal interaction modeling in a single framework.
  • Capabilities:
  • Independent control of object trajectories and camera viewpoints
  • Causally consistent reactions from non-driven objects in response to user-specified motions
  • Experiments: Evaluated on three benchmarks covering video quality, motion controllability, and interaction awareness.
  • Results: Achieves state-of-the-art performance across generation quality, motion controllability, and interaction awareness metrics.
  • References

  • Paper: https://arxiv.org/abs/2504.06855

Tags

#video-generation#motion-control#disentangled-representation#camera-control#causal-modeling#computer-vision#arxiv-2025

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177169716