Generative Video Motion Editing with 3D Point Tracks

TL;DR

This paper introduces a novel track-conditioned video-to-video framework that uses 3D point tracks to enable precise, joint editing of camera and object motions in videos, addressing limitations of existing methods.

Contribution

It proposes a new method leveraging 3D point tracks for joint editing of camera and object motion, improving control and coherence in video editing tasks.

Findings

Supports diverse motion edits including joint camera/object manipulation.

Uses 3D tracks to resolve depth and occlusion issues.

Achieves spatiotemporal coherence in edited videos.

Abstract

Camera and object motions are central to a video's narrative. However, precisely editing these captured motions remains a significant challenge, especially under complex object movements. Current motion-controlled image-to-video (I2V) approaches often lack full-scene context for consistent video editing, while video-to-video (V2V) methods provide viewpoint changes or basic object translation, but offer limited control over fine-grained object motion. We present a track-conditioned V2V framework that enables joint editing of camera and object motion. We achieve this by conditioning a video generation model on a source video and paired 3D point tracks representing source and target motions. These 3D tracks establish sparse correspondences that transfer rich context from the source video to new motions while preserving spatiotemporal coherence. Crucially, compared to 2D tracks, 3D tracks provide explicit depth cues, allowing the model to resolve depth order and handle occlusions for precise motion editing. Trained in two stages on synthetic and real data, our model supports diverse motion edits, including joint camera/object manipulation, motion transfer, and non-rigid deformation, unlocking new creative potential in video editing.