FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning
2026-03-05 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present FaceCam, a system that allows changing the camera view in videos of a single person's face using just one video input. They improve on past methods by using a special way to represent camera movements that avoids common visual glitches and doesn't need complex 3D models. They train their system on both controlled studio videos and regular videos and use new techniques to simulate camera motion during training. Tests show their system produces better-looking videos that keep the person's identity and movements consistent.
monocular videocamera trajectoryvideo generationscale-aware representation3D reconstructionmulti-view capturesynthetic camera motionvisual artifactsidentity preservationmotion preservation
Authors
Weijie Lyu, Ming-Hsuan Yang, Zhixin Shu
Abstract
We introduce FaceCam, a system that generates video under customizable camera trajectories for monocular human portrait video input. Recent camera control approaches based on large video-generation models have shown promising progress but often exhibit geometric distortions and visual artifacts on portrait videos due to scale-ambiguous camera representations or 3D reconstruction errors. To overcome these limitations, we propose a face-tailored scale-aware representation for camera transformations that provides deterministic conditioning without relying on 3D priors. We train a video generation model on both multi-view studio captures and in-the-wild monocular videos, and introduce two camera-control data generation strategies: synthetic camera motion and multi-shot stitching, to exploit stationary training cameras while generalizing to dynamic, continuous camera trajectories at inference time. Experiments on Ava-256 dataset and diverse in-the-wild videos demonstrate that FaceCam achieves superior performance in camera controllability, visual quality, identity and motion preservation.