Research map / Video / Video generation
FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning
Weijie Lyu, Ming-Hsuan Yang, Zhixin Shu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add in-the-wild videos with synthetic camera motion to training (ablation) | FaceCam · In-the-wild videos (dynamic cameras) | ArcFace similarity: 77.73 -> 83.94 | Improved |
| add in-the-wild videos with synthetic camera motion to training (ablation) | FaceCam · In-the-wild videos (dynamic cameras) | imaging quality: 70.71 -> 73.49 | Improved |
| add in-the-wild videos with synthetic camera motion to training (ablation) | FaceCam · In-the-wild videos (dynamic cameras) | aesthetic quality: 55.73 -> 59.91 | Improved |
| add in-the-wild videos with synthetic camera motion to training (ablation) | FaceCam · In-the-wild videos (dynamic cameras) | camera correctness (%): 100.00 -> 97.00 | Hurt |
| add in-the-wild videos with synthetic camera motion to training (ablation) | FaceCam · In-the-wild videos (dynamic cameras) | dynamic degree: 89.00 -> 96.00 | Improved |
| condition on target-frame landmarks (FaceCam) vs generic-head landmarks (FaceCam*) (ablation) | FaceCam · Ava-256 (static cameras) | PSNR: 9.83 -> 15.85 | Improved |
| use scale-aware landmark camera conditioning instead of extrinsics (ReCamMaster) | FaceCam · Ava-256 (static cameras) | ArcFace: 0.7014 -> 0.8574 | Improved |
| use landmark camera conditioning instead of point-cloud reconstruction (TrajectoryCrafter) | FaceCam · In-the-wild videos (dynamic cameras) | ArcFace similarity: 49.79 -> 83.94 | Improved |
| use FaceCam vs TrajectoryCrafter for camera correctness | FaceCam · In-the-wild videos (dynamic cameras) | camera correctness (%): 99.00 -> 97.00 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ReCamMaster — ReCamMaster: Camera-Controlled Generative Rendering from A Single Video (ICCV 2025) · better on 7 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers (CVPR 2025 · similarity 0.88)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.86)
- Training-free Camera Control for Video Generation (ICLR 2025 · similarity 0.86)
- EchoShot: Multi-Shot Portrait Video Generation (NeurIPS 2025 · similarity 0.86)
- RealPortrait: Realistic Portrait Animation with Diffusion Transformers (AAAI 2025 · similarity 0.86)
- DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
