ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912959244009472 |
|---|---|
| author | Yang, Liudi Eskandar, George Shen, Fengyi Altillawi, Mohammad Bai, Yang Zhang, Chi Liu, Ziyuan Valada, Abhinav |
| author_facet | Yang, Liudi Eskandar, George Shen, Fengyi Altillawi, Mohammad Bai, Yang Zhang, Chi Liu, Ziyuan Valada, Abhinav |
| contents | We address the challenge of novel view synthesis from only two input images under large viewpoint changes. Existing regression-based methods lack the capacity to reconstruct unseen regions, while camera-guided diffusion models often deviate from intended trajectories due to noisy point cloud projections or insufficient conditioning from camera poses. To address these issues, we propose ConfCtrl, a confidence-aware video interpolation framework that enables diffusion models to follow prescribed camera poses while completing unseen regions. ConfCtrl initializes the diffusion process by combining a confidence-weighted projected point cloud latent with noise as the conditioning input. It then applies a Kalman-inspired predict-update mechanism, treating the projected point cloud as a noisy measurement and using learned residual corrections to balance pose-driven predictions with noisy geometric observations. This allows the model to rely on reliable projections while down-weighting uncertain regions, yielding stable, geometry-aware generation. Experiments on multiple datasets show that ConfCtrl produces geometrically consistent and visually plausible novel views, effectively reconstructing occluded regions under large viewpoint changes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09819 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation Yang, Liudi Eskandar, George Shen, Fengyi Altillawi, Mohammad Bai, Yang Zhang, Chi Liu, Ziyuan Valada, Abhinav Computer Vision and Pattern Recognition We address the challenge of novel view synthesis from only two input images under large viewpoint changes. Existing regression-based methods lack the capacity to reconstruct unseen regions, while camera-guided diffusion models often deviate from intended trajectories due to noisy point cloud projections or insufficient conditioning from camera poses. To address these issues, we propose ConfCtrl, a confidence-aware video interpolation framework that enables diffusion models to follow prescribed camera poses while completing unseen regions. ConfCtrl initializes the diffusion process by combining a confidence-weighted projected point cloud latent with noise as the conditioning input. It then applies a Kalman-inspired predict-update mechanism, treating the projected point cloud as a noisy measurement and using learned residual corrections to balance pose-driven predictions with noisy geometric observations. This allows the model to rely on reliable projections while down-weighting uncertain regions, yielding stable, geometry-aware generation. Experiments on multiple datasets show that ConfCtrl produces geometrically consistent and visually plausible novel views, effectively reconstructing occluded regions under large viewpoint changes. |
| title | ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.09819 |