3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis
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_ | 1866910124705054720 |
|---|---|
| author | Schulz, Stefan Edelstein, Fernando Dröge, Hannah Hullin, Matthias B. Plack, Markus |
| author_facet | Schulz, Stefan Edelstein, Fernando Dröge, Hannah Hullin, Matthias B. Plack, Markus |
| contents | Real-time free-viewpoint rendering requires balancing multi-camera redundancy with the latency constraints of interactive applications. We address this challenge by combining lightweight geometry with learning and propose 3DTV, a feedforward network for real-time sparse-view interpolation. A Delaunay-based triplet selection ensures angular coverage for each target view. Building on this, we introduce a pose-aware depth module that estimates a coarse-to-fine depth pyramid, enabling efficient feature reprojection and occlusion-aware blending. Unlike methods that require scene-specific optimization, 3DTV runs feedforward without retraining, making it practical for AR/VR, telepresence, and interactive applications. Our experiments on challenging multi-view video datasets demonstrate that 3DTV consistently achieves a strong balance of quality and efficiency, outperforming recent real-time novel-view baselines. Crucially, 3DTV avoids explicit proxies, enabling robust rendering across diverse scenes. This makes it a practical solution for low-latency multi-view streaming and interactive rendering.
Project Page: https://stefanmschulz.github.io/3DTV_webpage/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11211 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | 3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis Schulz, Stefan Edelstein, Fernando Dröge, Hannah Hullin, Matthias B. Plack, Markus Computer Vision and Pattern Recognition Machine Learning Multimedia Real-time free-viewpoint rendering requires balancing multi-camera redundancy with the latency constraints of interactive applications. We address this challenge by combining lightweight geometry with learning and propose 3DTV, a feedforward network for real-time sparse-view interpolation. A Delaunay-based triplet selection ensures angular coverage for each target view. Building on this, we introduce a pose-aware depth module that estimates a coarse-to-fine depth pyramid, enabling efficient feature reprojection and occlusion-aware blending. Unlike methods that require scene-specific optimization, 3DTV runs feedforward without retraining, making it practical for AR/VR, telepresence, and interactive applications. Our experiments on challenging multi-view video datasets demonstrate that 3DTV consistently achieves a strong balance of quality and efficiency, outperforming recent real-time novel-view baselines. Crucially, 3DTV avoids explicit proxies, enabling robust rendering across diverse scenes. This makes it a practical solution for low-latency multi-view streaming and interactive rendering. Project Page: https://stefanmschulz.github.io/3DTV_webpage/ |
| title | 3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis |
| topic | Computer Vision and Pattern Recognition Machine Learning Multimedia |
| url | https://arxiv.org/abs/2604.11211 |