Real-Time Human Frontal View Synthesis from a Single Image
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912968605696000 |
|---|---|
| author | Lin, Fangyu Hu, Yingdong Zhu, Lunjie Liu, Zhening Huang, Yushi Lin, Zehong Zhang, Jun |
| author_facet | Lin, Fangyu Hu, Yingdong Zhu, Lunjie Liu, Zhening Huang, Yushi Lin, Zehong Zhang, Jun |
| contents | Photorealistic human novel view synthesis from a single image is crucial for democratizing immersive 3D telepresence, eliminating the need for complex multi-camera setups. However, current rendering-centric methods prioritize visual fidelity over explicit geometric understanding and struggle with intricate regions like faces and hands, leading to temporal instability. Meanwhile, human-centric frameworks suffer from memory bottlenecks since they typically rely on an auxiliary model to provide informative structural priors for geometric modeling, which limits real-time performance. To address these challenges, we propose PrismMirror, a geometry-guided framework for instant frontal view synthesis from a single image. By avoiding external geometric modeling and focusing on frontal view synthesis, our model optimizes visual integrity for telepresence. Specifically, PrismMirror introduces a novel cascade learning strategy that enables coarse-to-fine geometric feature learning. It first directly learns coarse geometric features, such as SMPL-X meshes and point clouds, and then refines textures through rendering supervision. To achieve real-time efficiency, we distill this unified framework into a lightweight linear attention model. Notably, PrismMirror is the first monocular human frontal view synthesis model that achieves real-time inference at 24 FPS, significantly outperforming previous methods in both visual authenticity and structural accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15433 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Real-Time Human Frontal View Synthesis from a Single Image Lin, Fangyu Hu, Yingdong Zhu, Lunjie Liu, Zhening Huang, Yushi Lin, Zehong Zhang, Jun Computer Vision and Pattern Recognition Photorealistic human novel view synthesis from a single image is crucial for democratizing immersive 3D telepresence, eliminating the need for complex multi-camera setups. However, current rendering-centric methods prioritize visual fidelity over explicit geometric understanding and struggle with intricate regions like faces and hands, leading to temporal instability. Meanwhile, human-centric frameworks suffer from memory bottlenecks since they typically rely on an auxiliary model to provide informative structural priors for geometric modeling, which limits real-time performance. To address these challenges, we propose PrismMirror, a geometry-guided framework for instant frontal view synthesis from a single image. By avoiding external geometric modeling and focusing on frontal view synthesis, our model optimizes visual integrity for telepresence. Specifically, PrismMirror introduces a novel cascade learning strategy that enables coarse-to-fine geometric feature learning. It first directly learns coarse geometric features, such as SMPL-X meshes and point clouds, and then refines textures through rendering supervision. To achieve real-time efficiency, we distill this unified framework into a lightweight linear attention model. Notably, PrismMirror is the first monocular human frontal view synthesis model that achieves real-time inference at 24 FPS, significantly outperforming previous methods in both visual authenticity and structural accuracy. |
| title | Real-Time Human Frontal View Synthesis from a Single Image |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.15433 |