Neural Image Space Tessellation efect
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_ | 1866910262626353152 |
|---|---|
| author | Du, Youyang Zhu, Junqiu Zeng, Zheng Wang, Lu Yan, Lingqi |
| author_facet | Du, Youyang Zhu, Junqiu Zeng, Zheng Wang, Lu Yan, Lingqi |
| contents | We present Neural Image Space Tessellation effect (NIST), a lightweight screen-space post-processing approach for reducing the faceted silhouettes of low-poly renderings. Instead of tessellating primitives, creating new geometry, or modifying the underlying mesh, NIST uses the low-poly rendering result together with simple auxiliary G-buffer attributes to learn geometry-guided smoothing of object contours in image space. At its core, NIST first deforms image-space contours implicitly and then learns to reassign appearance in the whole image-space, including the deformed regions, preserving texture continuity and avoiding seam artifacts. Experiments show that NIST reduces visually apparent geometric faceting and produces smooth, coherent silhouettes close to tessellation-based smoothing references, with a nearly constant per-frame cost in our tested settings. To the best of our knowledge, NIST is the first work to move the solution of low-poly silhouette faceting from the pre-rendering geometry stage to a post-rendering screen-space stage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23754 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Neural Image Space Tessellation efect Du, Youyang Zhu, Junqiu Zeng, Zheng Wang, Lu Yan, Lingqi Graphics Computer Vision and Pattern Recognition We present Neural Image Space Tessellation effect (NIST), a lightweight screen-space post-processing approach for reducing the faceted silhouettes of low-poly renderings. Instead of tessellating primitives, creating new geometry, or modifying the underlying mesh, NIST uses the low-poly rendering result together with simple auxiliary G-buffer attributes to learn geometry-guided smoothing of object contours in image space. At its core, NIST first deforms image-space contours implicitly and then learns to reassign appearance in the whole image-space, including the deformed regions, preserving texture continuity and avoiding seam artifacts. Experiments show that NIST reduces visually apparent geometric faceting and produces smooth, coherent silhouettes close to tessellation-based smoothing references, with a nearly constant per-frame cost in our tested settings. To the best of our knowledge, NIST is the first work to move the solution of low-poly silhouette faceting from the pre-rendering geometry stage to a post-rendering screen-space stage. |
| title | Neural Image Space Tessellation efect |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.23754 |