Neural Image Space Tessellation

TL;DR

Neural Image-Space Tessellation (NIST) introduces a novel post-processing method that simulates tessellated geometry effects in real-time rendering without modifying original meshes, using neural techniques for silhouette refinement.

Contribution

NIST is the first to reformulate tessellation as a screen-space neural post-processing operation, enabling efficient, geometry-independent visual effects.

Findings

Produces smooth, coherent silhouettes comparable to geometric tessellation

Operates with constant per-frame cost independent of geometric complexity

Suitable for large-scale real-time rendering scenarios

Abstract

We present Neural Image-Space Tessellation (NIST), a lightweight screen-space post-processing approach that produces the visual effect of tessellated geometry while rendering only the original low-polygon meshes. Inspired by our observation from Phong tessellation, NIST leverages the discrepancy between geometric normals and shading normals as a minimal, view-dependent cue for silhouette refinement. At its core, NIST performs multi-scale neural tessellation by progressively deforming image-space contours with convolutional operators, while jointly reassigning appearance information through an implicit warping mechanism to preserve texture coherence and visual fidelity. Experiments demonstrate that our approach produces smooth, visually coherent silhouettes comparable to geometric tessellation, while incurring a constant per-frame cost and fully decoupled from geometric complexity, making it well-suited for large-scale real-time rendering scenarios. To the best of our knowledge, our NIST is the first work to reformulate tessellation as a post-processing operation, shifting it from a pre-rendering geometry pipeline to a screen space neural post-processing stage.