Neural Image Space Tessellation
This work addresses the challenge of efficient high-quality rendering for large-scale real-time scenarios, such as in games or simulations, by decoupling tessellation from geometric complexity, though it is incremental as it builds on existing screen-space and neural techniques.
The paper tackles the problem of achieving the visual effect of tessellated geometry in real-time rendering without increasing geometric complexity, by introducing Neural Image-Space Tessellation (NIST), a lightweight screen-space post-processing approach that produces smooth, visually coherent silhouettes comparable to geometric tessellation at a constant per-frame cost.
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.