AI TrackerFrontier desk · AEST
Back to news
normalai

SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation

arXiv cs.AI · 2 Oct 2026, 03:59 AEST

High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry. While effective, this design fragments continuous surfaces into many local tokens, inflates generation cost, and often weakens topological consistency for thin or highly connected shapes.

Key facts

Read aloud

High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry. While effective, this design fragments continuous surfaces into many local tokens, inflates generation cost, and often weakens topological consistency for thin or highly connected shapes. High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry. While effective, this design fragments continuous surfaces into many local tokens, inflates generation cost, and often weakens topological consistency for thin or highly connected shapes. We introduce SILSA, a topology-aware 3D generation framework that represents shapes with compact sliding-window slice latents. Instead of generating expensive voxel tokens, SILSA uses a fixed set of overlapping slices along the three canonical axes, where each token summarizes a local depth window to preserve cross-sectional continuity and. A Slice VAE encodes oriented surface samples into multi-axis slice latents and reconstructs them with a sparse volumetric decoder, while a Volumetric Anchor Lattice coordinates directional slice streams through a.

Sources in this cluster