pith. sign in

Direct3d-s2: Gigascale 3d generation made easy with spatial sparse attention, 2025

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Repurposing 3D Generative Model for Autoregressive Layout Generation

cs.CV · 2026-04-17 · unverdicted · novelty 6.0

LaviGen turns 3D generative models into an autoregressive layout generator that models geometric and physical constraints, delivering 19% higher physical plausibility and 65% faster inference on the LayoutVLM benchmark.

SegviGen: Repurposing 3D Generative Model for Part Segmentation

cs.CV · 2026-03-17 · unverdicted · novelty 6.0

SegviGen shows pretrained 3D generative models can be repurposed for part segmentation via voxel colorization, beating prior methods by 40% interactively and 15% on full segmentation using only 0.32% of labeled data.

citing papers explorer

Showing 2 of 2 citing papers.

  • Repurposing 3D Generative Model for Autoregressive Layout Generation cs.CV · 2026-04-17 · unverdicted · none · ref 87

    LaviGen turns 3D generative models into an autoregressive layout generator that models geometric and physical constraints, delivering 19% higher physical plausibility and 65% faster inference on the LayoutVLM benchmark.

  • SegviGen: Repurposing 3D Generative Model for Part Segmentation cs.CV · 2026-03-17 · unverdicted · none · ref 70

    SegviGen shows pretrained 3D generative models can be repurposed for part segmentation via voxel colorization, beating prior methods by 40% interactively and 15% on full segmentation using only 0.32% of labeled data.