pith. sign in

Scenenet rgb-d: Can 5m synthetic images beat generic imagenet pre-training on indoor segmentation? InInt

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Geometric Context Transformer for Streaming 3D Reconstruction

cs.CV · 2026-04-15 · unverdicted · novelty 6.0

LingBot-Map is a streaming 3D reconstruction model built on a geometric context transformer that combines anchor context, pose-reference window, and trajectory memory to deliver accurate, drift-resistant results at 20 FPS over sequences longer than 10,000 frames.

citing papers explorer

Showing 1 of 1 citing paper.

  • Geometric Context Transformer for Streaming 3D Reconstruction cs.CV · 2026-04-15 · unverdicted · none · ref 43

    LingBot-Map is a streaming 3D reconstruction model built on a geometric context transformer that combines anchor context, pose-reference window, and trajectory memory to deliver accurate, drift-resistant results at 20 FPS over sequences longer than 10,000 frames.