Pith. sign in

Lift, splat, shoot: Encod- ing images from arbitrary camera rigs by implicitly unpro- jecting to 3d

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

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Semantic Causality-Aware Vision-Based 3D Occupancy Prediction

cs.CV · 2025-09-10 · conditional · novelty 6.0

A class-conditional gradient loss (Causal Loss) plus channel-grouped lifting, learnable camera offsets, and normalized convolution raises Occ3D mIoU by 1.2/0.8 points and cuts the camera-noise mIoU drop from 32% to 7%.

citing papers explorer

Showing 1 of 1 citing paper.

  • Semantic Causality-Aware Vision-Based 3D Occupancy Prediction cs.CV · 2025-09-10 · conditional · none · ref 38

    A class-conditional gradient loss (Causal Loss) plus channel-grouped lifting, learnable camera offsets, and normalized convolution raises Occ3D mIoU by 1.2/0.8 points and cuts the camera-noise mIoU drop from 32% to 7%.