Pith. sign in

The lov ´asz-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks

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

background 1

representative citing papers

GaussRender: Learning 3D Occupancy with Gaussian Rendering

cs.CV · 2025-02-07 · conditional · novelty 6.0

A plug-and-play Gaussian-splatting rendering loss that supervises 3D occupancy predictions through 2D depth and semantic images improves geometric fidelity and surface-sensitive metrics across multiple models and benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • GaussRender: Learning 3D Occupancy with Gaussian Rendering cs.CV · 2025-02-07 · conditional · none · ref 2

    A plug-and-play Gaussian-splatting rendering loss that supervises 3D occupancy predictions through 2D depth and semantic images improves geometric fidelity and surface-sensitive metrics across multiple models and benchmarks.