Softmax-GS generalizes 3D Gaussians with learnable softmax competition in overlaps to enable a spectrum from blending to crisp edges while preserving order invariance and transmittance.
Optimization is run for 10K steps without opacity reset against the target image using default rendering losses
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Softmax-GS: Generalized Gaussians Learning When to Blend or Bound
Softmax-GS generalizes 3D Gaussians with learnable softmax competition in overlaps to enable a spectrum from blending to crisp edges while preserving order invariance and transmittance.