Latticethe structure behind the noise

Papers Digest Topics Selected Labs Collections FAQ

Created by Flynn Lachendro

Papers Digest Topics Labs Saved

Search

Search papers, labs, and topics across Lattice.

Built by Flynn Lachendro·𝕏 / Twitter·RSS··FAQ·Glossary·Privacy

Zexiang Xu | Lattice

Zexiang Xu

D GS and Softmax-GS decreases when more Gaussians are used, since

Papers on Lattice

1

Total citations

0

Topics

2

Publication activitypapers/week, last 8 weeks

Research focus

Computer Vision (1)Training Efficiency & Optimization (1)

Frequent co-authors

Chen Ziwen (1)Peng Wang (1)Hao Tan (1)Li Fuxin (1)

Papers (1)

Apr 30, 2026

Kck(∫2d ago·also × increase in training time, D GS and Softmax-GS decreases when more Gaussians are used, Oregon State

Softmax-GS: Generalized Gaussians Learning When to Blend or Bound

Stop those fuzzy edges: Softmax-GS brings crisp boundaries to 3D Gaussian Splatting by making Gaussians compete instead of just blending.

Chen Ziwen, Peng Wang, Hao Tan +2

Computer Vision Training Efficiency & Optimization