RGE-GS uses a learned pixel-wise reward filter and convergence-aware Gaussian training to improve cross-lane novel view synthesis for driving scenes.
Streetscapes: Large- scale consistent street view generation using autoregressive video diffusion
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 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors
RGE-GS uses a learned pixel-wise reward filter and convergence-aware Gaussian training to improve cross-lane novel view synthesis for driving scenes.