A meta-learned optimizer for 3DGS that extends the optimization horizon via checkpoint buffers and latent gradient-scale encoding, delivering better early novel-view quality and long-term stability with zero-shot generalization.
Gifsplat: Generative prior-guided iterative feed-forward 3d gaussian splatting from sparse views
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
AIR amortizes 2D Gaussian splatting into a self-supervised feed-forward network via residual stages, explicit stage control, and Predict-Optimize-Distill training.
citing papers explorer
-
Learn2Splat: Extending the Horizon of Learned 3DGS Optimization
A meta-learned optimizer for 3DGS that extends the optimization horizon via checkpoint buffers and latent gradient-scale encoding, delivering better early novel-view quality and long-term stability with zero-shot generalization.
-
AIR: Amortized Image Reconstruction Framework for Self-Supervised Feed-Forward 2D Gaussian Splatting
AIR amortizes 2D Gaussian splatting into a self-supervised feed-forward network via residual stages, explicit stage control, and Predict-Optimize-Distill training.