Learn2Splat: Extending the Horizon of Learned 3DGS Optimization

arXiv:2605.15760 · cs.CV · Submitted 2026-05-15 · Read on arXiv

cs.CV

Submitted: 2026-05-15

Updated: 2026-09-23

Project page: https://naamapearl.github.io/learn2splat

Terminology

• Adam — 89× in this paper · explained in 2 episodes
• Learned Optimizer — 65× in this paper
• Gaussian Splatting — 19× in this paper · explained in 4 episodes
• Meta-learning — 15× in this paper · explained in 2 episodes
• 3D Gaussian Splatting — 13× in this paper · explained in 2 episodes
• Generalization — 12× in this paper · explained in 13 episodes
• Transformer — 10× in this paper · explained in 2 episodes
• Zero-Shot Generalization — 10× in this paper · explained in 5 episodes
• Computer Vision and Pattern Recognition — 5× in this paper
• 3D Gaussian Splatting (3DGS) — 4× in this paper · explained in 4 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Point Clouds — 3× in this paper · explained in 2 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Unified Framework — 3× in this paper · explained in 5 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Data Augmentation — 2× in this paper · explained in 7 episodes
• Gradient Flow — 2× in this paper · explained in 2 episodes
• Journal of Machine Learning Research — 2× in this paper
• Pruning — 2× in this paper · explained in 4 episodes
• alpha — 2× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes

Sources

• GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views
• RealLiFe: Real-Time Light Field Reconstruction via Hierarchical Sparse Gradient Descent
• EDGS: Eliminating Densification for Efficient Convergence of 3DGS
• WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
• VeLO: Training Versatile Learned Optimizers by Scaling Up
• Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves
• ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
• VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
• ReSplat: Learning Recurrent Gaussian Splatting

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models