LeGS turns density control in 3D Gaussian Splatting into a learnable RL policy whose reward is derived from a closed-form sensitivity analysis that measures each Gaussian's marginal contribution to reconstruction quality.
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
PULSE stabilizes mmWave human pose estimation by screening Doppler motion prompts before injecting them into spatial magnitude reasoning.
GADA corrects spatial misalignments in warped images for Gaussian Splatting via iterative deformable offsets and confidence-weighted fusion, yielding higher quality and 2.13x faster FPS than prior warping methods.
citing papers explorer
-
Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
LeGS turns density control in 3D Gaussian Splatting into a learnable RL policy whose reward is derived from a closed-form sensitivity analysis that measures each Gaussian's marginal contribution to reconstruction quality.
-
GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting
GADA corrects spatial misalignments in warped images for Gaussian Splatting via iterative deformable offsets and confidence-weighted fusion, yielding higher quality and 2.13x faster FPS than prior warping methods.