paper-with-me

홈 › Papers

Gradient-Weighted Feature Back-Projection: A Fast Alternative to Feature Distillation in 3D Gaussian Splatting

2024-11-19 · Joji Joseph, Bharadwaj Amrutur, Shalabh Bhatnagar

We introduce a training-free method for feature field rendering in Gaussian splatting. Our approach back-projects 2D features into pre-trained 3D Gaussians, using a weighted sum based on each Gaussian's influence in the final rendering. While most training-based feature field rendering methods excel at 2D segmentation but perform poorly at 3D segmentation without post-processing, our method achieves high-quality results in both 2D and 3D segmentation. Experimental results demonstrate that our approach is fast, scalable, and offers performance comparable to training-based methods.

📄 PDF Abstract BibTeX arXiv:2411.15193

Code (1)

JojiJoseph/3dgs-gradient-backprojection 공식 구현 pytorch

Tasks

Segmentation

Similar Papers 제목 키워드 기반

Efficient Projection Algorithms onto the Weighted l1 Ball

2020-09-07 · Guillaume Perez, Sebastian Ament, Carla Gomes, Michel Barlaud

Projected gradient descent has been proved efficient in many optimization and machine learning problems. The weighted $\ell_1$ ball has been shown effective in sparse system identification and features selection. In this…

BIG-bench Machine Learningfeature selection

The Ordered Weighted $\ell_1$ Norm: Atomic Formulation, Projections, and Algorithms

2014-09-15 · Xiangrong Zeng, Mário A. T. Figueiredo

The ordered weighted $\ell_1$ norm (OWL) was recently proposed, with two different motivations: its good statistical properties as a sparsity promoting regularizer; the fact that it generalizes the so-called {\it octagon…

Clusteringregression

Weighted structure tensor total variation for image denoising

2023-06-18 · Xiuhan Sheng, Lijuan Yang, Jingya Chang

For image denoising problems, the structure tensor total variation (STV)-based models show good performances when compared with other competing regularization approaches. However, the STV regularizer does not couple the …

DenoisingImage Denoising

Contextual Directed Acyclic Graphs

2023-10-24 · Ryan Thompson, Edwin V. Bonilla, Robert Kohn

Estimating the structure of directed acyclic graphs (DAGs) from observational data remains a significant challenge in machine learning. Most research in this area concentrates on learning a single DAG for the entire popu…

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime

2025-04-25 · Raphaël Barboni, Gabriel Peyré, François-Xavier Vialard

We study the convergence of gradient methods for the training of mean-field single hidden layer neural networks with square loss. Observing this is a separable non-linear least-square problem which is linear w.r.t. the o…