Gradient-Weighted Feature Back-Projection: A Fast Alternative to Feature Distillation in 3D Gaussian Splatting
This provides a fast and scalable solution for 3D segmentation tasks in computer vision, though it is incremental as it builds on existing Gaussian splatting techniques.
The paper tackles the problem of feature field rendering in 3D Gaussian splatting by introducing a training-free method that back-projects 2D features into pre-trained 3D Gaussians, achieving high-quality results in both 2D and 3D segmentation with fast and scalable performance comparable to training-based methods.
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.