LUDVIG: Learning-free Uplifting of 2D Visual Features to Gaussian Splatting Scenes
Keywords: 3D vision, vision foundation models, graph diffusion
TL;DR: A simple and effective technique for uplifting 2D visual features to 3D Gaussian Splatting scenes
Abstract: We address the problem of extending the capabilities of vision foundation models
such as DINO, SAM, and CLIP, to 3D tasks. Specifically, we introduce a novel
method to uplift 2D image features into 3D Gaussian Splatting scenes. Unlike traditional approaches that rely on minimizing a reconstruction
loss, our method employs a simpler and more efficient feature aggregation
technique, augmented by a graph diffusion mechanism. Graph diffusion
enriches features from a given model, such as CLIP, by leveraging pairwise
similarities that encode 3D geometry or similarities induced by another embedding
like DINOv2. Our approach achieves performance comparable to the state of
the art on multiple downstream tasks while delivering significant speed-ups.
Notably, we obtain competitive segmentation results using generic
DINOv2 features, despite DINOv2 not being trained on millions of
annotated segmentation masks like SAM. When applied to CLIP
features, our method demonstrates strong performance in open-vocabulary,
language-based object detection tasks, highlighting the versatility of our
approach.
Supplementary Material: zip
Primary Area: foundation or frontier models, including LLMs
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 199
Loading