Merge pull request #328 from RohanChacko/main

Adding Lifting by Gaussians: A Simple, Fast and Flexible Method for 3D Instance Segmentation

awesome_3dgs_papers.yaml

@@ -1,3 +1,36 @@
+- id: chacko2025lifting
+  title: 'Lifting by Gaussians: A Simple, Fast and Flexible Method for 3D Instance
+    Segmentation'
+  authors: Rohan Chacko, Nicolai Haeni, Eldar Khaliullin, Lin Sun, Douglas Lee
+  year: '2025'
+  abstract: 'We introduce Lifting By Gaussians (LBG), a novel approach for open-world
+    instance segmentation of 3D Gaussian Splatted Radiance Fields (3DGS). Recently,
+    3DGS Fields have emerged as a highly efficient and explicit alternative to Neural
+    Field-based methods for high-quality Novel View Synthesis. Our 3D instance segmentation
+    method directly lifts 2D segmentation masks from SAM (alternately FastSAM, etc.),
+    together with features from CLIP and DINOv2, directly fusing them onto 3DGS (or
+    similar Gaussian radiance fields such as 2DGS). Unlike previous approaches, LBG
+    requires no per-scene training, allowing it to operate seamlessly on any existing
+    3DGS reconstruction. Our approach is not only an order of magnitude faster and
+    simpler than existing approaches; it is also highly modular, enabling 3D semantic
+    segmentation of existing 3DGS fields without requiring a specific parametrization
+    of the 3D Gaussians. Furthermore, our technique achieves superior semantic segmentation
+    for 2D semantic novel view synthesis and 3D asset extraction results while maintaining
+    flexibility and efficiency. We further introduce a novel approach to evaluate
+    individually segmented 3D assets from 3D radiance field segmentation methods.
+
+    '
+  project_page: null
+  paper: https://arxiv.org/pdf/2502.00173.pdf
+  code: null
+  video: null
+  tags:
+  - Language Embedding
+  - Segmentation
+  - Virtual Reality
+  thumbnail: assets/thumbnails/chacko2025lifting.jpg
+  publication_date: '2025-01-31T21:30:59+00:00'
+  date_source: arxiv
 - id: lin2025diffsplat
   title: 'DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat
     Generation'