SATR: Zero-Shot Semantic Segmentation of 3D Shapes
This addresses the problem of segmenting 3D shapes without labeled data for researchers in computer vision, offering a novel approach but is incremental as it builds on existing 2D models.
The paper tackles zero-shot semantic segmentation of 3D shapes by leveraging 2D image recognition models, finding that zero-shot 2D object detectors outperform other methods, and achieves state-of-the-art performance with improvements of 1.3% to 5.2% average mIoU on benchmarks.
We explore the task of zero-shot semantic segmentation of 3D shapes by using large-scale off-the-shelf 2D image recognition models. Surprisingly, we find that modern zero-shot 2D object detectors are better suited for this task than contemporary text/image similarity predictors or even zero-shot 2D segmentation networks. Our key finding is that it is possible to extract accurate 3D segmentation maps from multi-view bounding box predictions by using the topological properties of the underlying surface. For this, we develop the Segmentation Assignment with Topological Reweighting (SATR) algorithm and evaluate it on ShapeNetPart and our proposed FAUST benchmarks. SATR achieves state-of-the-art performance and outperforms a baseline algorithm by 1.3% and 4% average mIoU on the FAUST coarse and fine-grained benchmarks, respectively, and by 5.2% average mIoU on the ShapeNetPart benchmark. Our source code and data will be publicly released. Project webpage: https://samir55.github.io/SATR/.