{"slug": "meshfm-2d-features-are-all-you-need-for-3d-shape-understanding", "title": "MeshFM: 2D Features Are All You Need for 3D Shape Understanding", "summary": "Researchers introduced MeshFM, a feedforward framework that distills 2D features from visual foundation models into 3D, enabling rich 3D shape understanding without 3D annotations. The method, which uses a two-stage training strategy, performs on par with 3D-supervised methods on tasks like part segmentation, dense correspondence, and mesh deformation, and is robust to extreme rotations.", "body_md": "arXiv:2607.27592v1 Announce Type: new\nAbstract: We present MeshFM, an efficient feedforward framework for extracting rich features from 3D inputs. Our method distills 2D features from visual foundation models into 3D. We train a feedforward network to directly predict 3D features without requiring optimization during inference. The approach utilizes a two-stage training strategy. First, we optimize a feature field in 3D using only 2D feature supervision. Second, we train a network to regress this feature field. The entire procedure requires no 3D annotation, instead relying on the powerful information in 2D foundation models. We demonstrate that our learned features can be immediately applied to downstream tasks, including part segmentation, dense correspondence, and mesh deformation. Extensive experiments show that MeshFM, trained solely with 2D supervision, performs on par with methods trained explicitly with 3D supervision, even without task-specific fine-tuning. Moreover, our model is trained to be robust to extreme rotations of the input objects. Project page: https://threedle.github.io/MeshFM/", "url": "https://wpnews.pro/news/meshfm-2d-features-are-all-you-need-for-3d-shape-understanding", "canonical_source": "https://arxiv.org/abs/2607.27592", "published_at": "2026-07-31 04:00:00+00:00", "updated_at": "2026-07-31 04:39:41.287496+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "computer-vision"], "entities": ["MeshFM", "arXiv", "Threedle"], "alternates": {"html": "https://wpnews.pro/news/meshfm-2d-features-are-all-you-need-for-3d-shape-understanding", "markdown": "https://wpnews.pro/news/meshfm-2d-features-are-all-you-need-for-3d-shape-understanding.md", "text": "https://wpnews.pro/news/meshfm-2d-features-are-all-you-need-for-3d-shape-understanding.txt", "jsonld": "https://wpnews.pro/news/meshfm-2d-features-are-all-you-need-for-3d-shape-understanding.jsonld"}}