Shape: A Self-Supervised 3D Geometry Foundation Model for Industrial CAD Analysis

• URL: http://arxiv.org/abs/2604.22826v1
• Date: Sun, 19 Apr 2026 11:59:36 GMT
• Title: Shape: A Self-Supervised 3D Geometry Foundation Model for Industrial CAD Analysis
• Abstract summary: Industrial CAD require robust, generalizable 3D representations supporting accuracy and explainability.<n>We introduce Shape, a self-supervised foundation model converting surface meshes into dense per-token embeddings.
• Score: 0.19116784879310025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Industrial CAD workflows require robust, generalizable 3D geometric representations supporting accuracy and explainability. We introduce Shape, a self-supervised foundation model converting surface meshes into dense per-token embeddings. Shape combines a structured 3D latent grid, a multi-scale geometry-aware tokenizer (MAGNO) with cross-attention, and a transformer processor using grouped-query attention and RMSNorm. A learned reconstruction prior enables per-region attribution for explainable predictions. Pretraining uses masked-token reconstruction of normalized geometry statistics and multi-resolution contrastive consistency. The 10.9M-parameter backbone is pretrained on 61,052 CAD meshes from Thingi10K, MFCAD, and Fusion360. On a held-out split of 2,983 meshes, Shape achieves reconstruction R2 = 0.729 and 98.1% top-1 retrieval under the Wang-Isola protocol, with near-zero reconstruction train/val gap (contrastive scores use a larger evaluation pool). A 2x2 ablation on loss type and target-space normalization shows per-dimension normalization is critical: without it, performance collapses (R2 < 0.14, top-1 < 88%); with it, both losses succeed (R2 > 0.70, top-1 > 96%). Smooth-L1 offers secondary stability. Code, embeddings, and an interactive demo are released at https://github.com/simd-ai/shape.

Related papers

• GATE-3D: Geometry-Aware Test-time Adaptive Reranking for Open-Set 3D Shape Retrieval [18.485032317867205]
  We propose a lightweight query-adaptive reranking method that incorporates geometry without retraining the retrieval backbone.<n>Gates-3D predicts how much a geometry-aware score should adjust the appearance-based ranking using features that capture disagreement between the two modalities.
  arXiv  Detail & Related papers  (2026-07-21T13:56:07Z)
• SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment [8.675679091961213]
  CAD-to-image alignment aims to estimate an object's 9D pose from a single RGB image.<n>Recent zero-shot methods use visual foundation models to match image regions to CAD models.<n>We introduce SUFLECA, a weakly-supervised framework for zero-shot CAD alignment.
  arXiv  Detail & Related papers  (2026-07-16T14:32:34Z)
• LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows [10.300202521638274]
  We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows impacts feed-forward 3D reconstruction.<n>We show that expanding the context window -- by substantially increasing the number of active object and image tokens -- remarkably narrows this gap and enables high-fidelity 3D object reconstruction and inverse rendering.
  arXiv  Detail & Related papers  (2026-04-06T21:21:12Z)
• CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validation [10.21291474099901]
  Existing methods for text-to-CAD generation either operate in a single pass with no geometric verification or rely on lossy visual feedback that cannot resolve dimensional errors.<n>We present CADSmith, a multi-agent pipeline that generates CadQuery code from natural language.<n>It then undergoes an iterative refinement process through two nested correction loops: an inner loop that resolves execution errors and an outer loop grounded in programmatic geometric validation.
  arXiv  Detail & Related papers  (2026-03-27T15:23:05Z)
• Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation [53.09168514034483]
  Bimanual manipulation requires policies that can reason about 3D geometry, anticipate how it evolves under action, and generate smooth, coordinated motions.<n>We propose a framework that builds bimanual manipulation directly on a pre-trained 3D geometric foundation model.<n>Our policy fuses geometry-aware latents, 2D semantic features, and proprioception into a unified state representation, and uses diffusion model to jointly predict a future action chunk and a future 3D latent that decodes into a dense pointmap.
  arXiv  Detail & Related papers  (2026-02-27T08:54:20Z)
• KaoLRM: Repurposing Pre-trained Large Reconstruction Models for Parametric 3D Face Reconstruction [51.67605823241639]
  KaoLRM re-targets the learned prior of the Large Reconstruction Model (LRM) for parametric 3D face reconstruction from single-view images.<n> Experiments on both controlled and in-the-wild benchmarks demonstrate that KaoLRM achieves superior reconstruction accuracy and cross-view consistency.
  arXiv  Detail & Related papers  (2026-01-19T05:36:59Z)
• Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface [49.742538510885]
  We propose Faithful Contouring, a voxelized representation that achieves near-lossless fidelity in 3D meshes.<n>The proposed method also shows flexibility and improvement for existing representation.
  arXiv  Detail & Related papers  (2025-11-06T03:56:12Z)
• GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image [11.612167656421079]
  Multi-modal large language models (MLLMs) still struggle with accurately inferring 3D geometry from 2D images.<n>We introduce GACO-CAD, a novel two-stage post-training framework.<n>Experiments on the DeepCAD and Fusion360 datasets show that GACO-CAD achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-10-20T04:57:20Z)
• Dens3R: A Foundation Model for 3D Geometry Prediction [44.13431776180547]
  Dens3R is a 3D foundation model designed for joint geometric dense prediction.<n>By integrating image-pair matching features with intrinsic invariance modeling, Dens3R accurately regresses multiple geometric quantities.
  arXiv  Detail & Related papers  (2025-07-22T07:22:30Z)
• DiMeR: Disentangled Mesh Reconstruction Model [29.827345186012558]
  DiMeR is a novel geometry-texture disentangled feed-forward model with 3D supervision for sparse-view mesh reconstruction.<n>We streamline the algorithm of mesh extraction by eliminating modules with low performance/cost ratios and redesigning regularization losses with 3D supervision.<n>Extensive experiments demonstrate that DiMeR generalises across sparse-view-, single-image-, and text-to-3D tasks, consistently outperforming baselines.
  arXiv  Detail & Related papers  (2025-04-24T15:39:20Z)
• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction [86.726941702182]
  We introduce geometric guidance into the reconstruction network PS-CAD. We provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces.
  arXiv  Detail & Related papers  (2024-05-24T03:43:55Z)
• Learning Deformable Tetrahedral Meshes for 3D Reconstruction [78.0514377738632]
  3D shape representations that accommodate learning-based 3D reconstruction are an open problem in machine learning and computer graphics. Previous work on neural 3D reconstruction demonstrated benefits, but also limitations, of point cloud, voxel, surface mesh, and implicit function representations. We introduce Deformable Tetrahedral Meshes (DefTet) as a particular parameterization that utilizes volumetric tetrahedral meshes for the reconstruction problem.
  arXiv  Detail & Related papers  (2020-11-03T02:57:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.