Fastcad: Real-time CAD Retrieval And Alignment From Scans And Videos

Abstract

Digitising the 3D world into a clean, CAD model-based representation has important applications for augmented reality and robotics. Current state-of-the-art methods are computationally intensive as they individually encode each detected object and optimise CAD alignments in a second stage. In this work, we propose FastCAD, a real-time method that simultaneously retrieves and aligns CAD models for all objects in a given scene. In contrast to previous works, we directly predict alignment parameters and shape embeddings. We achieve high-quality shape retrievals by learning CAD embeddings in a contrastive learning framework and distilling those into FastCAD. Our single-stage method accelerates the inference time by a factor of 50 compared to other methods operating on RGB-D scans while outperforming them on the challenging Scan2CAD alignment benchmark. Further, our approach collaborates seamlessly with online 3D reconstruction techniques. This enables the real-time generation of precise CA

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keylanger2024fastcad

Related papers

• ROCA: Robust CAD Model Retrieval And Alignment From A Single Image (2021)12.61
• Weakly-supervised End-to-end CAD Retrieval To Scan Objects (2022)0.00
• Mask2cad: 3D Shape Prediction By Learning To Segment And Retrieve (2020)12.87
• Joint Embedding Of 3D Scan And CAD Objects (2019)11.08
• 'cadsketchnet' -- An Annotated Sketch Dataset For 3D CAD Model Retrieval With Deep Neural Networks (2021)11.19
• Patch2cad: Patchwise Embedding Learning For In-the-wild Shape Retrieval From A Single Image (2021)10.85
• Self-supervised Graph Neural Network For Mechanical CAD Retrieval (2024)0.00
• OSCAR: Open-set CAD Retrieval From A Language Prompt And A Single Image (2026)0.00