SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction

arXiv:2607.04119 · cs.CV, cs.AI · Submitted 2026-07-05 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-07-05

Updated: 2026-09-24

Comments: Accepted to ICME 2026

Code: https://github.com/LukePhong/SOV-CAD

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 26× in this paper · explained in 2 episodes
• Embeddings — 12× in this paper · explained in 2 episodes
• Decision Transformer — 7× in this paper
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Latent Space — 4× in this paper · explained in 7 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Transformer Architecture — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition Conference — 2× in this paper
• Fidelity — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Reconstructing Computer-Aided Design — 2× in this paper
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Activation Function — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Hamming Distance — 1× in this paper · explained in 2 episodes
• Invalid Rate — 1× in this paper
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Vision Transformer (ViT) — 1× in this paper · explained in 2 episodes

Sources

• Wonder3D: Single Image to 3D using Cross-Domain Diffusion
• CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models