9 papers
Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models
Emilien Seiler, Nicolas Talabot, Yingxuan You +2
Optimizing 3D shapes within the latent spaces of deep generative models is fundamental to computer assisted engineering, yet remains prone to a critical failure mode we term manifo…
End-to-End 4D Heart Mesh Recovery Across Full-Stack and Sparse Cardiac MRI
Yihong Chen, Jiancheng Yang, Deniz Sayin Mercadier +3
Reconstructing cardiac motion from CMR sequences is critical for diagnosis, prognosis, and intervention. Existing methods rely on complete CMR stacks to infer full heart motion, li…
S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
Deniz Sayin Mercadier, Federico Stella, Aurel Bizeau +2
Compositional implicit surface representations model scenes as collections of objects, each encoded by a Signed Distance Field (SDF). A fundamental limitation of this approach is t…
Limited-Angle Tomography Reconstruction via Projector Guided 3D Diffusion
Zhantao Deng, Mériem Er-Rafik, Anna Sushko +2
Limited-angle electron tomography aims to reconstruct 3D shapes from 2D projections of Transmission Electron Microscopy (TEM) within a restricted range and number of tilting angles…
PhysGen: Physically Grounded 3D Shape Generation for Industrial Design
Yingxuan You, Chen Zhao, Hantao Zhang +2
Existing generative models for 3D shapes can synthesize high-fidelity and visually plausible shapes. For certain classes of shapes that have undergone an engineering design process…
PrIntMesh: Precise Intersection Surfaces for 3D Organ Mesh Reconstruction
Deniz Sayin Mercadier, Hieu Le, Yihong Chen +3
Human organs are composed of interconnected substructures whose geometry and spatial relationships constrain one another. Yet, most deep-learning approaches treat these parts indep…