Skip to main content
Search

# Implicit Neural Representation

4 related articles

Subscribe to updates
  1. arXiv

    Elastic full-waveform inversion gets a neural field: on Marmousi, Vp MAE falls from 412.02 to 216.90 with fewer crosstalk artifacts

    Multiparameter elastic full-waveform inversion estimates several elastic properties at once, and crosstalk between them leaves artifacts in the recovered models. INR-EFWI replaces independent grid-point values with a coordinate neural network that generates the subsurface model continuously, and pairs it with a Vp, P-wave impedance Ip and Vs/Vp parameterization whose radiation patterns overlap less. On the Marmousi and Overthrust synthetic models and the Volve ocean-bottom dataset, it yields lower model error and better structural continuity than automatic-differentiation EFWI, though the authors stress that this parameterization is not universally optimal.

  2. A preoperative clue for pediatric Wilms tumor subtypes: D* separates stromal from epithelial, mixed and regressive slices

    Pediatric Wilms tumor is treated with preoperative chemotherapy under the SIOP-RTSG 2016 UMBRELLA protocol, and histological subtyping comes only after surgery, leaving no reliable preoperative marker. A retrospective study fitted intravoxel incoherent motion imaging with implicit neural representations and used patient-specific 3D-printed cutting guides to align MRI slices with histopathology slices, comparing parameters across subtypes in 94 slices from 30 lesions. Median D* was significantly higher in stromal than in epithelial, mixed and regressive slices, while D, f and ADC showed no significant differences between subtypes.

  3. arXiv

    OX-NeRF attains the highest 3D reconstruction accuracy on ultra-sparse X-ray scenes with four to ten projections

    The authors present OX-NeRF, which fuses a cross-scene convolutional encoder with a per-scene multi-resolution hash grid into an MLP and optimises them jointly by self-supervision, achieving higher 3D reconstruction accuracy than existing self-supervised radiance field methods on parallel-beam and cone-beam X-ray datasets in the ultra-sparse regime of four to ten projections.

  4. arXiv

    A low-rank constraint turns the ultrasound video latent space into a readable cardiac-cycle trajectory, giving ED/ES frames without extra training

    The work introduces LRM-Functa, which imposes a low-rank constraint on the time-resolved modulation vectors of VidFuncta (mt = v + Bβϕt), so that the latent space of cardiac ultrasound videos forms periodic spiral trajectories; this allows direct readout of end-diastolic (ED) and end-systolic (ES) frames without additional model training, keeps stable reconstruction and ejection-fraction prediction at the extremely low rank k = 2 on EchoNet-Dynamic, and generalizes to a POCUS cardiac view and to lung-ultrasound B-line classification.

You’re all caught up