# 3D Reconstruction

Finger-movement labels in non-human primates have long come from instrumented manipulanda fitted with bend sensors, which cap the dimensionality of measurable movement. Freebie uses several synchronized cameras and real-time pose estimation to output finger keypoints directly, reaching median end-to-end latencies of 15.8 ms at 30 FPS and 16.2 ms at 60 FPS, with a median absolute correlation of 0.96 against bend-sensor signals. EMG decoders trained on Freebie labels matched those trained on bend-sensor labels in closed-loop control, indicating that training a decoder need not require instrumenting the hand.

Finger-movement labels in non-human primates have long come from instrumented manipulanda fitted with bend sensors, which cap the dimensionality of measurable movement. Freebie uses several synchronized cameras and real-time pose estimation to output finger keypoints directly, reaching median end-to-end latencies of 15.8 ms at 30 FPS and 16.2 ms at 60 FPS, with a median absolute correlation of 0.96 against bend-sensor signals. EMG decoders trained on Freebie labels matched those trained on bend-sensor labels in closed-loop control, indicating that training a decoder need not require instrumenting the hand.

Raysemble splits single-view bone reconstruction into shape and placement: it predicts each bone's shape on a normalized grid, then uses predicted depth and camera geometry to fix its center and scale in millimeters. On simulated frontal radiographs from 43 CT scans of 23 held-out patients, it averages 65.24% Dice, 9.09 mm HD95 and 3.32 mm ASSD before rigid alignment, leading 15 configurations; with identical inputs it beats VolumeNeRF by 5.86 Dice points.

Raysemble splits single-view bone reconstruction into shape and placement: it predicts each bone's shape on a normalized grid, then uses predicted depth and camera geometry to fix its center and scale in millimeters. On simulated frontal radiographs from 43 CT scans of 23 held-out patients, it averages 65.24% Dice, 9.09 mm HD95 and 3.32 mm ASSD before rigid alignment, leading 15 configurations; with identical inputs it beats VolumeNeRF by 5.86 Dice points.

Reconstructing a 3D surface from a single high-frequency fringe image is hard because long-range spatial consistency and fine geometric detail must both survive. Convolutional networks model long-range context weakly, and window-based Transformers build global interactions only gradually with depth. A hybrid Mamba-Transformer network adds visual state-space blocks at the intermediate-resolution encoder stage of a Swin-style U-shaped architecture, with an axial-dilated block that strengthens directional fringe features before selective scanning. On a public fringe-projection dataset, using only one deformed fringe image, it reaches 0.548 mm RMSE and 0.9985 SSIM, cutting RMSE by 65.2% and 59.6% relative to UHRNet and HiDNet.

Reconstructing a 3D surface from a single high-frequency fringe image is hard because long-range spatial consistency and fine geometric detail must both survive. Convolutional networks model long-range context weakly, and window-based Transformers build global interactions only gradually with depth. A hybrid Mamba-Transformer network adds visual state-space blocks at the intermediate-resolution encoder stage of a Swin-style U-shaped architecture, with an axial-dilated block that strengthens directional fringe features before selective scanning. On a public fringe-projection dataset, using only one deformed fringe image, it reaches 0.548 mm RMSE and 0.9985 SSIM, cutting RMSE by 65.2% and 59.6% relative to UHRNet and HiDNet.

Low texture, specular reflection and irregular morphology make external pose estimation such as COLMAP unreliable on bone surfaces, yet existing hyperspectral 3D reconstruction methods depend on such poses. BoNeRF-HS jointly optimizes camera intrinsics, per-view poses, volume density and the hyperspectral radiance field, and adds a gated spectral adapter head that learns a residual correction across neighbouring bands. On 45-view, 120-band, 400–1000 nm data from mouse bone, a trabecular bone analogue and a cortical bone analogue, it gives the highest PSNR and SSIM on all three specimens, with PSNR 29.94 and SSIM 0.9254 on mouse bone.

Low texture, specular reflection and irregular morphology make external pose estimation such as COLMAP unreliable on bone surfaces, yet existing hyperspectral 3D reconstruction methods depend on such poses. BoNeRF-HS jointly optimizes camera intrinsics, per-view poses, volume density and the hyperspectral radiance field, and adds a gated spectral adapter head that learns a residual correction across neighbouring bands. On 45-view, 120-band, 400–1000 nm data from mouse bone, a trabecular bone analogue and a cortical bone analogue, it gives the highest PSNR and SSIM on all three specimens, with PSNR 29.94 and SSIM 0.9254 on mouse bone.

Limited-angle atomic electron tomography leaves a missing wedge because specimens cannot be tilted far enough, degrading depth resolution and atomic localization. RESIRE-Net uses only the input dataset: it rotates the reconstructed volume, projects it at the experimental tilt angles, reconstructs each synthetic tilt series with RESIRE, and trains a 3D U-Net on the resulting pairs to approximate the inverse of the missing-wedge operator. On multislice-simulated metallic-glass and medium-entropy-alloy nanoparticles, 3D positional RMSD falls from 21 to 14 picometers and from 24 to 15 picometers, with atom recovery and elemental classification improving as well.

Limited-angle atomic electron tomography leaves a missing wedge because specimens cannot be tilted far enough, degrading depth resolution and atomic localization. RESIRE-Net uses only the input dataset: it rotates the reconstructed volume, projects it at the experimental tilt angles, reconstructs each synthetic tilt series with RESIRE, and trains a 3D U-Net on the resulting pairs to approximate the inverse of the missing-wedge operator. On multislice-simulated metallic-glass and medium-entropy-alloy nanoparticles, 3D positional RMSD falls from 21 to 14 picometers and from 24 to 15 picometers, with atom recovery and elemental classification improving as well.

Zebra3D swaps dense global attention in pretrained 3D reconstruction models for a per-layer mix of linear and tile-sparse attention, holding pose accuracy close to dense models at roughly 94% mean attention sparsity and reaching up to 5.6x end-to-end speedup at 1,024 views.

Zebra3D swaps dense global attention in pretrained 3D reconstruction models for a per-layer mix of linear and tile-sparse attention, holding pose accuracy close to dense models at roughly 94% mean attention sparsity and reaching up to 5.6x end-to-end speedup at 1,024 views.

Three-dimensional Gaussian reconstruction for building inspection no longer aims only at photorealistic views: with region and point-wise depth supervision, Gaussian centers are pulled toward physical surfaces, cutting depth error by 58.1% and 86.8% on synthetic UAV and smartphone-captured data, with a mean relative height-measurement error of 0.33%.

Three-dimensional Gaussian reconstruction for building inspection no longer aims only at photorealistic views: with region and point-wise depth supervision, Gaussian centers are pulled toward physical surfaces, cutting depth error by 58.1% and 86.8% on synthetic UAV and smartphone-captured data, with a mean relative height-measurement error of 0.33%.

The work introduces a flow-matching generative model that reconstructs the posterior distribution of 3D gas density fields from redshift-space galaxy density fields, conditioned on cosmological parameters, a minimum stellar mass threshold, and the baryon suppression power spectrum, and validates on CAMELS50 (IllustrisTNG) test boxes that the reconstructed dispersion measures agree with the truth both sightline by sightline and in overall distribution, with generalization to TNG300-1 at roughly 43 times the training volume.

The work introduces a flow-matching generative model that reconstructs the posterior distribution of 3D gas density fields from redshift-space galaxy density fields, conditioned on cosmological parameters, a minimum stellar mass threshold, and the baryon suppression power spectrum, and validates on CAMELS50 (IllustrisTNG) test boxes that the reconstructed dispersion measures agree with the truth both sightline by sightline and in overall distribution, with generalization to TNG300-1 at roughly 43 times the training volume.

LiteReality-Agent formulates reconstruction of interactable 3D indoor scenes from RGB-D scans as a coding problem: a coding agent gathers evidence with specialised tools and iteratively edits an executable Python script, within an observe-edit-verify harness covering evidence gathering, measurement, verification, layout optimisation, simulation readiness, and quality control, yielding digital twins reported as more geometrically accurate, visually realistic, and simulation-compatible than those from frontier models such as Astra and Fable.

LiteReality-Agent formulates reconstruction of interactable 3D indoor scenes from RGB-D scans as a coding problem: a coding agent gathers evidence with specialised tools and iteratively edits an executable Python script, within an observe-edit-verify harness covering evidence gathering, measurement, verification, layout optimisation, simulation readiness, and quality control, yielding digital twins reported as more geometrically accurate, visually realistic, and simulation-compatible than those from frontier models such as Astra and Fable.