arXiv subjects

Yuki Ono

Publications and source records attributed to Yuki Ono.

6 recordsLinked to original sources

arXiv2026

Solv3R: 3D Looped Transformer as a Multi-view Solver

Classical structure-from-motion reconstruction proceeds iteratively, refining camera poses and scene geometry from a current estimate. This allows maps to easily expand without recomputing already computed views, or geometry estimates to improve as more observations are provided. Most geometric foundation models, however, predict entire geometry in a single forward pass or update a recurrent state as frames arrive sequentially, making this expansion and refinement non-trivial. We introduce Solv3R, a looped transformer that learns to continue solving multi-view geometry from its current state. Importantly, its update operator is independent of the iteration count, allowing previously refined and newly introduced views to be jointly updated regardless of how ``solved'' they are. We train the operator to preserve accurate reconstructions under continued iteration and correct inaccurate states, enabling refinement of fixed image collections and integration of new observations. Representations of solved views can also be cached once and reused as geometric context across iterations, enabling compact and efficient key-value caching. We analyze the solver dynamics and compare it with the state-of-the-art, demonstrating that a single learned solver supports offline reconstruction, incremental reconstruction, relocalization, and streaming without task-specific training or modules. The code and models will be made publicly available at https://ubc-vision.github.io/solv3r/.

cs.CV↗

arXiv2026

DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models

Foundational visual features such as DINO have played a critical role across modern computer vision, and have recently become key components in multi-view feed-forward geometry estimators. In this work, we demonstrate that by re-distilling these multi-view models---their internal knowledge of 3D geometry---into a single-view estimator, we can obtain enhanced 3D consistent foundational features. Our key idea is to construct a multi-view teacher by fusing pretrained 2D foundation features with multi-view geometric features, and refining the fused representation with a discriminative ranking objective. Through our discriminative distillation framework, we enforce the learned features to be both 3D consistent and locally distinctive, while keeping them aligned with the feature space of the original foundation model to preserve the semantic structure of the pretrained representation. Consistency and local discriminability are critical for 3D computer vision problems such as forming semantic and geometric correspondences across images. To demonstrate the effectiveness of our method, we perform comprehensive experiments spanning multiple angles: direct feature analysis, dense prediction transfer, and explicit 3D lifting and rendering. Across these evaluations, our method consistently produces stronger 3D-aware foundation features that improve multi-view consistency and local discriminability while preserving the semantic transferability of the original representation.

cs.CV↗

arXiv2026

Directional Hydrogen Migration in Acetonitrile Dication in Asymmetric Ultrashort Intense Laser Fields

We investigate intramolecular hydrogen migration in acetonitrile dication in phase-controlled $ω$-$2ω$ intense laser fields (800 and 400 nm, 3.3$\times$10$^{14}$ W/cm$^2$) using three-dimensional coincidence ion momentum imaging. The two-body Coulomb explosion pathway, CH$_3$CN$^{2+}$ $\rightarrow$ CH$_3^+$ + CN$^+$, exhibits a clear phase-dependent fragment asymmetry along the laser polarization direction, showing that the tunnel ionization preferentially prepares the acetonitrile dication with the methyl group pointing toward the smaller amplitude side of the laser electric fields. The Coulomb explosion pathway occurring after the migration of a single hydrogen atom, CH$_3$CN$^{2+}$ $\rightarrow$ CH$_2^+$ + HCN$^+$, shows a pronounced reduction in the fragment asymmetry. A clear deuteration effect observed for the asymmetry of the hydrogen-migration pathway suggests that the two-color asymmetric laser field has a significant impact on directionality of intramolecular hydrogen migration in acetonitrile dication.

physics.atom-ph↗

arXiv2026

Photoelectron spectroscopy of 3s3p doubly excited helium dressed with strong near-infrared laser fields

We report time-resolved photoelectron spectroscopy of the $3s3p$ doubly excited states of helium dressed by an intense near-infrared (NIR) laser field. Using synchronized XUV free-electron-laser and 800-nm NIR laser pulses, we observe a pronounced delay-dependent shift of resonance-related spectral minima together with the emergence of additional structures around the NIR sideband energy. \textit{Ab initio} theoretical calculations support these observations and identify the features as signatures of NIR-induced coupling of the bright ($3s3p {}^{1}P^{o}$) autoionizing state to nearby dark ($^{1}D^{e}$ and $^{1}S^{e}$) resonances below the $N = 3$ threshold. A multichannel Fano resonance analysis of the measured spectra yields delay-dependent line-shape parameters and resonance energies, establishing a quantitative route to characterize and control correlated two-electron resonances in strong laser fields.

physics.atom-ph↗

arXiv2018

LF-Net: Learning Local Features from Images

We present a novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision. To do so we exploit depth and relative camera pose cues to create a virtual target that the network should achieve on one image, provided the outputs of the network for the other image. While this process is inherently non-differentiable, we show that we can optimize the network in a two-branch setup by confining it to one branch, while preserving differentiability in the other. We train our method on both indoor and outdoor datasets, with depth data from 3D sensors for the former, and depth estimates from an off-the-shelf Structure-from-Motion solution for the latter. Our models outperform the state of the art on sparse feature matching on both datasets, while running at 60+ fps for QVGA images.

cs.CV↗

arXiv2018

Learning to Find Good Correspondences

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outliers, while simultaneously using them to recover the relative pose, as encoded by the essential matrix. Our architecture is based on a multi-layer perceptron operating on pixel coordinates rather than directly on the image, and is thus simple and small. We introduce a novel normalization technique, called Context Normalization, which allows us to process each data point separately while imbuing it with global information, and also makes the network invariant to the order of the correspondences. Our experiments on multiple challenging datasets demonstrate that our method is able to drastically improve the state of the art with little training data.

cs.CV↗