arXiv subjects

Yasuyuki Matsushita

Publications and source records attributed to Yasuyuki Matsushita.

At least 19 recordsLinked to original sources

arXiv2026

ESP: Energy-Score Policy for One-Step Multimodal Action Generation

Generative action models based on diffusion and flow matching have been increasingly adopted in vision-language-action (VLA) policies for their ability to capture diverse behaviors, including multiple valid action sequences under the same observation and instruction. Their iterative sampling procedures, however, require repeated network evaluations to generate each action chunk, increasing inference latency in closed-loop control. We propose ESP (Energy-Score Policy), a teacher-free approach that maps policy context and noise directly to an action chunk in a single network evaluation. ESP trains the action head with the energy score rather than mean squared error. Whereas squared-error regression targets the conditional mean, the energy score is strictly proper: its expected value is uniquely minimized by the target distribution. This provides a principled objective for learning multimodal action distributions without iterative sampling, with exact recovery at the population optimum when the model can represent the target distribution. Experiments on both simulation and real-world manipulation tasks demonstrate competitive task success with substantially lower action-generation latency than the flow matching baseline. These results support direct distributional learning as an efficient alternative to iterative generative robot policies.

cs.RO↗

arXiv2026

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

Scaling robot data and model capacity has improved Vision-Language-Action (VLA) policies, but further progress is constrained by the high cost of robotic data. Verifier-guided test-time scaling offers an efficient alternative by sampling multiple action candidates and selecting the one most likely to lead to task success at inference time. Existing classification-based verifiers learn from trajectory-level outcomes but treat all visited states equally, even though their value for candidate discrimination can vary across a trajectory. At many states, plausible actions are similar and provide limited discrimination signal, while only a sparse set of decision-critical states admits meaningfully different actions that can substantially affect downstream outcomes. To address this, we propose DiVeR, which estimates decision criticality from the dispersion of sampled action representations. DiVeR then uses this signal to reweight verifier learning toward states where action selection is most consequential, without requiring step-level annotations or additional environment interaction. Across LIBERO, RoboCasa, and real-world experiments on a Franka Research 3 robot, DiVeR consistently improves task success through more effective verifier-guided action selection, while adding negligible verifier inference overhead.

cs.RO↗

arXiv2026

VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL

Vision-language-action (VLA) models provide broad, instruction-conditioned manipulation behaviors, but their physical execution can remain imprecise during contact-rich interaction. Residual reinforcement learning (RL) can correct such errors while keeping the VLA frozen, but real-robot RL is costly and safety-critical. We propose VLA Latent-Conditioned RL (VLaRL), which enables residual RL for frozen VLAs to be trained in simulation and deployed on real robots without real-world RL or online adaptation. The key challenge is transferring the learned residual policy despite the visual gap between simulation and reality. Rather than requiring pixel-level visual correspondence, VLaRL uses the VLA's internal vision-language latent representation to condition residual control and as the sim-to-real transfer interface, and learns a lightweight mapper that transforms simulation-derived latents toward the real latent distribution. Across four contact-rich manipulation tasks and two VLA backbones, VLaRL improves real-world success in all task-backbone combinations, while controlled ablations demonstrate the importance of both latent conditioning and latent alignment for transferring simulation-trained residual control.

cs.RO↗

arXiv2026

ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration

Sim-to-real policy transfer -- deploying policies trained in simulation in the real world -- is a promising paradigm for scaling robot manipulation without large-scale real-world data. However, transferring simulation-trained policies remains challenging due to discrepancies in contact dynamics -- particularly in contact-rich tasks where subtle differences can alter task outcomes entirely. Because interaction between the manipulated object and the environment is mediated through contact, task success depends on accurately reproducing task-relevant contacts. Accordingly, in manipulation, contact-centric fidelity -- reproducing both the contact event sequence (when, where, and how contacts occur) and the local contact dynamics (how forces and motions evolve at each contact) -- is a necessary condition for task success. Based on this insight, we propose a contact-centric real-to-sim-to-real RL framework that uses task-relevant contact event sequences extracted from real demonstrations as the learning objective. We approximate objects as groups of primitives and optimize their contact geometry in simulation so that the resulting local contact dynamics explain the observed state transitions. The contact event sequence is automatically extracted by replaying the demonstration. This sequence serves as a structured reward signal, guiding the policy toward physically plausible contact regimes validated in reality and preventing exploitation of unrealistic simulator contacts. The signal is obtained automatically, requiring no per-task reward design. Experiments on contact-rich manipulation tasks demonstrate more stable and robust sim-to-real policy transfer compared to unconstrained RL baselines.

cs.RO↗

arXiv2026

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions due to compounding execution errors; Can a reinforcement learning policy trained purely in simulation improve the robustness of real-world VLAs zero-shot? Residual RL, which learns a corrective policy on top of a frozen VLA, offers a natural framework, but existing approaches face a fundamental sim-to-real dilemma: privileged-state methods require lossy distillation for deployment; image-based methods suffer from the visual domain gap; and real-world RL is costly and unsafe. We propose an object-centric residual RL framework that refines VLA actions using object poses, enabling a compact observation space that transfers consistently between simulation and reality. To align the two domains, we additionally replay the same teleoperation demonstrations in simulation to train a sim counterpart of the real-world VLA. The residual RL policy is trained only in simulation with pose noise injection and dropout, and transfers zero-shot to the real robot. Across five manipulation tasks on a real Franka Research 3 (FR3) robot, our method improves the success rate from 42% to 76% zero-shot, and the improved rollouts can be further reused to retrain the base VLA for self-improvement without additional teleoperation. Project page: https://www.microsoft.com/en-us/research/articles/object-centric-residual-rl/

cs.RO↗

arXiv2026

DP-SfM: Dual-Pixel Structure-from-Motion without Scale Ambiguity

Multi-view 3D reconstruction, namely, structure-from-motion followed by multi-view stereo, is a fundamental component of 3D computer vision. In general, multi-view 3D reconstruction suffers from an unknown scale ambiguity unless a reference object of known size is present in the scene. In this article, we show that multi-view images captured using a dual-pixel (DP) sensor can automatically resolve the scale ambiguity, without requiring a reference object or prior calibration. Specifically, the defocus blur observed in DP images provides sufficient information to determine the absolute scale when paired with depth maps (up to scale) recovered from multi-view 3D reconstruction. Based on this observation, we develop a simple yet effective linear method to estimate the absolute scale, followed by the intensity-based optimization stage that aligns the left and right DP images by shifting them back toward each other using cross-view blur kernels. Experiments demonstrate the effectiveness of the proposed approach across diverse scenes captured with different cameras and lenses. Code and data are available at https://github.com/lilika-makabe/dp-sfm-tpami.git

cs.CV↗

arXiv2026

High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation

Previous multi-view normal integration methods typically sample a single ray per pixel, without considering the spatial area covered by each pixel, which varies with camera intrinsics and the camera-to-object distance. Consequently, when the target object is captured at different distances, the normals at corresponding pixels may differ across views. This multi-view surface normal inconsistency results in the blurring of high-frequency details in the reconstructed surface. To address this issue, we propose a scale-encoded neural surface representation that incorporates the pixel coverage area into the neural representation. By associating each 3D point with a spatial scale and calculating its normal from a hybrid grid-based encoding, our method effectively represents multi-scale surface normals captured at varying distances. Furthermore, to enable scale-aware surface reconstruction, we introduce a mesh extraction module that assigns an optimal local scale to each vertex based on the training observations. Experimental results demonstrate that our approach consistently yields high-fidelity surface reconstruction from normals observed at varying distances, outperforming existing multi-view normal integration methods.

cs.CV↗

arXiv2026

Near-light Photometric Stereo with Symmetric Lights

This paper describes a linear solution method for near-light photometric stereo by exploiting symmetric light source arrangements. Unlike conventional non-convex optimization approaches, by arranging multiple sets of symmetric nearby light source pairs, our method derives a closed-form solution for surface normal and depth without requiring initialization. In addition, our method works as long as the light sources are symmetrically distributed about an arbitrary point even when the entire spatial offset is uncalibrated. Experiments showcase the accuracy of shape recovery accuracy of our method, achieving comparable results to the state-of-the-art calibrated near-light photometric stereo method while significantly reducing requirements of careful depth initialization and light calibration.

cs.CV↗

arXiv2025

RobustSplat++: Decoupling Densification, Dynamics, and Illumination for In-the-Wild 3DGS

3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. However, existing methods struggle with accurately modeling in-the-wild scenes affected by transient objects and illuminations, leading to artifacts in the rendered images. We identify that the Gaussian densification process, while enhancing scene detail capture, unintentionally contributes to these artifacts by growing additional Gaussians that model transient disturbances and illumination variations. To address this, we propose RobustSplat++, a robust solution based on several critical designs. First, we introduce a delayed Gaussian growth strategy that prioritizes optimizing static scene structure before allowing Gaussian splitting/cloning, mitigating overfitting to transient objects in early optimization. Second, we design a scale-cascaded mask bootstrapping approach that first leverages lower-resolution feature similarity supervision for reliable initial transient mask estimation, taking advantage of its stronger semantic consistency and robustness to noise, and then progresses to high-resolution supervision to achieve more precise mask prediction. Third, we incorporate the delayed Gaussian growth strategy and mask bootstrapping with appearance modeling to handling in-the-wild scenes including transients and illuminations. Extensive experiments on multiple challenging datasets show that our method outperforms existing methods, clearly demonstrating the robustness and effectiveness of our method.

cs.CV↗

arXiv2025

NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement

We develop a neural parametric model for 3D leaves for plant modeling and reconstruction that are essential for agriculture and computer graphics. While neural parametric models are actively studied for humans and animals, plant leaves present unique challenges due to their diverse shapes and flexible deformation. To this problem, we introduce a neural parametric model for leaves, NeuraLeaf. Capitalizing on the fact that flattened leaf shapes can be approximated as a 2D plane, NeuraLeaf disentangles the leaves' geometry into their 2D base shapes and 3D deformations. This representation allows learning from rich sources of 2D leaf image datasets for the base shapes, and also has the advantage of simultaneously learning textures aligned with the geometry. To model the 3D deformation, we propose a novel skeleton-free skinning model and create a newly captured 3D leaf dataset called DeformLeaf. We show that NeuraLeaf successfully generates a wide range of leaf shapes with deformation, resulting in accurate model fitting to 3D observations like depth maps and point clouds. Our implementation and dataset are available at https://neuraleaf-yang.github.io/.

cs.CV↗

arXiv2025

Spectral Sensitivity Estimation with an Uncalibrated Diffraction Grating

This paper introduces a practical and accurate calibration method for camera spectral sensitivity using a diffraction grating. Accurate calibration of camera spectral sensitivity is crucial for various computer vision tasks, including color correction, illumination estimation, and material analysis. Unlike existing approaches that require specialized narrow-band filters or reference targets with known spectral reflectances, our method only requires an uncalibrated diffraction grating sheet, readily available off-the-shelf. By capturing images of the direct illumination and its diffracted pattern through the grating sheet, our method estimates both the camera spectral sensitivity and the diffraction grating parameters in a closed-form manner. Experiments on synthetic and real-world data demonstrate that our method outperforms conventional reference target-based methods, underscoring its effectiveness and practicality.

cs.CV↗

arXiv2025

HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting

Novel view synthesis has demonstrated impressive progress recently, with 3D Gaussian splatting (3DGS) offering efficient training time and photorealistic real-time rendering. However, reliance on Cartesian coordinates limits 3DGS's performance on distant objects, which is important for reconstructing unbounded outdoor environments. We found that, despite its ultimate simplicity, using homogeneous coordinates, a concept on the projective geometry, for the 3DGS pipeline remarkably improves the rendering accuracies of distant objects. We therefore propose Homogeneous Gaussian Splatting (HoGS) incorporating homogeneous coordinates into the 3DGS framework, providing a unified representation for enhancing near and distant objects. HoGS effectively manages both expansive spatial positions and scales particularly in outdoor unbounded environments by adopting projective geometry principles. Experiments show that HoGS significantly enhances accuracy in reconstructing distant objects while maintaining high-quality rendering of nearby objects, along with fast training speed and real-time rendering capability. Our implementations are available on our project page https://kh129.github.io/hogs/.

cs.GR↗

arXiv2025

Shadow Art Kanji: Inverse Rendering Application

Finding a balance between artistic beauty and machine-generated imagery is always a difficult task. This project seeks to create 3D models that, when illuminated, cast shadows resembling Kanji characters. It aims to combine artistic expression with computational techniques, providing an accurate and efficient approach to visualizing these Japanese characters through shadows.

cs.GR↗

arXiv2023

Multi-View Azimuth Stereo via Tangent Space Consistency

We present a method for 3D reconstruction only using calibrated multi-view surface azimuth maps. Our method, multi-view azimuth stereo, is effective for textureless or specular surfaces, which are difficult for conventional multi-view stereo methods. We introduce the concept of tangent space consistency: Multi-view azimuth observations of a surface point should be lifted to the same tangent space. Leveraging this consistency, we recover the shape by optimizing a neural implicit surface representation. Our method harnesses the robust azimuth estimation capabilities of photometric stereo methods or polarization imaging while bypassing potentially complex zenith angle estimation. Experiments using azimuth maps from various sources validate the accurate shape recovery with our method, even without zenith angles.

cs.CV↗

arXiv2022

Edge-preserving Near-light Photometric Stereo with Neural Surfaces

This paper presents a near-light photometric stereo method that faithfully preserves sharp depth edges in the 3D reconstruction. Unlike previous methods that rely on finite differentiation for approximating depth partial derivatives and surface normals, we introduce an analytically differentiable neural surface in near-light photometric stereo for avoiding differentiation errors at sharp depth edges, where the depth is represented as a neural function of the image coordinates. By further formulating the Lambertian albedo as a dependent variable resulting from the surface normal and depth, our method is insusceptible to inaccurate depth initialization. Experiments on both synthetic and real-world scenes demonstrate the effectiveness of our method for detailed shape recovery with edge preservation.

cs.CV↗

arXiv2021

Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo

We propose a method for estimating high-definition spatially-varying lighting, reflectance, and geometry of a scene from 360$^{\circ}$ stereo images. Our model takes advantage of the 360$^{\circ}$ input to observe the entire scene with geometric detail, then jointly estimates the scene's properties with physical constraints. We first reconstruct a near-field environment light for predicting the lighting at any 3D location within the scene. Then we present a deep learning model that leverages the stereo information to infer the reflectance and surface normal. Lastly, we incorporate the physical constraints between lighting and geometry to refine the reflectance of the scene. Both quantitative and qualitative experiments show that our method, benefiting from the 360$^{\circ}$ observation of the scene, outperforms prior state-of-the-art methods and enables more augmented reality applications such as mirror-objects insertion.

cs.CV↗

arXiv2020

Descriptor-Free Multi-View Region Matching for Instance-Wise 3D Reconstruction

This paper proposes a multi-view extension of instance segmentation without relying on texture or shape descriptor matching. Multi-view instance segmentation becomes challenging for scenes with repetitive textures and shapes, e.g., plant leaves, due to the difficulty of multi-view matching using texture or shape descriptors. To this end, we propose a multi-view region matching method based on epipolar geometry, which does not rely on any feature descriptors. We further show that the epipolar region matching can be easily integrated into instance segmentation and effective for instance-wise 3D reconstruction. Experiments demonstrate the improved accuracy of multi-view instance matching and the 3D reconstruction compared to the baseline methods.

cs.CV↗

arXiv2020

Deep Photometric Stereo for Non-Lambertian Surfaces

This paper addresses the problem of photometric stereo, in both calibrated and uncalibrated scenarios, for non-Lambertian surfaces based on deep learning. We first introduce a fully convolutional deep network for calibrated photometric stereo, which we call PS-FCN. Unlike traditional approaches that adopt simplified reflectance models to make the problem tractable, our method directly learns the mapping from reflectance observations to surface normal, and is able to handle surfaces with general and unknown isotropic reflectance. At test time, PS-FCN takes an arbitrary number of images and their associated light directions as input and predicts a surface normal map of the scene in a fast feed-forward pass. To deal with the uncalibrated scenario where light directions are unknown, we introduce a new convolutional network, named LCNet, to estimate light directions from input images. The estimated light directions and the input images are then fed to PS-FCN to determine the surface normals. Our method does not require a pre-defined set of light directions and can handle multiple images in an order-agnostic manner. Thorough evaluation of our approach on both synthetic and real datasets shows that it outperforms state-of-the-art methods in both calibrated and uncalibrated scenarios.

cs.CV↗