arXiv subjects

Takafumi Aoki

Publications and source records attributed to Takafumi Aoki.

At least 19 recordsLinked to original sources

arXiv2026

MARS-CLIP: Multi-Resolution and Attention Refined Zero-Shot Image Segmentation

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in zero-shot transfer but often struggles with dense prediction tasks due to low spatial resolution and the loss of structural information. To address these limitations, we propose MARS-CLIP (Multi-resolution and Attention Refined Segmentation for CLIP), a novel framework for zero-shot semantic segmentation. Our approach introduces two key strategies: (i) a multi-resolution feature extraction module that fuses local fine-grained features with global context to overcome input resolution constraints, and (ii) an attention refinement mechanism that injects spatial and color biases from intermediate layers into the final self-attention block to accurately restore object boundaries. A set of experiments on six public datasets demonstrates that MARS-CLIP significantly outperforms state-of-the-art methods.

cs.CV↗

arXiv2026

MAGE-Vein: Multi-Instance Age and Gender Estimation from Finger Vein Images

Age estimation from finger vein images has been widely considered impractical due to severe demographic biases in public datasets and physiological confounding factors like gender. To overcome these limitations, we propose MAGE-Vein, a novel multi-instance, multi-task learning framework. Our approach extracts robust structural aging signs by employing a hybrid feature-level fusion of three fingers, effectively suppressing local imaging noise. Furthermore, simultaneous optimization of gender classification conditions the network to effectively eliminate gender-specific vascular variations. Evaluated on a demographically balanced dataset of 402 subjects, MAGE-Vein achieves a mean absolute error of 6.12 years and a correlation of 0.880. Our results not only overturn the conventional consensus regarding the limitations of the finger vein modality but also demonstrate that previous estimation failures were primarily artifacts of biased public datasets. Our code is available at https://github.com/gsisaoki/MAGE-Vein.

cs.CV↗

arXiv2026

DINO-VPT: Hierarchical Visual Prompt Tuning for Joint Physical-Digital Face Anti-Spoofing

With the increasing diversity of spoofing attacks, there is a growing demand for unified Face Anti-Spoofing (FAS) models capable of detecting both physical and digital threats. While existing Vision-Language Models (VLMs) demonstrate high generalization in this context, they heavily rely on complex multimodal fusion and external text encoders. In this paper, we propose DINO-VPT, a lightweight, vision-only framework leveraging hierarchical visual prompt tuning. By dynamically injecting prompts conditioned on input features via a Prompt Routing Network (PRN), our method effectively disentangles diverse spoofing artifacts without requiring multimodal fusion. Evaluations on the UniAttackData benchmark demonstrate that DINO-VPT achieves higher accuracy than state-of-the-art VLM-based methods. Our results indicate that a properly structured vision-only architecture can achieve state-of-the-art performance in unified FAS without the need for multimodal supervision.

cs.CV↗

arXiv2026

PC-Seg: Progressive Cross-View Consistency for 3D OCT Segmentation from Sparse 2D Annotations

Volumetric segmentation of optical coherence tomography (OCT) images is essential for diagnosing ocular diseases but requires labor-intensive voxel-wise annotations. While semi-supervised learning (SSL) can reduce annotation costs, most existing methods process data slice by slice and fail to exploit the inherent 3D spatial context. We propose PC-Seg, a progressive cross-view consistency framework that learns high-accuracy 3D segmentation models from sparse 2D annotations. Unlike conventional multi-view approaches, PC-Seg uses a single 2D model to learn cross-view consistency from standard B-scans and orthogonal slices, thereby generating reliable volumetric pseudo-labels. These pseudo-labels are then distilled into a 3D model, followed by a co-training stage in which the 2D and 3D models mutually refine each other through ensemble pseudo-labeling. Experiments on the MSHC and Duke DME datasets demonstrate that PC-Seg achieves accuracy comparable to fully supervised learning while using labels for only about 0.7% of the training data, outperforming state-of-the-art semi-supervised and retinal layer segmentation methods. Our code is publicly available at https://github.com/gsisaoki/pc-seg-official.

cs.CV↗

arXiv2026

G-MASt3R-SfM: Graph-based View Pruning and Multi-stage Optimization for Robust SfM

Structure from Motion (SfM) is essential for multi-view 3D reconstruction, however, its accuracy heavily relies on the accuracy of image matching. While the recent correspondence matching method, MASt3R, enables robust matching even under challenging conditions, it tends to generate incorrect correspondences for non-overlapping image pairs. Consequently, existing SfM methods using MASt3R, such as MASt3R-SfM, suffer from significant degradation in pose estimation accuracy as they incorporate these unreliable matches directly into optimization. To address this issue, we propose G-MASt3R-SfM, a novel SfM pipeline that enhances robustness through two key modules. First, the Graph-based View Pruning (GVP) module constructs a scene graph from matching confidence and geometrically prunes outlier views. Second, the Multi-Stage Optimization (MSO) module progressively refines camera parameters by expanding the optimization scope from local consistency to the global consistency. Experiments on the ETH3D dataset demonstrate that our method achieves state-of-the-art accuracy in both camera pose estimation and 3D reconstruction, effectively suppressing noise caused by outliers.

cs.CV↗

arXiv2026

Benchmarking Vision Foundation Models for Domain-Generalizable Face Anti-Spoofing

Face Anti-Spoofing (FAS) remains challenging due to the requirement for robust domain generalization across unseen environments. While recent trends leverage Vision-Language Models (VLMs) for semantic supervision, these multimodal approaches often demand prohibitive computational resources and exhibit high inference latency. Furthermore, their efficacy is inherently limited by the quality of the underlying visual features. This paper revisits the potential of vision-only foundation models to establish a highly efficient and robust baseline for FAS. We conduct a systematic benchmarking of 15 pre-trained models, such as supervised CNNs, supervised ViTs, and self-supervised ViTs, under severe cross-domain scenarios including the MICO and Limited Source Domains (LSD) protocols. Our comprehensive analysis reveals that self-supervised vision models, particularly DINOv2 with Registers, significantly suppress attention artifacts and capture critical, fine-grained spoofing cues. Combined with Face Anti-Spoofing Data Augmentation (FAS-Aug), Patch-wise Data Augmentation (PDA) and Attention-weighted Patch Loss (APL), our proposed vision-only baseline achieves state-of-the-art performance in the MICO protocol. This baseline outperforms existing methods under the data-constrained LSD protocol while maintaining superior computational efficiency. This work provides a definitive vision-only baseline for FAS, demonstrating that optimized self-supervised vision transformers can serve as a backbone for both vision-only and future multimodal FAS systems. The project page is available at: https://gsisaoki.github.io/FAS-VFMbenchmark-CVPRW2026/ .

cs.CV↗

arXiv2026

PlankFormer: Robust Plankton Instance Segmentation via MAE-Pretrained Vision Transformers and Pseudo Community Image Generation

Plankton monitoring is essential for assessing aquatic ecosystems but is limited by the labor-intensive nature of manual microscopic analysis. Automating the segmentation of plankton from crowded images is crucial, however, it faces two major challenges: (i) the scarcity of pixel-level annotated datasets and (ii) the difficulty of distinguishing plankton from debris and overlapping individuals using conventional CNN-based methods. To address these issues, we propose PlankFormer, a novel framework for plankton instance segmentation. First, to overcome the data shortage, we introduce a method to generate labeled Pseudo Community Images (PCI) by synthesizing individual plankton images onto diverse backgrounds, including those created by generative models. Second, we propose a segmentation model utilizing a Vision Transformer (ViT) backbone with a Mask2Former decoder. To robustly capture the global structural features of plankton against occlusion and debris, we employ a Masked Autoencoder (MAE) for self-supervised pre-training on unlabeled individual images. Experimental results on real-world datasets demonstrate that our method significantly outperforms conventional methods, such as Mask R-CNN, particularly in challenging environments with high debris density. We demonstrate that our synthetic training strategy and MAE-based architecture enable high-precision segmentation with requiring less manual annotations for individual plankton images.

cs.CV↗

arXiv2026

A Closer Look at Constrained Instantons

Instantons play a crucial role in understanding non-perturbative dynamics in quantum field theories, including those with spontaneously broken gauge symmetries. In the broken phase, finite-size instanton-like configurations are no longer exact stationary points of the Euclidean action, in contrast to the symmetric phase. Non-perturbative effects in this setting are therefore typically studied within the constrained instanton framework. However, a previous study pointed out a possible difficulty in constructing consistent constrained instanton solutions based on conventional gauge-invariant constraints. In this work, we revisit the asymptotic structure of constrained instantons and re-examine the claimed difficulty. By carefully tracking the behavior of the solutions near the spatial origin and at infinity, we show that the required boundary conditions can be satisfied without encountering the inconsistency. We explicitly construct consistent constrained instantons in both massive $ϕ^4$ theory and Yang--Mills theory with spontaneous symmetry breaking, and we support our analytic matching procedure with numerical solutions. Our results establish that conventional gauge-invariant constraints can be consistently employed in semiclassical computations when asymptotic expansions are treated properly.

hep-th↗

arXiv2025

Optimizing DINOv2 with Registers for Face Anti-Spoofing

Face recognition systems are designed to be robust against variations in head pose, illumination, and image blur during capture. However, malicious actors can exploit these systems by presenting a face photo of a registered user, potentially bypassing the authentication process. Such spoofing attacks must be detected prior to face recognition. In this paper, we propose a DINOv2-based spoofing attack detection method to discern minute differences between live and spoofed face images. Specifically, we employ DINOv2 with registers to extract generalizable features and to suppress perturbations in the attention mechanism, which enables focused attention on essential and minute features. We demonstrate the effectiveness of the proposed method through experiments conducted on the dataset provided by ``The 6th Face Anti-Spoofing Workshop: Unified Physical-Digital Attacks Detection@ICCV2025'' and SiW dataset. The project page is available at: https://gsisaoki.github.io/FAS-DINOv2-ICCVW/ .

cs.CV↗

arXiv2025

Backdoor Poisoning Attack Against Face Spoofing Attack Detection Methods

Face recognition systems are robust against environmental changes and noise, and thus may be vulnerable to illegal authentication attempts using user face photos, such as spoofing attacks. To prevent such spoofing attacks, it is crucial to discriminate whether the input image is a live user image or a spoofed image prior to the face recognition process. Most existing spoofing attack detection methods utilize deep learning, which necessitates a substantial amount of training data. Consequently, if malicious data is injected into a portion of the training dataset, a specific spoofing attack may be erroneously classified as live, leading to false positives. In this paper, we propose a novel backdoor poisoning attack method to demonstrate the latent threat of backdoor poisoning within face anti-spoofing detection. The proposed method enables certain spoofing attacks to bypass detection by embedding features extracted from the spoofing attack's face image into a live face image without inducing any perceptible visual alterations. Through experiments conducted on public datasets, we demonstrate that the proposed method constitutes a realistic threat to existing spoofing attack detection systems.

cs.CV↗

arXiv2025

Multibiometrics Using a Single Face Image

Multibiometrics, which uses multiple biometric traits to improve recognition performance instead of using only one biometric trait to authenticate individuals, has been investigated. Previous studies have combined individually acquired biometric traits or have not fully considered the convenience of the system. Focusing on a single face image, we propose a novel multibiometric method that combines five biometric traits, i.e., face, iris, periocular, nose, eyebrow, that can be extracted from a single face image. The proposed method does not sacrifice the convenience of biometrics since only a single face image is used as input. Through a variety of experiments using the CASIA Iris Distance database, we demonstrate the effectiveness of the proposed multibiometrics method.

cs.CV↗

arXiv2025

Leveraging Intermediate Features of Vision Transformer for Face Anti-Spoofing

Face recognition systems are designed to be robust against changes in head pose, illumination, and blurring during image capture. If a malicious person presents a face photo of the registered user, they may bypass the authentication process illegally. Such spoofing attacks need to be detected before face recognition. In this paper, we propose a spoofing attack detection method based on Vision Transformer (ViT) to detect minute differences between live and spoofed face images. The proposed method utilizes the intermediate features of ViT, which have a good balance between local and global features that are important for spoofing attack detection, for calculating loss in training and score in inference. The proposed method also introduces two data augmentation methods: face anti-spoofing data augmentation and patch-wise data augmentation, to improve the accuracy of spoofing attack detection. We demonstrate the effectiveness of the proposed method through experiments using the OULU-NPU and SiW datasets. The project page is available at: https://gsisaoki.github.io/FAS-ViT-CVPRW/ .

cs.CV↗

arXiv2025

ErpGS: Equirectangular Image Rendering enhanced with 3D Gaussian Regularization

The use of multi-view images acquired by a 360-degree camera can reconstruct a 3D space with a wide area. There are 3D reconstruction methods from equirectangular images based on NeRF and 3DGS, as well as Novel View Synthesis (NVS) methods. On the other hand, it is necessary to overcome the large distortion caused by the projection model of a 360-degree camera when equirectangular images are used. In 3DGS-based methods, the large distortion of the 360-degree camera model generates extremely large 3D Gaussians, resulting in poor rendering accuracy. We propose ErpGS, which is Omnidirectional GS based on 3DGS to realize NVS addressing the problems. ErpGS introduce some rendering accuracy improvement techniques: geometric regularization, scale regularization, and distortion-aware weights and a mask to suppress the effects of obstacles in equirectangular images. Through experiments on public datasets, we demonstrate that ErpGS can render novel view images more accurately than conventional methods.

cs.CV↗

arXiv2025

Zero-Shot Pseudo Labels Generation Using SAM and CLIP for Semi-Supervised Semantic Segmentation

Semantic segmentation is a fundamental task in medical image analysis and autonomous driving and has a problem with the high cost of annotating the labels required in training. To address this problem, semantic segmentation methods based on semi-supervised learning with a small number of labeled data have been proposed. For example, one approach is to train a semantic segmentation model using images with annotated labels and pseudo labels. In this approach, the accuracy of the semantic segmentation model depends on the quality of the pseudo labels, and the quality of the pseudo labels depends on the performance of the model to be trained and the amount of data with annotated labels. In this paper, we generate pseudo labels using zero-shot annotation with the Segment Anything Model (SAM) and Contrastive Language-Image Pretraining (CLIP), improve the accuracy of the pseudo labels using the Unified Dual-Stream Perturbations Approach (UniMatch), and use them as enhanced labels to train a semantic segmentation model. The effectiveness of the proposed method is demonstrated through the experiments using the public datasets: PASCAL and MS COCO. The project web page is available at: https://gsisaoki.github.io/ZERO-SHOT-PLG/

cs.CV↗

arXiv2025

Sparse2DGS: Sparse-View Surface Reconstruction using 2D Gaussian Splatting with Dense Point Cloud

Gaussian Splatting (GS) has gained attention as a fast and effective method for novel view synthesis. It has also been applied to 3D reconstruction using multi-view images and can achieve fast and accurate 3D reconstruction. However, GS assumes that the input contains a large number of multi-view images, and therefore, the reconstruction accuracy significantly decreases when only a limited number of input images are available. One of the main reasons is the insufficient number of 3D points in the sparse point cloud obtained through Structure from Motion (SfM), which results in a poor initialization for optimizing the Gaussian primitives. We propose a new 3D reconstruction method, called Sparse2DGS, to enhance 2DGS in reconstructing objects using only three images. Sparse2DGS employs DUSt3R, a fundamental model for stereo images, along with COLMAP MVS to generate highly accurate and dense 3D point clouds, which are then used to initialize 2D Gaussians. Through experiments on the DTU dataset, we show that Sparse2DGS can accurately reconstruct the 3D shapes of objects using just three images. The project page is available at https://gsisaoki.github.io/SPARSE2DGS/

cs.CV↗

arXiv2025

Stereo Radargrammetry Using Deep Learning from Airborne SAR Images

In this paper, we propose a stereo radargrammetry method using deep learning from airborne Synthetic Aperture Radar (SAR) images. Deep learning-based methods are considered to suffer less from geometric image modulation, while there is no public SAR image dataset used to train such methods. We create a SAR image dataset and perform fine-tuning of a deep learning-based image correspondence method. The proposed method suppresses the degradation of image quality by pixel interpolation without ground projection of the SAR image and divides the SAR image into patches for processing, which makes it possible to apply deep learning. Through a set of experiments, we demonstrate that the proposed method exhibits a wider range and more accurate elevation measurements compared to conventional methods. The project web page is available at: https://gsisaoki.github.io/IGARSS2025_sasayama/

cs.CV↗

arXiv2025

OB3D: A New Dataset for Benchmarking Omnidirectional 3D Reconstruction Using Blender

Recent advancements in radiance field rendering, exemplified by Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have significantly progressed 3D modeling and reconstruction. The use of multiple 360-degree omnidirectional images for these tasks is increasingly favored due to advantages in data acquisition and comprehensive scene capture. However, the inherent geometric distortions in common omnidirectional representations, such as equirectangular projection (particularly severe in polar regions and varying with latitude), pose substantial challenges to achieving high-fidelity 3D reconstructions. Current datasets, while valuable, often lack the specific focus, scene composition, and ground truth granularity required to systematically benchmark and drive progress in overcoming these omnidirectional-specific challenges. To address this critical gap, we introduce Omnidirectional Blender 3D (OB3D), a new synthetic dataset curated for advancing 3D reconstruction from multiple omnidirectional images. OB3D features diverse and complex 3D scenes generated from Blender 3D projects, with a deliberate emphasis on challenging scenarios. The dataset provides comprehensive ground truth, including omnidirectional RGB images, precise omnidirectional camera parameters, and pixel-aligned equirectangular maps for depth and normals, alongside evaluation metrics. By offering a controlled yet challenging environment, OB3Daims to facilitate the rigorous evaluation of existing methods and prompt the development of new techniques to enhance the accuracy and reliability of 3D reconstruction from omnidirectional images.

cs.CV↗

arXiv2024

Formula-Driven Data Augmentation and Partial Retinal Layer Copying for Retinal Layer Segmentation

Major retinal layer segmentation methods from OCT images assume that the retina is flattened in advance, and thus cannot always deal with retinas that have changes in retinal structure due to ophthalmopathy and/or curvature due to myopia. To eliminate the use of flattening in retinal layer segmentation for practicality of such methods, we propose novel data augmentation methods for OCT images. Formula-driven data augmentation (FDDA) emulates a variety of retinal structures by vertically shifting each column of the OCT images according to a given mathematical formula. We also propose partial retinal layer copying (PRLC) that copies a part of the retinal layers and pastes it into a region outside the retinal layers. Through experiments using the OCT MS and Healthy Control dataset and the Duke Cyst DME dataset, we demonstrate that the use of FDDA and PRLC makes it possible to detect the boundaries of retinal layers without flattening even retinal layer segmentation methods that assume flattening of the retina.

eess.IV↗