WACV 2026 Papers

3D face recognition offers a robust biometric solution by capturing facial geometry, providing resilience to variations in illumination, pose changes, and presentation attacks. Its strong spoof resistance makes it suitable for high-security applications, but protecting stored biometric templates remains critical. We present GFT-GCN, a privacy-preserving 3D face recognition framework that combines spectral graph learning with diffusion-based template protection. Our approach integrates the Graph Fourier Transform (GFT) and Graph Convolutional Networks (GCN) to extract compact, discriminative spectral features from 3D face meshes. To secure these features, we introduce a spectral diffusion mechanism that produces irreversible, renewable, and unlinkable templates. A lightweight client-server architecture ensures that raw biometric data never leaves the client device. Experiments on the BU-3DFE and FaceScape datasets demonstrate high recognition accuracy and strong resistance to reconstruction attacks. Results show that GFT-GCN effectively balances privacy and performance, offering a practical solution for secure 3D face authentication.

Vision Transformers (ViTs) offer strong performance by modeling global relationships across image patches, but their scalability is limited by the quadratic cost of self-attention. To mitigate this, Token Merging (ToMe) reduces computation by merging similar tokens. This approach relies on proportional attention to preserve the original balance of attention weights after merging. Yet, proportional attention does not fully resolve the attention distortion. It only compensates for a merged token's influence on other tokens, while ignoring the fundamental distortion of the token's own self-attention score. This change creates unaddressed distortions that vary across attention heads. In this work, we conduct a detailed analysis of these attention distortions and reveal their dependence on the query-key projection weights of each head. Based on this finding, we propose Head-wise Attention Correction (HAC), a method that adjusts attention scores after token merging by accounting for head-specific characteristics. HAC effectively mitigates the distortions overlooked by proportional attention, maintaining model accuracy while significantly reducing computation. Experiments on ImageNet demonstrate that our method effectively improves the trade-off between efficiency and performance, advancing the development of efficient Vision Transformers via token merging. Code is available at https://github.com/ychikawa/HAC-ToMe

We present Mobile-Oriented Video Diffusion (MOVD) framework, the first diffusion-based text-to-video generation framework designed for efficient on-device execution on smartphone-grade hardware without requiring retraining, compression or pruning of the target denoising model. To address the challenges of diffusion-based text-to-video generation on computation- and memory-limited mobile devices, MOVD applies two novel techniques to pretrained video generative models. First, Linear Proportional Leap (LPL) reduces the excessive denoising steps required in video diffusion through an efficient leap-based approach. Second, Temporal Dimension Token Merging (TDTM) reduces the heavy computational load of attention layers by merging consecutive tokens along the temporal dimension. By integrating these techniques with Concurrent Inference with Dynamic Loading (CI-DL), which splits large models into smaller, executable segments for limited memory environments, MOVD allows a text-to-video diffusion generative model to run on an iPhone 15 Pro. We envision the proposed MOVD as a significant first step toward democratizing state-of-the-art generative technologies, enabling video generation on mobile and embedded devices without resource-intensive optimization procedures.

Deep learning increasingly relies on massive data with substantial storage, annotation, and training costs. To reduce costs, coreset selection finds a representative subset of data to train models while ideally performing on par with the full data training. To maximize performance, current state-of-the-art coreset methods select data using dataset-specific ground truth labels and training. However, these methodological requirements prevent selection at scale on real-world, unlabeled data. To that end, this paper addresses the selection of coresets that achieve state-of-the-art performance but without using any labels or training on candidate data. Instead, our solution, Zero-Shot Coreset Selection via Iterative Subspace Sampling (ZCore), uses previously-trained foundation models to generate zero-shot, high-dimensional embedding spaces to interpret unlabeled data. ZCore then iteratively quantifies the relative value of all candidate data based on coverage and redundancy in numerous subspace distributions. Finally, ZCore selects a coreset sized for any data budget to train downstream models. We evaluate ZCore on four datasets and outperform several state-of-the-art label-based methods, especially at low data rates that provide the most substantial cost reduction. On ImageNet, ZCore selections for 10% training data achieve a downstream validation accuracy of 53.99%, which outperforms prior label-based methods and removes annotation and training costs for 1.15 million images. Our paper's code is publicly available at https://github.com/voxel51/zcore.

Vision-language models (VLMs) like CLIP excel in zero-shot learning by aligning image and text representations through contrastive pretraining. Existing approaches to unsupervised adaptation (UA) for fine-grained classification with VLMs either rely on fixed alignment scores that may not capture evolving, subtle class distinctions or rely on computationally expensive pseudo-labeling strategies that limit scalability.In contrast, we show that modeling fine-grained cross-modal interactions during adaptation produces more accurate, class-discriminative pseudo-labels and substantially improves performance over state-of-the-art (SOTA) methods.We introduce Fine-grained Alignment and Interaction Refinement (FAIR), an innovative approach that dynamically aligns localized image features with descriptive language embeddings through a set of Class Description Anchors (CDA). This enables the definition of a Learned Alignment Score (LAS), which incorporates CDA as an adaptive classifier, facilitating cross-modal interactions to improve self-training in unsupervised adaptation.Furthermore, we propose a self-training weighting mechanism designed to refine pseudo-labels in the presence of inter-class ambiguities.Our approach, FAIR, delivers a substantial performance boost in fine-grained unsupervised adaptation, achieving a notable overall gain of 2.78% across 13 fine-grained datasets compared to SOTA methods.

Accurate counting of surgical instruments in Operating Rooms (OR) is a critical prerequisite for ensuring patient safety during surgery. Despite recent progress of large visual-language models and agentic AI, accurately counting such instruments remains highly challenging, particularly in dense scenarios where instruments are tightly clustered. To address this problem, we introduce Chain-of-Look, a novel visual reasoning framework that mimics the sequential human counting process by enforcing a structured visual chain, rather than relying on classic object detection which is unordered. This visual chain guides the model to count along a coherent spatial trajectory, improving accuracy in complex scenes. To further enforce the physical plausibility of the visual chain, we introduce the neighboring loss function, which explicitly models the spatial constraints inherent to densely packed surgical instruments. We also present SurgCount-HD, a new dataset comprising 1,464 high-density surgical instrument images. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches for counting (e.g., CountGD, REC) as well as Multimodality Large Language Models (e.g., Qwen, ChatGPT) in the challenging task of dense surgical instrument counting.

We tackle the problem of quantifying the number of objects by a generative text-to-image model. Rather than retraining such a model for each new image domain of interest, which leads to high computational costs and limited scalability, we are the first to consider this problem from a domain-agnostic perspective. We propose QUOTA, an optimization framework for text-to-image models that enables effective object quantification across unseen domains without retraining. It leverages a dual-loop meta-learning strategy to optimize a domain-invariant prompt. Further, by integrating prompt learning with learnable counting and domain tokens, our method captures stylistic variations and maintains accuracy, even for object classes not encountered during training.For evaluation, we adopt a new benchmark QUANT-Bench specifically designed for object quantification in domain generalization, enabling rigorous assessment of object quantification accuracy and adaptability across unseen domains in text-to-image generation.Extensive experiments demonstrate that QUOTA outperforms conventional models in both object quantification accuracy and semantic consistency, setting a new benchmark for efficient and scalable text-to-image generation for any domain.

Magnetic Resonance Imaging (MRI) plays a crucial role in brain disease diagnosis, but it is not always feasible for certain patients due to physical or clinical constraints. Recent studies attempt to synthesize MRI from Computed Tomography (CT) scans; however, low-dose protocols often result in highly sparse CT volumes with poor through-plane resolution, making accurate reconstruction of the full brain MRI volume particularly challenging. To address this, we propose ReBrain, a retrieval-augmented diffusion framework for brain MRI reconstruction. Given any 3D CT scan with limited slices, we first employ a Brownian Bridge Diffusion Model (BBDM) to synthesize MRI slices along the 2D dimension. Simultaneously, we retrieve structurally and pathologically similar CT slices from a comprehensive prior database via a fine-tuned retrieval model. These retrieved slices are used as references, incorporated through a ControlNet branch to guide the generation of intermediate MRI slices and ensure structural continuity. We further account for rare retrieval failures when the database lacks suitable references and apply spherical linear interpolation to provide supplementary guidance. Extensive experiments on SynthRAD2023 and BraTS demonstrate that ReBrain achieves state-of-the-art performance in cross-modal reconstruction under sparse conditions.

Underground mining disasters produce pervasive darkness, dust, and collapses that obscure vision and make situational awareness difficult for humans and conventional systems. To address this, we propose MDSE, Multimodal Disaster Situation Explainer, a novel vision-language framework that automatically generates detailed textual explanations of post-disaster underground scenes. MDSE has three-fold innovations: (i) Context-Aware Cross-Attention for robust alignment of visual and textual features even under severe degradation; (ii) Segmentation-aware dual pathway visual encoding that fuses global and region-specific embeddings; and (iii) Resource-Efficient Transformer-Based Language Model for expressive caption generation with minimal compute cost. To support this task, we present the Underground Mine Disaster (UMD) dataset--the first image-caption corpus of real underground disaster scenes--enabling rigorous training and evaluation. Extensive experiments on UMD and related benchmarks show that MDSE substantially outperforms state-of-the-art captioning models, producing more accurate and contextually relevant descriptions that capture crucial details in obscured environments, improving situational awareness for underground emergency response. The code is at https://github.com/mizanJewel/Multimodal-Disaster-Situation-Explainer.

Robotic manipulation of unseen objects via natural language commands remains challenging. Language driven robotic grasping (LDRG) predicts stable grasp poses from natural language queries and RGB-D images. We propose MapleGrasp, a novel framework that leverages mask-guided feature pooling for efficient vision-language driven grasping. Our two-stage training first predicts segmentation masks from CLIP-based vision-language features. The second stage pools features within these masks to generate pixel-level grasp predictions, improving efficiency, and reducing computation. Incorporating mask pooling results in a 7% improvement over prior approaches on the OCID-VLG benchmark. Furthermore, we introduce RefGraspNet, an open-source dataset eight times larger than existing alternatives, significantly enhancing model generalization for open-vocabulary grasping. MapleGrasp scores a strong grasping accuracy of 89% when compared with competing methods in the RefGraspNet benchmark. Our method achieves comparable performance to larger Vision-Language-Action models on the LIBERO benchmark, and shows significantly better generalization to unseen tasks. Real-world experiments on a Franka arm demonstrate 73% success rate with unseen objects, surpassing competitive baselines by 11%. Code and dataset is available here: https://github.com/vineet2104/MapleGrasp.

Large 3D shape repositories are rapidly expanding, driven by advances in generative modeling, making efficient shape retrieval increasingly important for authoring tools. While text queries capture high-level semantics, they often fail to convey precise geometric details. 3D sketches provide a more expressive means of representing shape geometry, and recent AR/VR developments have made sketch-based retrieval practical. However, existing 3D sketch datasets face three major limitations:(1) reliance on quad meshes or voxel hulls, which often fail on complex or non-manifold shapes; (2) use of fixed-size point clouds that discard stroke connectivity and limit geometric fidelity; and (3) dependence on expensive curve-based or multi-view rendering pipelines, which hinder large-scale data generation. Limited point cloud representations also fail to capture sketch connectivity and topology when used to train retrieval models. To address these challenges, we propose Sketch3R, a scalable framework that converts arbitrary 3D meshes into human-like VR sketches using a graph-based representation that preserves stroke connectivity and adapts to sketch complexity. Leveraging this representation, Sketch3R employs a lightweight graph-attention Siamese network for efficient and accurate sketch-to-shape retrieval. Experiments demonstrate that our method outperforms prior approaches in both accuracy and speed, while robustly handling 3D shapes across diverse topologies.

Visibility of natural landmarks such as Mount Fuji is a defining factor in both tourism planning and visitor experience, yet it remains difficult to predict due to rapidly changing atmospheric conditions. We present FujiView, a multimodal learning framework and dataset for predicting scenic visibility by fusing webcam imagery with structured meteorological data. Our late-fusion approach combines image-derived class probabilities with numerical weather features to classify visibility into five categories. The dataset currently comprises over 100,000 webcam images paired with concurrent and forecasted weather conditions from more than 40 cameras around Mount Fuji, and continues to expand; it will be released to support further research in environmental forecasting. Experiments show that YOLO-based vision features dominate short-term horizons such as "nowcasting" and "samedaycasting", while weather-driven forecasts increasingly take over as the primary predictive signal beyond +1d. Late fusion consistently yields the highest overall accuracy, achieving ACC0.89 for same-day prediction and up to 84% for next-day forecasts. These results position Scenic Visibility Forecasting (SVF) as a new benchmark task for multimodal learning.

Pre-trained vision-language (VL) models are highly vulnerable to adversarial attacks. However, existing defense methods primarily focus on image classification, overlooking two key aspects of VL tasks: multimodal attacks, where both image and text can be perturbed, and the one-to-many relationship of images and texts, where a single image can correspond to multiple textual descriptions and vice versa (1:N and N:1). This work is the first to explore defense strategies against multimodal attacks in VL tasks, whereas prior VL defense methods focus on vision robustness. We propose multimodal adversarial training (MAT), which incorporates adversarial perturbations in both image and text modalities during training, significantly outperforming existing unimodal defenses. Furthermore, we discover that MAT is limited by deterministic one-to-one (1:1) image-text pairs in VL training data. To address this, we conduct a comprehensive study on leveraging one-to-many relationships to enhance robustness, investigating diverse augmentation techniques. Our analysis shows that, for a more effective defense, augmented image-text pairs should be well-aligned, diverse, yet avoid distribution shift---conditions overlooked by prior research. This work pioneers defense strategies against multimodal attacks, providing insights for building robust VLMs from both optimization and data perspectives. Our code is publicly available at https://github.com/CyberAgentAI/multimodal-adversarial-training.

Neural representations for 3D meshes are emerging as an effective solution for compact storage and efficient processing. Existing methods often rely on neural overfitting, where a coarse mesh is stored and progressively refined through multiple decoder networks. While this can restore high-quality surfaces, it is computationally expensive due to successive decoding passes and the irregular structure of mesh data. In contrast, images have a regular structure that enables powerful super-resolution and restoration frameworks, but applying these advantages to meshes is difficult because their irregular connectivity demands complex encoder-decoder architectures. Our key insight is that a geometry image-based representation transforms irregular meshes into a regular image grid, making efficient image-based neural processing directly applicable. Building on this idea, we introduce our neural geometry image-based representation, which is decoder-free, storage-efficient, and naturally suited for neural processing. It stores a low-resolution geometry-image mipmap of the surface, from which high-quality meshes are restored in a single forward pass. To construct geometry images, we leverage Optimal Transport (OT), which resolves oversampling in flat regions and undersampling in feature-rich regions, and enables continuous levels of detail (LoD) through geometry-image mipmapping. Experimental results demonstrate state-of-the-art storage efficiency and restoration accuracy, measured by compression ratio (CR), Chamfer distance (CD), and Hausdorff distance (HD).

Existing eyeglass removal methods can handle frames and shadows but fail to correct lens-induced geometric distortions, as public datasets lack the necessary supervision. To address this, we introduce the HiGlass Dataset, the first large-scale synthetic dataset providing explicit flow-based supervision for refractive warping. We also propose HiGlassRM, a novel pipeline whose core is a network that explicitly estimates a displacement flowmap to de-warp distorted facial geometry.Experiments on both synthetic and real images show that this flowmap-centric approach, trained on our data, significantly improves identity preservation and perceptual quality over existing methods. Our work demonstrates that explicitly modeling and correcting geometric distortion via flowmap estimation, enabled by targeted supervision, is key to faithful eyeglass removal.

Convolutional neural networks have shown remarkable performance in recent years on various computer vision problems. However, the traditional convolutional neural network architecture lacks a critical property: shift equivariance and invariance, broken by downsampling and upsampling operations. Although data augmentation techniques can help the model learn the latter property empirically, a consistent and systemic way to achieve this goal is by designing downsampling and upsampling layers that theoretically guarantee these properties by construction. Adaptive Polyphase Sampling (APS)introduced the cornerstone for shift invariance, later extended to shift equivariance with Learnable Polyphase up/downsampling (LPS) applied to real-valued neural networks. In this paper, we extend the work on LPSto complex-valued neural networks both from a theoretical perspective and with a novel building block of a projection layer from \mathbb C to \mathbb R before the Gumbel Softmax. We finally evaluate this extension on several computer vision problems for either the invariance property with classification tasks or the equivariance with both reconstruction and semantic segmentation problems using polarimetric synthetic aperture images.

Remote photoplethysmography (rPPG) has emerged as a promising foundation for camera-based blood pressure (BP) monitoring, but practical deployment remains limited by strong domain gaps across datasets, scarce and imbalanced labels, and the difficulty of preserving waveform morphology. We present a dual-branch framework that combines raw rPPG segments with handcrafted waveform features and introduces an augmentation-free contrastive pre-training strategy. The approach learns subject-invariant, domain-agnostic embeddings from unlabeled facial videos and aligns them with physiology-inspired descriptors in a shared latent space, while a distribution-aware loss reduces label imbalance. This design integrates the strengths of data-driven representations and handcrafted physiological cues, producing morphology-sensitive features that generalize across acquisition domains. Experiments on multiple datasets demonstrate that the proposed method achieves competitive accuracy under both controlled and in-the-wild conditions, improves cross-dataset transfer, and maintains robust performance when labeled data are limited. Beyond accuracy, the framework emphasizes interpretability by grounding learned embeddings in physiological features, and its reliance on unlabeled videos makes it highly scalable to larger populations without requiring extensive manual annotation. Taken together, these results suggest that bridging representation learning with physiological modeling offers a practical and scalable path toward reliable, non-contact BP monitoring in diverse real-world environments.

Multi-line laser ID assignment is crucial for underwater 3D reconstruction but fails when lines fragment. We reformulate this as a graph-based sequence labeling task and propose a novel two-stage hierarchical framework using Spatio-Temporal Graph Attention Networks (ST-GAT). Our method first reasons over a spatio-temporal graph of laser endpoints and intersections to handle local fragmentation, then elevates this to a global segment-level optimization with trajectory-constrained Viterbi decoding to ensure temporal consistency. This GNN-based approach eliminates the reliance on complete epipolar geometry. Experiments on real underwater datasets demonstrate superior reconstruction completeness and temporal stability, especially in challenging environments where traditional methods fail.

Recent text-to-image models, such as Stable Diffusion, have achieved impressive visual quality, yet they often suffer from geometric inconsistencies that undermine the structural realism of generated scenes. One prominent issue is vanishing point inconsistency, where projections of parallel lines fail to converge correctly in 2D space. This leads to structurally implausible geometry that degrades spatial realism, especially in architectural scenes. We propose ControlVP, a user-guided framework for correcting vanishing point inconsistencies in generated images. Our approach extends a pre-trained diffusion model by incorporating structural guidance derived from building contours. We also introduce geometric constraints that explicitly encourage alignment between image edges and perspective cues. Our method enhances global geometric consistency while maintaining visual fidelity comparable to the baselines. This capability is particularly valuable for applications that require accurate spatial structure, such as image-to-3D reconstruction. The dataset and source code are available at https://github.com/RyotaOkumura/ControlVP.