WACV 2026 论文列表

The creation of lifelike human avatars capable of realistic pose variation and viewpoint flexibility remains a fundamental challenge in computer vision and graphics. Current approaches typically yield either geometrically inconsistent multi-view images or sacrifice photorealism, resulting in blurry outputs under diverse viewing angles and complex motions. To address these issues, we propose Blur2Sharp, a novel framework integrating 3D-aware neural rendering and diffusion models to generate sharp, geometrically consistent novel-view images from only a single reference view. Our method employs a dual-conditioning architecture: initially, a Human NeRF model generates geometrically coherent multi-view renderings for target poses, explicitly encoding 3D structural guidance. Subsequently, a diffusion model conditioned on these renderings refines the generated images, preserving fine-grained details and structural fidelity. We further enhance visual quality through hierarchical feature fusion, incorporating texture, normal, and semantic priors extracted from parametric SMPL models to simultaneously improve global coherence and local detail accuracy. Extensive experiments demonstrate that Blur2Sharp consistently surpasses state-of-the-art techniques in both novel pose and view generation tasks, particularly excelling under challenging scenarios involving loose clothing and occlusions.

Reasoning over sequences of images remains a challenge for multimodal large language models (MLLMs). While recent models incorporate multi-image data during pre-training, they still struggle to recognize sequential structures, often treating images independently. This work introduces ImageChain, a framework that enhances MLLMs with sequential reasoning capabilities over image data by modeling visual sequences as a multi-turn conversation. In ImageChain, images are interleaved with corresponding textual descriptions to form a controlled dialogue that explicitly captures temporal dependencies and narrative progression. Our method optimizes for the task of next-scene description, where the model generates a context-aware description of an upcoming scene based on preceding visual and textual cues. We demonstrate that our approach improves performance on the next-scene description task -- achieving an average improvement from 3.7% to 19% in SimRate, a metric that quantifies semantic similarity to human-annotated ground truths. Moreover, ImageChain achieves robust zero-shot out-of-domain performance in applications ranging from comics to robotics. Extensive experiments validate that instruction-tuning in a multimodal, multi-turn conversation design is key to bridging the gap between static image understanding and temporally-aware reasoning.

Recent advances in reinforcement learning (RL) have enabled effective reward-based finetuning of text-to-image diffusion models, improving their alignment with user preferences. However, existing RL methods typically optimize only the denoising UNet while relying on fixed generation strategies, limiting their flexibility and controllability. In this work, we propose ADOPT, an adaptive diffusion policy training framework that unifies the optimization of Classifier-Free Guidance (CFG) scaling and timestep embedding modulation within a single RL paradigm. Specifically, ADOPT learns a prompt-conditioned policy to adjust the CFG strength dynamically and to modulate timestep embeddings via learnable curve-based scaling, enhancing both semantic guidance and temporal understanding of the diffusion process. Extensive experiments demonstrate that ADOPT consistently improves semantic alignment, aesthetic quality, and human preference scores across diverse prompt datasets, while maintaining efficient inference cost. Our results highlight the potential of jointly optimizing adaptive control strategies to unlock greater flexibility and performance for reward-driven diffusion generation.

We present a surface-template-free method for reconstructing dense, rigged (re-animatable) 3D models from monocular videos. By combining robust pose optimization with differentiable Gaussian splatting, this work bridges the gap between flexible template-free approaches and the visual quality of template-based methods. Starting from noisy 2D keypoints, we refine 3D poses through kinematic and temporal constraints, then attach Gaussian primitives to the optimized skeleton for differentiable supervision and rendering. We demonstrate dense, rigged (re-animatable) 3D models without surface templates across humans, animals, insects, and everyday articulated objects, and we empirically show that closing the rendering-pose loop improves 3D lifting from noisy landmarks. A key enabler of these template-free reconstructions is our kinematic optimization, which reduces 3D pose error by 20-25% relative to template-free baselines; at the same time, our results approach template-based visual metrics (PSNR/SSIM within 5%). We also demonstrate the method's practical utility by detecting and correcting geometric inconsistencies in AI-generated videos. While limited to articulated subjects with detectable keypoints, the approach provides a practical pipeline that serves as a drop-in refinement to improve 3D lifting in existing pipelines and enables the creation of rigged 3D assets from casual captures when expensive surface templates (e.g., MoCap-derived) are unavailable.

Underwater images suffer from color distortion, haziness, and low-contrast due to light absorption and scattering. Despite deep learning advances in enhancement, challenges persist in efficiency, global context modeling, spatial-spectral consistency, and perceptually accurate detail recovery. To address these challenges, we design a novel underwater image enhancement framework, D2Mamba, adopting a dual-domain information (spatial and frequency) with state space models (SSMs), enabling efficient global context modeling while preserving local details. Unlike conventional SSMs that rely on raster, bidirectional, cross or diagonal scans, D2Mamba uses an A* search guided by physics-based Geodesic Information-Field Heuristic (GIFH) scan for feature traversal based on input degradation characteristics. GIFH combines feature gradients, high-frequency heterogeneity, and low-frequency semantic distance to compute adaptive costs, enabling the capture of both spatial and spectral dependencies. Further, a Spectral Wasserstein Attenuation Loss (SWAL) is introduced to enforce distributional alignment in the spectral domain, enabling perceptually consistent and physically consistent color restoration in enhanced underwater images. Extensive experiments on benchmark datasets demonstrate that D2Mamba achieves state-of-the-art performance with only 788K parameters and 7.06 GFLOPs. The code is available at https://github.com/Alik033/D2Mamba.

Understanding human skill performance is essential for intelligent assistive systems, with struggle recognition offering a natural cue for identifying user difficulties. While prior work focuses on offline struggle classification and localization, real-time applications require models capable of detecting and anticipating struggle online. We reformulate struggle localization as an online detection task and further extend it to anticipation--predicting struggle moments before they occur. We adapt two off-the-shelf models as baselines for online struggle detection and anticipation. Online struggle detection achieves 70-80% per-frame mAP, while struggle anticipation up to 2 seconds ahead yields comparable performance with slight drops. We further examine generalization across tasks and activities and analyse the impact of skill evolution. Despite larger domain gaps in activity-level generalization, models still outperform random baselines by 4-20%. Our feature-based models run at up to 143 FPS, and the whole pipeline, including feature extraction, operates at around 20 FPS -- sufficient for real-time assistive applications.

Early-stage fruit yield prediction plays a key role in supporting timely agronomic decisions, enhancing market planning, and empowering farmers with data-driven insights. Over the years, most approaches to yield estimation have focused on fruit counting techniques, typically performed just before harvest. While these methods have proven useful, they often come into play late in the cultivation cycle, limiting their impact on early planning and resource optimization. In this work, we introduce a comprehensive baseline framework for predicting mango yield at an earlier stage - during flowering - using image-based learning. Our contributions are twofold. (i) Our approach combines a SegFormer-based segmentation model with a regression pipeline to estimate yield from images, while also exploring the role of contextual features such as weather and scale. (ii) This work introduces a novel benchmark and an enriched dataset, paving the way for scalable, automated tools that can assist farmers and stakeholders in making proactive decisions throughout the mango growing season. Our work demonstrates that for multi-modal yield prediction, integrating features that complement visual representations (like scale) can be more impactful than using features with a stronger standalone linear correlation (like weather). Our single-image model, based on the SegFormer-B1 encoder, achieved a mean absolute error (MAE) of 7.68, R2 of 0.76, and mean squared error (MSE) of 115.48. These results highlight the promise of vision-based models for yield estimation from early-stage flowering cues. To the best of our knowledge, this is the first work to address the prediction of mango yield using images from the flowering stage and weather data.

Wildlife re-identification (Re-ID) is critical for non-invasive monitoring. Yet, animal Re-ID performances remain far behind person Re-ID due to limited datasets and a greater fine-grained appearance variability between individuals. One strategy is to adopt part-based methods in order to more precisely attend to distinct anatomical regions. To adapt to animal Re-ID, we propose PAW-ViT (Part-AWare animal re-identification Vision Transformer), a ViT that replaces the standard classification token with K learnable part tokens, each specialized to a specific anatomical region of the animal. Spatial specialization is achieved via feature-based knowledge distillation by training each token's attention to image patches to produce a semantic segmentation mask. An additional aggregation token fuses the part embeddings into a single part-aware descriptor. Trained with a multi-task loss, PAW-ViT outperforms state-of-the-art methods in animal Re-ID on ATRW (Amur tigers) and YakREID-103 (yaks), particularly in scenarios of strong viewpoint variations like the cross-camera setting.

In this paper, we introduce zero-shot audio-video editing, a novel task that requires transforming original audio-visual content to align with a specified textual prompt without additional model training. To evaluate this task, we curate a benchmark dataset, AVED-Bench, designed explicitly for zero-shot audio-video editing. AVED-Bench includes 110 videos, each with a 10-second duration, spanning 11 categories from VGGSound. It offers diverse prompts and scenarios that require precise alignment between auditory and visual elements, enabling robust evaluation. We identify limitations in existing zero-shot audio and video editing methods, particularly in synchronization and coherence between modalities, which often result in inconsistent outcomes. To address these challenges, we propose AVED, a zero-shot cross-modal delta denoising framework that leverages audio-video interactions to achieve synchronized and coherent edits. AVED demonstrates superior results on both AVED-Bench and the recent OAVE dataset to validate its generalization capabilities. Our codes, data, and results are available at https://genjib.github.io/project_page/AVED/index.html

Medical image analysis increasingly relies on the integration of multiple imaging modalities to capture complementary anatomical and functional information, enabling more accurate diagnosis and treatment planning.Achieving aligned feature representations across these diverse modalities is therefore important for effective multimodal analysis.While contrastive language-image pre-training (CLIP) and its variant have enabled image-text alignments, they require explicitly paired data between arbitrary two modalities, which is difficult to acquire in medical contexts. To address the gap, we present Multimodal Medical Image Binding with Text (M^3Bind), a novel pre-training framework that enables seamless alignment of multiple medical imaging modalities through a shared text representation space without requiring explicit paired data between any two medical image modalities.Specifically, based on the insight that different images can naturally bind with text, M^3Bind first fine-tunes pre-trained CLIP-like image-text models, which are derived from different medical modalities, to align their modality-specific text embedding space while preserving their original image-text alignments. Subsequently, we distill these modality-specific text encoders into a unified model, creating a shared text embedding space.Notably, M^3Bind is a flexible framework in which the selection of CLIP-like models is not fixed and can be adapted according to the requirements of the task.Experiments on X-ray, CT, retina, ECG, and pathological images on multiple downstream tasks demonstrate that M^3Bind achieves competitive or even superior performance in zero-shot, few-shot classification and cross-modal retrieval tasks compared to its CLIP-like counterparts.These results validate M^3Bind's effectiveness in achieving cross-image-modal alignment for medical analysis.

Underwater object tracking is challenging due to wavelength-dependent attenuation and scattering, which severely distort appearance across depths and water conditions. Existing trackers trained on terrestrial data fail to generalize to these physics-driven degradations. We present MANTA, a physics-informed framework integrating representation learning with tracking design for underwater scenarios. We propose a dual-positive contrastive learning strategy coupling temporal consistency with Beer--Lambert augmentations to yield features robust to both temporal and underwater distortions. We further introduce a multi-stage pipeline augmenting motion-based tracking with a physics-informed secondary association algorithm that integrates geometric consistency and appearance similarity for re-identification under occlusion and drift. To complement standard IoU metrics, we propose Center-Scale Consistency (CSC) and Geometric Alignment Score (GAS) to assess geometric fidelity. Experiments on four underwater benchmarks (WebUOT-1M, UOT32, UTB180, UWCOT220) show that MANTA achieves state-of-the-art performance, improving Success AUC by up to 6%, while ensuring stable long-term generalized underwater tracking and efficient runtime. Code available at https://github.com/Kazedaa/MANTA.

Personalized expression recognition (ER) involves adapting a machine learning model to subject-specific data for improved recognition of expressions with considerable interpersonal variability. Subject-specific ER can benefit significantly from multi-source domain adaptation (MSDA) methods - where each domain corresponds to a specific subject - to improve model accuracy and robustness. Despite promising results, state-of-the-art MSDA approaches often overlook multimodal information or blend sources into a single domain, limiting subject diversity and failing to explicitly capture unique subject-specific characteristics. To address these limitations, we introduce MuSACo, a multimodal subject-specific selection and adaptation method for ER based on co-training. It leverages complementary information across multiple modalities and multiple source domains for subject-specific adaptation. This makes MuSACo particularly relevant for affective computing applications in digital health, such as patient-specific assessment for stress or pain, where subject-level nuances are crucial. MuSACo selects source subjects relevant to the target and generates pseudo-labels using the dominant modality for class-aware learning, in conjunction with a class-agnostic loss to learn from less confident target samples. Finally, source features from each modality are aligned, while only confident target features are combined. Experimental results on challenging multimodal ER datasets - BioVid, StressID, and BAH - show that MuSACo outperforms UDA (blending) and state-of-the-art MSDA methods.

State-of-the-art semantic segmentation models are typically optimized in a data-driven fashion, minimizing solely per-pixel or per-segment classification objectives on their training data. This purely data-driven paradigm often leads to absurd segmentations, especially when the domain of input images is shifted from the one encountered during training. For instance, state-of-the-art models may assign the label "road" to a segment that is included by another segment that is respectively labeled as "sky". However, the ground truth of the existing dataset at hand dictates such inclusion is not feasible. Our method, Infeasible Semantic Inclusions (InSeIn), first extracts explicit inclusion constraints that govern spatial class relations from the semantic segmentation training set at hand in an offline, data-driven fashion, and then enforces a morphological yet differentiable loss that penalizes violations of these constraints during training to promote prediction feasibility. InSeIn is a light-weight plug-and-play method, constitutes a novel step towards minimizing infeasible semantic inclusions in the predictions of learned segmentation models, and yields consistent and significant performance improvements over diverse state-of-the-art networks across the ADE20K, Cityscapes, and ACDC datasets. Code and models will be made publicly available.

Parasitic infections remain a pressing global health challenge, particularly in low-resource settings where diagnosis still depends on labor-intensive manual inspection of blood smears and the availability of expert domain knowledge. While deep learning models have shown strong performance in automating parasite detection, their clinical usefulness is constrained by limited interpretability. Existing explainability methods are largely restricted to visual heatmaps or attention maps, which highlight regions of interest but fail to capture the morphological traits that clinicians rely on for diagnosis. In this work, we present MorphXAI, an explainable framework that unifies parasite detection with fine-grained morphological analysis. MorphXAI integrates morphological supervision directly into the prediction pipeline, enabling the model to localize parasites while simultaneously characterizing clinically relevant attributes such as shape, curvature, visible dot count, flagellum presence, and developmental stage. To support this task, we curate a clinician-annotated dataset of three parasite species (Leishmania, Trypanosoma brucei, and Trypanosoma cruzi) with detailed morphological labels, establishing a new benchmark for interpretable parasite analysis. Experimental results show that MorphXAI not only improves detection performance over the baseline but also provides structured, biologically meaningful explanations.

Hallucinations remain a central challenge in multimodal large language models (MLLMs), where models generate incorrect or fabricated information not present in the input. Existing benchmarks assess hallucinations only at the image level and lack a holistic object-level evaluation of types, attributes, and relations for multiple individual objects within the image. To address this limitation, we introduce GHOST, a benchmark that focuses on evaluating hallucinations at the object level. GHOST offers a fine-grained assessment by evaluating compositional triplets -- combinations of object types, attributes, and relations tied together for objects within images. We also propose a multi-round consistency-based evaluation framework and introduce the GHOST Consistency Score, a novel metric based on consistency checks using both positive (true) and hard negative (false) statements about the same object. This approach better captures hallucination tendencies by penalizing inconsistent and contradicting responses. Our benchmark includes 760 images and offers a comprehensive dataset of 38,076 questions for comprehensive hallucination evaluation. We conduct extensive experiments on 20 state-of-the-art MLLMs, including GPT-4o and Gemini-1.5-Pro and we reveal significant gaps in object-level understanding and consistency. Our analysis emphasizes the necessity of object-centric evaluation and provides valuable insights into MLLM vision encoders and their sizes in applications where accuracy and reliability are critical. Code and dataset: https://vibashan.github.io/ghost-web

Encoder-free multimodal large language models (MLLMs) eliminate the need for a well-trained vision encoder by directly processing image tokens before the language model. While this approach reduces computational overhead and model complexity, it often requires large amounts of training data to effectively capture the visual knowledge typically encoded by vision models like CLIP. The absence of a vision encoder implies that the model is likely to rely on substantial data to learn the necessary visual-semantic alignments. In this work, we present BREEN, a data-efficient encoder-free multimodal architecture that mitigates this issue. BREEN leverages a learnable query and image experts to achieve comparable performance with significantly less training data. The learnable query, positioned between image and text tokens, is supervised by the output of a pretrained CLIP model to distill visual knowledge, bridging the gap between visual and textual modalities. Additionally, the image expert processes image tokens and learnable queries independently, improving efficiency and reducing interference with the LLM's textual capabilities. BREEN achieves comparable performance to prior encoder-free state-of-the-art models like Mono-InternVL, using only 13 million text-image pairs in training--about one percent of the data required by existing methods. Our work highlights a promising direction for data-efficient encoder-free multimodal learning, offering an alternative to traditional encoder-based approaches.

Counterfeiting affects diverse industries, including pharmaceuticals, electronics, and food, posing serious health and economic risks. Printable unclonable codes, such as Copy Detection Patterns (CDPs), are widely used as an anti-counterfeiting measure and are applied to products and packaging. However, the increasing availability of high-resolution printing and scanning devices, along with advances in generative deep learning, undermines traditional authentication systems, which often fail to distinguish high-quality counterfeits from genuine prints. In this work, we propose a diffusion-based authentication framework that jointly leverages the original binary template, the printed CDP, and a representation of printer identity that captures relevant semantic information. Formulating authentication as multi-class printer classification over printer signatures lets our model capture fine-grained, device-specific features via spatial and textual conditioning. We extend ControlNet by repurposing the denoising process for class-conditioned noise prediction, enabling effective printer classification. On the Indigo 1x1 Base dataset, our method outperforms traditional similarity metrics and prior deep learning approaches. Results show the framework generalizes to counterfeit types unseen during training.

Multi-weather image restoration seeks to recover scene visibility under rainy, snowy, and hazy conditions, thereby enhancing high-level vision tasks. Existing methods typically train on combined datasets with single-type weather degradations, limiting their generalization to real-world scenarios involving mixed degradations. Domain translation has emerged as a viable solution by generating diverse weather-degraded variants of the same scene. However, current approaches require separate models for each degradation type, resulting in increased system complexity. To address this, we propose DTMIR-Pro, a prompt-based domain translation framework with latent space generalization for multi-weather image restoration. A single trainable network performs multi-domain translation using domain-adaptive prompts and dynamic kernel selection via a proposed Dynamic Multi-Head Attention block to learn diverse degradation patterns. The restoration network takes translated outputs and employs a Multi-Weather Fusion Block with global-local feature streams to capture complex degradations. Furthermore, we introduce a Similarity-Based Encoder Routing mechanism to transfer domain-specific features from the translation encoder to the restoration stage. Extensive experiments on both synthetic and real-world weather-degraded datasets demonstrate the effectiveness and generalizability of the proposed method. The code is made available at https://github.com/AshutoshKulkarni4998/DTMIR-Pro.

Vision encoders power modern vision-only and vision-language systems, yet the geometry of their internal features remains opaque. In this work, we introduce a simple, general approach for vision latent analysis: reconstruct images from frozen encoder features and treat reconstructability as a proxy for retained information and feature organization. Concretely, we train a lightweight reconstructor to invert feature tensors and use it to compare various vision encoders -- CLIP-based ViT, SigLIP, SAM, and InternViT. We rank models by the informativeness of their features and observe consistent gains with image-centric objectives and higher spatial resolution. Beyond measurement, controlled manipulations in feature space produce predictable pixel-level edits: orthogonal rotations (rather than spatial transformations) implement channel permutations and drive systematic color changes; linear contractions implement channel suppression; and a learned linear map enables plausible colorization of grayscale inputs. VLM-based experiments confirm that feature-space color swaps translate into semantic color changes in reconstructions. Our approach is encoder-agnostic in principle (demonstrated on ViT-based models), requires only access to features, and offers a practical diagnostic of what encoders remember, how that information is organized, and how it can be manipulated.