WACV 2026 Papers

The increasing availability of Earth observation data offers unprecedented opportunities for large-scale environmental monitoring and analysis. However, these datasets are inherently heterogeneous, stemming from diverse sensors, geographical regions, acquisition times, and atmospheric conditions. Distribution shifts between training and deployment domains severely limit the generalization of pretrained remote sensing models, making unsupervised domain adaptation (UDA) crucial for real-world applications.We introduce FlowEO, a novel framework that leverages generative models for image-space UDA in Earth observation. We leverage flow matching to learn a semantically preserving mapping that transports from the source to the target image distribution. This allows us to tackle challenging domain adaptation configurations for classification and semantic segmentation of Earth observation images. We conduct extensive experiments across four datasets covering adaptation scenarios such as SAR to optical translation and temporal and semantic shifts caused by natural disasters.Experimental results demonstrate that FlowEO outperforms existing image translation approaches for domain adaptation while achieving on-par or better perceptual image quality, highlighting the potential of flow-matching-based UDA for remote sensing.

We introduce VectorSynth, a diffusion-based framework for pixel-accurate satellite image synthesis conditioned on polygonal geographic annotations with semantic attributes. Unlike prior text- or layout-conditioned models, VectorSynth learns dense cross-modal correspondences that align imagery and semantic vector geometry, enabling fine-grained, spatially grounded edits. A vision language alignment module produces pixel-level embeddings from polygon semantics; these embeddings guide a conditional image generation framework to respect both spatial extents and semantic cues. VectorSynth supports interactive workflows that mix language prompts with geometry-aware conditioning, allowing rapid what-if simulations, spatial edits, and map-informed content generation. For training and evaluation, we assemble a collection of satellite scenes paired with pixel-registered polygon annotations spanning diverse urban scenes with both built and natural features. We observe strong improvements over prior methods in semantic fidelity and structural realism, and show that our trained vision language model demonstrates fine-grained spatial grounding. Code and data will be released.

The rapid growth of e-commerce has intensified the demand for Virtual Try-On (VTO) technologies, enabling customers to realistically visualize products overlaid on their own images. Despite recent advances, existing VTO models face challenges with fine-grained detail preservation, robustness to real-world imagery, efficient sampling, image editing capabilities, and generalization across diverse product categories. In this paper, we present DiT-VTON, a novel VTO framework that leverages an architecture based on a Diffusion Transformer (DiT), renowned for its performance on text-conditioned image generation (text-to-image), adapted here for the image-conditioned VTO task. We systematically explore multiple DiT configurations, including in-context token concatenation, channel concatenation, and ControlNet integration, to determine the best setup for VTO image conditioning. To enhance robustness, we train the model on an expanded dataset encompassing varied backgrounds, unstructured references, and non-garment categories, demonstrating the benefits of data scaling for VTO adaptability. DiT-VTON also redefines the VTO task beyond garment try-on, offering a versatile Virtual Try-All (VTA) solution capable of handling a wide range of product categories and supporting advanced image editing functionalities, such as pose preservation, precise localized region editing and refinement, texture transfer and object-level customization. Experimental results show that our model surpasses state-of-the-art methods on public benchmark tests like VITON-HD on the VTO task, achieving superior detail preservation and robustness without reliance on additional image condition encoders. It also surpasses state-of-the-art models that have VTA and image editing capabilities on a varied dataset composed of thousands of product categories. As a result, DiT-VTON significantly advances VTO applicability in diverse real-world scenarios, enhancing both the realism and personalization of online shopping experiences.

Face anti-spoofing (FAS) is essential for protecting facial-biometric systems from presentation attacks. We propose WSSSP-Net, a Weakly Supervised Semantic Segmentation Plugin Network that integrates a lightweight, attention-based segmentation decoder at multiple depths of any CNN or transformer encoder. Serving only as an auxiliary training-time module, the decoder guides feature learning without increasing inference runtime. Pixel-wise spoof masks are automatically generated via a face-parsing pipeline, removing the need for manual annotations and enabling multiscale spoof-aware feature refinement. In leave-one-out evaluations on leading FAS benchmarks, WSSSP-Net reduces HTER by up to 24.9% and increases AUC by up to 3.2% over state-of-the-art methods. In out-of-distribution tests on a separate dataset, it lowers HTER by up to 18.4%. Across attack classes, it reduces average APCER by up to 12.9% and BPCER by up to 12.4%, achieving all improvements without added inference cost.

We present the first cross-modality distillation framework specifically tailored for single-panoramic-camera Bird's-Eye-View (BEV) segmentation. Our approach leverages a novel LiDAR image representation fused from range, intensity and ambient channels, together with a voxel-aligned view transformer that preserves spatial fidelity while enabling efficient BEV processing. During training, a high-capacity LiDAR and camera fusion Teacher network extracts both rich spatial and semantic features for cross-modality knowledge distillation into a lightweight Student network that relies solely on a single 360-degree panoramic camera image. Extensive experiments on the Dur360BEV dataset demonstrate that our teacher model significantly outperforms existing camera-based BEV segmentation methods, achieving a 25.6% IoU improvement. Meanwhile, the distilled Student network attains competitive performance with an 8.5% IoU gain and state-of-the-art inference speed of 31.2 FPS. Moreover, evaluations on KITTI-360 (two fisheye cameras) confirm that our distillation framework generalises to diverse camera setups, underscoring its feasibility and robustness. This approach reduces sensor complexity and deployment costs while providing a practical solution for efficient, low-cost BEV segmentation in real-world autonomous driving. The code is available at: https://github.com/Tom-E-Durham/KD360-VoxelBEV.

Real-time multi-label video classification on embedded devices is constrained by limited compute and energy budgets. Yet, video streams exhibit structural properties such as label sparsity, temporal continuity, and label co-occurrence that can be leveraged for more efficient inference. We introduce Polymorph, a context-aware framework that activates a minimal set of lightweight Low Rank Adapters (LoRA) per frame. Each adapter specializes in a subset of classes derived from co-occurrence patterns and is implemented as a LoRA weight over a shared backbone. At runtime, Polymorph dynamically selects and composes only the adapters needed to cover the active labels, avoiding full-model switching and weight merging. This modular strategy improves scalability while reducing latency, and energy overhead. Polymorph achieves 40% lower energy consumption and improves mAP by 9 points over strong baselines executing the TAO dataset.

Recent advances in text-to-3D scene generation have demonstrated significant potential to transform content creation across multiple industries. Although the research community has made impressive progress in addressing the challenges of this complex task, existing methods often generate environments that are only front-facing, lack visual fidelity, exhibit limited scene understanding, and are typically fine-tuned for either indoor or outdoor settings. In this work, we address these issues and propose DreamAnywhere, a modular system for the fast generation and prototyping of 3D scenes. Our system synthesizes a 360deg panoramic image from text, decomposes it into background and objects, constructs a complete 3D representation through hybrid inpainting, and lifts object masks to detailed 3D objects that are placed in the virtual environment. DreamAnywhere supports immersive navigation and intuitive object-level editing, making it ideal for scene exploration, visual mock-ups, and rapid prototyping -- all with minimal manual modeling. These features make our system particularly suitable for low-budget movie production, enabling quick iteration on scene layout and visual tone without the overhead of traditional 3D workflows. Our modular pipeline is highly customizable as it allows components to be replaced independently. Compared to current state-of-the-art text and image-based 3D scene generation approaches, DreamAnywhere shows significant improvements in coherence in novel view synthesis and achieves competitive image quality, demonstrating its effectiveness across diverse and challenging scenarios. A comprehensive user study demonstrates a clear preference for our method over existing approaches, validating both its technical robustness and practical usefulness.

Intracranial aneurysms are a major cause of morbidity and mortality worldwide, and detecting them manually is a complex, time-consuming task. Albeit automated solutions are desirable, the limited availability of training data makes it difficult to develop such solutions using typical supervised learning frameworks. In this work, we propose a novel pre-training strategy using more widely available unannotated head CT scan data to pre-train a 3D Vision Transformer model prior to fine-tuning for the aneurysm detection task. Specifically, we modify masked auto-encoder (MAE) pre-training in the following ways: we use a factorized self-attention mechanism to make 3D attention computationally viable, we restrict the masked patches to areas near arteries to focus on areas where aneurysms are likely to occur, and we reconstruct not only CT scan intensity values but also artery distance maps, which describe the distance between each voxel and the closest artery, thereby enhancing the backbone's learned representations. Compared with SOTA aneurysm detection models, our approach gains +2-7% absolute Sensitivity at a false positive rate of 0.5. Code and weights will be released.

Vision Language Models (VLMs) mix visual tokens and text tokens. A puzzling issue is the fact that visual tokens most related to the query receive little to no attention in the final layers of the LLM module of VLMs from the answer tokens, where all tokens are treated equally, in particular, visual and language tokens in the LLM attention layers. This fact may result in wrong answers to visual questions, as our experimental results confirm. It appears that the standard next-token prediction (NTP) loss provides an insufficient signal for directing attention to visual tokens. We hypothesize that a more direct supervision of the attention of visual tokens to corresponding language tokens in the LLM module of VLMs will lead to improved performance on visual tasks. To demonstrate that this is indeed the case, we propose a novel loss function that directly supervises the attention of visual tokens. It directly grounds the answer language tokens in images by directing their attention to the relevant visual tokens. This is achieved by aligning the attention distribution of visual tokens to ground truth attention maps with KL divergence. The ground truth attention maps are obtained from task geometry in synthetic cases or from standard grounding annotations (e.g., bounding boxes or point annotations) in real images, and are used inside the LLM for attention supervision without requiring new labels. The obtained KL attention loss (KLAL) when combined with NTP encourages VLMs to attend to relevant visual tokens while generating answer tokens. This results in notable improvements across geometric tasks, pointing, and referring expression comprehension on both synthetic and real-world data, as demonstrated by our experiments. We also introduce a new dataset to evaluate the line tracing abilities of VLMs. Surprisingly, even commercial VLMs do not perform well on this task.

Incorporating generated annotated data into training sets can improve object detection. Prior approaches either condition image generation on annotation layouts, limiting diversity and often causing misalignment, or generate images independently and annotate them afterward, reducing accuracy. We introduce a diffusion model that jointly generates images and annotations, enabling their co-evolution and mutual dependency throughout the process. This design achieves tight image-annotation alignment and produces diverse scenarios beyond the original training set, enhancing object detection performance when used in training.

We propose Nexus Adapters, a novel family of text-guided and efficient adapters designed for diffusion-based Structure Preserving Conditional Generation (SPCG). Existing structure-preserving methods typically rely on using a base diffusion model conditioned on a prompt and a separate adapter for structural inputs like sketches or depth maps. However, such approaches are computationally expensive, often requiring adapter sizes comparable to the base model, making training impractical due to the already high cost of diffusion models. Moreover, traditional adapters operate independently of the input prompt, making them suboptimal for capturing the semantic alignment between textual and structural cues. To address these limitations, we introduce Nexus Prime and Nexus Slim, two prompt-aware adapters that jointly leverage both text and structural inputs. These adapters are composed of modular Nexus Blocks that utilize cross-attention mechanisms to enable effective multimodal conditioning. As a result, the adapters can maintain structural fidelity while aligning more closely with the intended textual prompt. Experimental results demonstrate that Nexus Prime significantly improves performance with only 8M additional parameters over the minimal T2I baseline. Additionally, Nexus Slim, a lightweight variant with 18M fewer parameters than T2I, still achieves competitive, state-of-the-art results--validating the efficiency and effectiveness of our proposed design.

Surgery continues to be perceived as an art, where proficiency is primarily achieved through years of experience. Artificial Intelligence research has yielded insight into the performance of expert surgeons and their associations with patient outcomes. Clinician expertise has led to the development of systematic assessments for fundamental skills (e.g., End-to-End Assessment of Suturing Expertise [EASE]) that contribute to positive outcomes. However, evaluating these skills requires manual expert review of endoscopic videos and is prone to inconsistencies between human raters. In this work, we present AutoEASE, the first end-to-end pipeline to automatically assess suturing performance from raw endoscopic video data using EASE rubrics. Our system utilizes a Mixture of Expert models (MoE) ; Multiscale vision transformers and 3D convolutional neural networks trained on Robot-assisted Radical Prostatectomy videos with over 13000 data points. For a given stitch clip, the MoE pipeline first determines each phase (needle handling, driving, withdrawal) of a continuous stitch and predicts a binary score (fail / ideal) for seven sub-skills based on rubrics defined in EASE. AutoEASE achieves 0.98 AUC while detecting each stitch phase. For EASE score prediction, the complete end-to-end pipeline attains >= 0.77 AUC in sub-skills associated with needle handling and driving. The promising performance of AutoEASE at the individual stitch level demonstrates the feasibility of developing more sophisticated assessment and reporting tools for complete surgical procedures objectively and at scale.

Visual prompt-based detection enables generalization to arbitrary novel instances in the target image by using one or a few visual templates. Previous methods rely on complex relation or explicit feature matching modules, and their designs are deeply coupled with specific detectors, greatly limiting their applicability. Instead, we propose our `Any Detector can Detect Anything' framework that can enable any detector to detect any object given a single or a few visual templates. Specifically, we design an adapter called Template-Aware Adapter that can be added on top of any existing detector architecture to inject visual template information directly into the detection features. After integration, localization is done on the feature maps as in standard object detectors, effectively transforming any detector into a visual prompt-based detector. Furthermore, we revisit current visual prompt detection benchmarks and correct their unrealistic test assumptions and class splits, which limit the usability of the developed algorithms in the real world. We introduce a set of realistic benchmarks to remedy these issues. We comprehensively evaluate the proposed model on both existing and our new benchmarks, outperforming current state-of-the-art one-shot and few-shot detection methods by a large margin.

Zero-shot Composed Image Retrieval (ZS-CIR) enables image search using a reference image and a text prompt without requiring specialized text-image composition networks trained on large-scale paired data. However, current ZS-CIR approaches suffer from three critical limitations in their reliance on composed text embeddings: static query embedding representations, insufficient utilization of image embeddings, and suboptimal performance when fusing text and image embeddings. To address these challenges, we introduce the Prompt Directional Vector (PDV), a simple yet effective training-free enhancement that captures semantic modifications induced by user prompts. PDV enables three key improvements: (1) Dynamic composed text embeddings where prompt adjustments are controllable via a scaling factor, (2) composed image embeddings through semantic transfer from text prompts to image features, and (3) weighted fusion of composed text and image embeddings that enhances retrieval by balancing visual and semantic similarity. Our approach serves as a plug-and-play enhancement for existing ZS-CIR methods with minimal computational overhead. Extensive experiments across multiple benchmarks demonstrate that PDV consistently improves retrieval performance when integrated with state-of-the-art ZS-CIR approaches, particularly for methods that generate accurate compositional embeddings. The code will be released upon publication.

We study the problem of self-supervised procedure learning, which discovers key steps and establishes their order from a set of unlabeled procedural videos. Previous procedure learning methods typically learn frame-to-frame correspondences between videos before determining key steps and their order. However, their performance often suffers from order variations, background/redundant frames, and repeated actions. To overcome these challenges, we propose a self-supervised procedure learning framework, which utilizes a fused Gromov-Wasserstein optimal transport formulation with a structural prior for computing frame-to-frame mapping between videos. However, optimizing exclusively for the above temporal alignment term may lead to degenerate solutions, where all frames are mapped to a small cluster in the embedding space and hence every video is associated with only one key step. To address that limitation, we further integrate a contrastive regularization term, which maps different frames to different points in the embedding space, avoiding the collapse to trivial solutions. Finally, we conduct extensive experiments on large-scale egocentric (i.e., EgoProceL) and third-person (i.e., ProceL and CrossTask) benchmarks to demonstrate superior performance by our approach against previous methods, including OPEL which relies on a traditional Kantorovich optimal transport formulation with an optimality prior.

Differentiating between cardiac and pulmonary diseases in emergency settings presents a significant challenge due to overlapping symptoms like dyspnea and chest pain, where misdiagnosis can lead to inappropriate interventions and increased morbidity. While electrocardiograms (ECGs) and chest X-rays (CXRs) provide complementary diagnostic information, existing multimodal fusion approaches fail to fully capture the complex relationships between these fundamentally different data modalities. To address these limitations, we propose DDMF-Net, a Dual-Domain Multimodal Fusion Network that explicitly unifies multi-domain features--from both frequency and spatial/temporal perspectives--and conducts cross-modality fusion of ECG, CXR signals and clinical parameters in hyperbolic space, thereby enhancing the modeling of complex cardiopulmonary pathophysiology. Our framework contains three innovations: (1) a frequency fusion module that captures complementary spectral patterns across modalities, (2) an inter-domain fusion module that dynamically balances domain-specific features, and (3) a hyperbolic cross-attention module with soft-entailment loss that effectively models hierarchical relationships between low-level imaging/signal data and high-level clinical parameters. Evaluated on four MIMIC datasets, DDMF-Net achieves state-of-the-art performance with over 2.9% improvement in micro-AUC, enabling more accurate differentiation of cardiac and pulmonary conditions in time-sensitive emergency settings. Code is publicly available at https://github.com/ kknankk/DDMF_Net.

We introduce a robust event-centric encoder that expands the practical reach of event-based data across diverse tasks. To overcome the scarcity of large-scale event datasets, our approach adapts CLIP's representation space to the event domain, preserving zero-shot learning and text alignment while mitigating catastrophic forgetting. By explicitly aligning event and image embeddings, the proposed encoder retains CLIP's core strengths and delivers competitive performance on object recognition as well as zero-shot and few-shot benchmarks. Moreover, it generalizes effectively to event streams derived from video datasets without additional training. Finally, we show that the encoder integrates seamlessly into cross-modal architectures, enabling accurate event-image retrieval and unlocking new applications for the event modality.

Cross-modality medical image segmentation is critical for diagnosis and treatment planning, yet domain shifts and source data restrictions pose significant challenges. This paper introduces Zero-LEAD, the first unified framework for source-free universal domain adaptation (SF-UniDA) in segmentation, addressing all four UDA scenarios, closed-set, partial-set, open-set, and universal-set, without access to source data. Zero-LEAD integrates (1) Label-Efficient Adaptive Decomposition (LEAD) to decompose features into source-known and source-unknown components, and (2) a zero-shot segmentation module leveraging anatomical priors and semantic attributes to segment novel target classes.Extensive experiments across four datasets, Synapse, CHAOS, BTCV, and FLARE22, demonstrate strong performance across all adaptation settings. Zero-LEAD achieves 0.9159 Dice in closed-set (Synapse->CHAOS), 0.8721 Dice in partial-set (BTCV->CHAOS), 0.7801 Dice in open-set (Synapse->BTCV), and 0.7716/0.6866 Dice in universal-set (BTCV\leftrightarrowFLARE22), significantly outperforming state-of-the-art baselines. Ablation studies confirm the complementary contributions of LEAD and zero-shot modules, and qualitative analysis highlights improved boundary precision and robustness under both domain and label shifts.

Spiking Neural Networks (SNNs) are increasingly studied as energy-efficient alternatives to Convolutional Neural Networks (CNNs), particularly for edge intelligence. However, prior work has largely emphasized large-scale models, leaving the design and evaluation of lightweight CNN-to-SNN pipelines underexplored. In this paper, we present the first systematic benchmark of lightweight SNNs obtained by converting compact CNN architectures into spiking networks, where activations are modeled with Leaky-Integrate-and-Fire (LIF) neurons and trained using surrogate gradient descent under a unified setup. We construct spiking variants of ShuffleNet, SqueezeNet, MnasNet, and MixNet, and evaluate them on CIFAR-10, CIFAR-100, and TinyImageNet, measuring accuracy, F1-score, parameter count, computational complexity, and energy consumption. Our results show that SNNs can achieve up to 15.7x higher energy efficiency than their CNN counterparts while retaining competitive accuracy. Among these, the SNN variant of SqueezeNet consistently outperforms other lightweight SNNs. To further optimize this model, we apply a structured pruning strategy that removes entire redundant fire modules, yielding a pruned architecture, SNN SqueezeNet-P. This pruned model improves CIFAR-10 accuracy by 6% and reduces parameters by 19% compared to the original SNN SqueezeNet. Crucially, it narrows the gap with CNN SqueezeNet, achieving nearly the same accuracy (only 1% lower) but with an 88.1% reduction in energy consumption due to sparse spike-driven computations. Together, these findings establish lightweight SNNs as practical, low-power alternatives for edge deployment, highlighting a viable path toward deploying high-performance, low-power intelligence on the edge. Code available at GitHub: Pruned-Spiking-SqueezeNet