Fresh from the feed

arXiv:2504.10825v2 Announce Type: replace Abstract: In this paper, we propose a novel framework for controllable video diffusion, OmniVDiff , aiming to synthesize and comprehend multiple video visual content in a single diffusion model. To achieve this, OmniVDiff treats all video visual modalities in the color space to learn a joint distribution, while employing an adaptive control strategy that dynamically adjusts the role of each visual modality during the diffusion process, either as a generation modality or a conditioning modality. Our framework supports three key capabilities: (1) Text-conditioned video generation, where all modalities are jointly synthesized from a textual prompt; (2) Video understanding, where structural modalities are predicted from rgb inputs in a coherent manner; and (3) X-conditioned video generation, where video synthesis is guided by finegrained inputs such as depth, canny and segmentation. Extensive experiments demonstrate that OmniVDiff achieves state-of-the-art performance in video generation tasks and competitive results in video understanding. Its flexibility and scalability make it well-suited for downstream applications such as video-to-video translation, modality adaptation for visual tasks, and scene reconstruction.

arXiv:2504.12197v2 Announce Type: replace Abstract: As AI systems grow more capable, it becomes increasingly important that their decisions remain understandable and aligned with human expectations. A key challenge is the limited interpretability of deep models. Post-hoc methods like GradCAM offer heatmaps but provide limited conceptual insight, while prototype-based approaches offer example-based explanations but often rely on rigid region selection and lack semantic consistency. To address these limitations, we propose PCMNet, a part-prototypical concept mining network that learns human-comprehensible prototypes from meaningful image regions without additional supervision. By clustering these prototypes into concept groups and extracting concept activation vectors, PCMNet provides structured, concept-level explanations and enhances robustness to occlusion and challenging conditions, which are both critical for building reliable and aligned AI systems. Experiments across multiple image classification benchmarks show that PCMNet outperforms state-of-the-art methods in interpretability, stability, and robustness. This work contributes to AI alignment by enhancing transparency, controllability, and trustworthiness in AI systems. Our code is available at: https://github.com/alehdaghi/PCMNet.

arXiv:2504.14290v2 Announce Type: replace Abstract: Content safety is a fundamental challenge for text-to-image (T2I) models, yet prevailing methods enforce a debilitating trade-off between safety and generation quality. We argue that mitigating this trade-off hinges on addressing systemic challenges in current T2I safety alignment across data, methods, and evaluation protocols. To this end, we introduce a unified framework for synergistic safety alignment. First, to overcome the flawed data paradigm that provides biased optimization signals, we develop LibraAlign-100K, the first large-scale dataset with dual annotations for safety and quality. Second, to address the myopic optimization of existing methods focus solely on safety reward, we propose Synergistic Preference Optimization (T2I-SPO), a novel alignment algorithm that extends the DPO paradigm with a composite reward function that integrates generation safety and quality to holistically model user preferences. Finally, to overcome the limitations of quality-agnostic and binary evaluation in current protocols, we introduce the Unified Alignment Score, a holistic, fine-grained metric that fairly quantifies the balance between safety and generative capability. Extensive experiments demonstrate that T2I-SPO achieves state-of-the-art safety alignment against a wide range of NSFW concepts, while better maintaining the model's generation quality and general capability

arXiv:2504.14717v3 Announce Type: replace Abstract: We introduce TAPIP3D, a novel approach for long-term 3D point tracking in monocular RGB and RGB-D videos. TAPIP3D represents videos as camera-stabilized spatio-temporal feature clouds, leveraging depth and camera motion information to lift 2D video features into a 3D world space where camera movement is effectively canceled out. Within this stabilized 3D representation, TAPIP3D iteratively refines multi-frame motion estimates, enabling robust point tracking over long time horizons. To handle the irregular structure of 3D point distributions, we propose a 3D Neighborhood-to-Neighborhood (N2N) attention mechanism - a 3D-aware contextualization strategy that builds informative, spatially coherent feature neighborhoods to support precise trajectory estimation. Our 3D-centric formulation significantly improves performance over existing 3D point tracking methods and even surpasses state-of-the-art 2D pixel trackers in accuracy when reliable depth is available. The model supports inference in both camera-centric (unstabilized) and world-centric (stabilized) coordinates, with experiments showing that compensating for camera motion leads to substantial gains in tracking robustness. By replacing the conventional 2D square correlation windows used in prior 2D and 3D trackers with a spatially grounded 3D attention mechanism, TAPIP3D achieves strong and consistent results across multiple 3D point tracking benchmarks. Project Page: https://tapip3d.github.io

arXiv:2504.15095v5 Announce Type: replace Abstract: Monocular depth estimation (MDE) aims to infer per-pixel depth from a single RGB image. While diffusion models have advanced MDE with impressive generalization, they often exhibit limitations in accurately reconstructing far-range regions. This difficulty arises from two key challenges. First, the implicit multi-scale processing in standard spatial-domain models can be insufficient for preserving the fine-grained, high-frequency details crucial for distant structures. Second, the intrinsic long-tail distribution of depth data imposes a strong training bias towards more prevalent near-range regions. To address these, we propose VistaDepth, a novel diffusion framework designed for balanced and accurate depth perception. We introduce two key innovations. First, the Latent Frequency Modulation (LFM) module enhances the model's ability to represent high-frequency details. It operates by having a lightweight network predict a dynamic, content-aware spectral filter to refine latent features, thereby improving the reconstruction of distant structures. Second, our BiasMap mechanism introduces an adaptive reweighting of the diffusion loss strategically scaled across diffusion timesteps. It further aligns the supervision with the progressive denoising process, establishing a more consistent learning signal. As a result, it mitigates data bias without sacrificing training stability. Experiments show that VistaDepth achieves state-of-the-art performance for diffusion-based MDE, particularly excelling in reconstructing detailed and accurate depth in far-range regions.

arXiv:2504.16362v2 Announce Type: replace Abstract: Despite several algorithmic advances in the training of convolutional neural networks (CNNs) over the years, their generalization capabilities are still subpar across several pertinent domains, particularly within open-set tasks often found in biometric and medical contexts. On the contrary, humans have an uncanny ability to generalize to unknown visual stimuli. The efficient coding hypothesis posits that early visual structures (retina, Lateral Geniculate Nucleus, and primary visual cortex) transform inputs to reduce redundancy and maximize information efficiency. This mechanism of redundancy minimization in early vision was the inspiration for CNN regularization techniques that force convolutional kernels to be orthogonal. However, the existing works rely upon matrix projections, architectural modifications, or specific weight initializations, which frequently overtly constrain the network's learning process and excessively increase the computational load during loss function calculation. In this paper, we introduce a flexible and lightweight approach that regularizes a subset of first-layer convolutional filters by making them pairwise-orthogonal, which reduces the redundancy of the extracted features but at the same time prevents putting excessive constraints on the network. We evaluate the proposed method on three open-set visual tasks (anomaly detection in chest X-ray images, synthetic face detection, and iris presentation attack detection) and observe an increase in the generalization capabilities of models trained with the proposed regularizer compared to state-of-the-art kernel orthogonalization approaches. We offer source codes along with the paper.

arXiv:2504.19210v3 Announce Type: replace Abstract: Surface parameterization is a fundamental geometry processing task, laying the foundations for the visual presentation of 3D assets and numerous downstream shape analysis scenarios. Conventional parameterization approaches demand high-quality mesh triangulation and are restricted to certain simple topologies unless additional surface cutting and decomposition are provided. In practice, the optimal configurations (e.g., type of parameterization domains, distribution of cutting seams, number of mapping charts) may vary drastically with different surface structures and task characteristics, thus requiring more flexible and controllable processing pipelines. To this end, this paper introduces FlexPara, an unsupervised neural optimization framework to achieve both global and multi-chart surface parameterizations by establishing point-wise mappings between 3D surface points and adaptively-deformed 2D UV coordinates. We ingeniously design and combine a series of geometrically-interpretable sub-networks, with specific functionalities of cutting, deforming, unwrapping, and wrapping, to construct a bi-directional cycle mapping framework for global parameterization without the need for manually specified cutting seams. Furthermore, we construct a multi-chart parameterization framework with adaptively-learned chart assignment. Extensive experiments demonstrate the universality, superiority, and inspiring potential of our neural surface parameterization paradigm. The code will be publicly available at https://github.com/AidenZhao/FlexPara

arXiv:2504.19347v2 Announce Type: replace Abstract: Detecting small drones, often indistinguishable from birds, is crucial for modern surveillance. This work introduces a drone detection methodology built upon the medium-sized YOLOv11 object detection model. To enhance its performance on small targets, we implemented a multi-scale approach in which the input image is processed both as a whole and in segmented parts, with subsequent prediction aggregation. We also utilized a copy-paste data augmentation technique to enrich the training dataset with diverse drone and bird examples. Finally, we implemented a post-processing technique that leverages frame-to-frame consistency to mitigate missed detections. The proposed approach attained first place in the 8th WOSDETC Drone-vs-Bird Detection Grand Challenge, held at the 2025 International Joint Conference on Neural Networks (IJCNN), showcasing its capability to detect drones in complex environments effectively.

arXiv:2504.19637v4 Announce Type: replace Abstract: Partially Relevant Video Retrieval (PRVR) aims to retrieve the target video that is partially relevant to the text query. The primary challenge in PRVR arises from the semantic asymmetry between textual and visual modalities, as videos often contain substantial content irrelevant to the query. Existing methods coarsely align paired videos and text queries to construct the semantic space, neglecting the critical cross-modal dual nature inherent in this task: inter-sample correlation and intra-sample redundancy. To this end, we propose a novel PRVR framework to systematically exploit these two characteristics. Our framework consists of three core modules. First, the Inter Correlation Enhancement (ICE) module captures inter-sample correlation by identifying semantically similar yet unpaired text queries and video moments, combining them to form pseudo-positive pairs for more robust semantic space construction. Second, the Intra Redundancy Mining (IRM) module mitigates intra-sample redundancy by mining redundant moment features and distinguishing them from query-relevant moments, encouraging the model to learn more discriminative representations. Finally, to reinforce these modules, we introduce the Temporal Coherence Prediction (TCP) module, which enhances discrimination of fine-grained moment-level semantics by training the model to predict the original temporal order of randomly shuffled video frames and moments. Extensive experiments demonstrate the superiority of our method, achieving state-of-the-art results.

arXiv:2505.02043v3 Announce Type: replace Abstract: Recovering CAD models from point clouds requires reconstructing their topology and sketch-based extrusion primitives. A dominant paradigm for representing sketches involves implicit neural representations such as Signed Distance Fields (SDFs). However, this indirect approach inherently struggles with precision, leading to unintended curved edges and models that are difficult to edit. In this paper, we propose Point2Primitive, a framework that learns to directly predict the explicit, parametric primitives of CAD models. Our method treats sketch reconstruction as a set prediction problem, employing a improved transformer-based decoder with explicit position queries to directly detect and predict the fundamental sketch curves (i.e., type and parameter) from the point cloud. Instead of approximating a continuous field, we formulate curve parameters as explicit position queries, which are optimized autoregressively to achieve high accuracy. The overall topology is rebuilt via extrusion segmentation. Extensive experiments demonstrate that this direct prediction paradigm significantly outperforms implicit methods in both primitive accuracy and overall geometric fidelity.

arXiv:2505.05456v2 Announce Type: replace Abstract: Spatial intelligence (SI) represents a cognitive ability encompassing the visualization, manipulation, and reasoning about spatial relationships, underpinning disciplines from neuroscience to robotics. We introduce SITE, a benchmark dataset towards SI Thorough Evaluation in a standardized format of multi-choice visual question-answering, designed to assess large vision-language models' spatial intelligence across diverse visual modalities (single-image, multi-image, and video) and SI factors (figural to environmental scales, spatial visualization and orientation, intrinsic and extrinsic, static and dynamic). Our approach to curating the benchmark combines a bottom-up survey about 31 existing datasets and a top-down strategy drawing upon three classification systems in cognitive science, which prompt us to design two novel types of tasks about view-taking and dynamic scenes. Extensive experiments reveal that leading models fall behind human experts especially in spatial orientation, a fundamental SI factor. Moreover, we demonstrate a positive correlation between a model's spatial reasoning proficiency and its performance on an embodied AI task.

arXiv:2505.09415v2 Announce Type: replace Abstract: Face anti-spoofing (FAS) is crucial for protecting facial recognition systems from presentation attacks. Previous methods approached this task as a classification problem, lacking interpretability and reasoning behind the predicted results. Recently, multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and decision-making in visual tasks. However, there is currently no universal and comprehensive MLLM and dataset specifically designed for FAS task. To address this gap, we propose FaceShield, a MLLM for FAS, along with the corresponding pre-training and supervised fine-tuning (SFT) datasets, FaceShield-pre10K and FaceShield-sft45K. FaceShield is capable of determining the authenticity of faces, identifying types of spoofing attacks, providing reasoning for its judgments, and detecting attack areas. Specifically, we employ spoof-aware vision perception (SAVP) that incorporates both the original image and auxiliary information based on prior knowledge. We then use an prompt-guided vision token masking (PVTM) strategy to random mask vision tokens, thereby improving the model's generalization ability. We conducted extensive experiments on three benchmark datasets, demonstrating that FaceShield significantly outperforms previous deep learning models and general MLLMs on four FAS tasks, i.e., coarse-grained classification, fine-grained classification, reasoning, and attack localization. Our instruction datasets, protocols, and codes will be released at https://github.com/Why0912/FaceShield.

arXiv:2505.11777v2 Announce Type: replace Abstract: Diffusion models have demonstrated remarkable success in various visual generation tasks, including image, video, and 3D content generation. Preference optimization (PO) is a prominent and growing area of research that aims to align these models with human preferences. While existing PO methods primarily concentrate on producing favorable outputs, they often overlook the significance of classifier-free guidance (CFG) in mitigating undesirable results. Diffusion-NPO addresses this gap by introducing negative preference optimization (NPO), training models to generate outputs opposite to human preferences and thereby steering them away from unfavorable outcomes through CFG. However, prior NPO approaches rely on costly and fragile procedures for obtaining explicit preference annotations (e.g., manual pairwise labeling or reward model training), limiting their practicality in domains where such data are scarce or difficult to acquire. In this work, we propose Self-NPO, specifically truncated diffusion fine-tuning, a data-free approach of negative preference optimization by directly learning from the model itself, eliminating the need for manual data labeling or reward model training. This data-free approach is highly efficient (less than 1% training cost of Diffusion-NPO) and achieves comparable performance to Diffusion-NPO in a data-free manner. We demonstrate that Self-NPO integrates seamlessly into widely used diffusion models, including SD1.5, SDXL, and CogVideoX, as well as models already optimized for human preferences, consistently enhancing both their generation quality and alignment with human preferences. Code is available at https://github.com/G-U-N/Diffusion-NPO.

arXiv:2505.11822v2 Announce Type: replace Abstract: Drone-view geo-localization (DVGL) aims to match images of the same geographic location captured from drone and satellite perspectives. Despite recent advances, DVGL remains challenging due to significant appearance changes and spatial distortions caused by viewpoint variations. Existing methods typically assume that drone and satellite images can be directly aligned in a shared feature space via contrastive learning. Nonetheless, this assumption overlooks the inherent conflicts induced by viewpoint discrepancies, resulting in extracted features containing inconsistent information that hinders precise localization. In this study, we take a manifold learning perspective and model $\textit{the feature space of cross-view images as a composite manifold jointly governed by content and viewpoint}$. Building upon this insight, we propose $\textbf{CVD}$, a new DVGL framework that explicitly disentangles $\textit{content}$ and $\textit{viewpoint}$ factors. To promote effective disentanglement, we introduce two constraints: $\textit{(i)}$ an intra-view independence constraint that encourages statistical independence between the two factors by minimizing their mutual information; and $\textit{(ii)}$ an inter-view reconstruction constraint that reconstructs each view by cross-combining $\textit{content}$ and $\textit{viewpoint}$ from paired images, ensuring factor-specific semantics are preserved. As a plug-and-play module, CVD integrates seamlessly into existing DVGL pipelines and reduces inference latency. Extensive experiments on University-1652 and SUES-200 show that CVD exhibits strong robustness and generalization across various scenarios, viewpoints and altitudes, with further evaluations on CVUSA and CVACT confirming consistent improvements.

arXiv:2505.12644v2 Announce Type: replace Abstract: In surrogate ensemble attacks, using more surrogate models yields higher transferability but lower resource efficiency. This practical trade-off between transferability and efficiency has largely limited existing attacks despite many pre-trained models are easily accessible online. In this paper, we argue that such a trade-off is caused by an unnecessary common assumption, i.e., all models should be \textit{identical} across iterations. By lifting this assumption, we can use as many surrogates as we want to unleash transferability without sacrificing efficiency. Concretely, we propose Selective Ensemble Attack (SEA), which dynamically selects diverse models (from easily accessible pre-trained models) across iterations based on our new interpretation of decoupling within-iteration and cross-iteration model diversity. In this way, the number of within-iteration models is fixed for maintaining efficiency, while only cross-iteration model diversity is increased for higher transferability. Experiments on ImageNet demonstrate the superiority of SEA in various scenarios. For example, when dynamically selecting 4 from 20 accessible models, SEA yields 8.5% higher transferability than existing attacks under the same efficiency. The superiority of SEA also generalizes to real-world systems, such as commercial vision APIs and large vision-language models. Overall, SEA opens up the possibility of adaptively balancing transferability and efficiency according to specific resource requirements.

arXiv:2505.13191v2 Announce Type: replace Abstract: Inspired by foveal vision, hard attention models promise interpretability and parameter economy. However, existing models like the Recurrent Model of Visual Attention (RAM) and Deep Recurrent Attention Model (DRAM) failed to model the hierarchy of human vision system, that compromise on the visual exploration dynamics. As a result, they tend to produce attention that are either overly fixational or excessively saccadic, diverging from human eye movement behavior. In this paper, we propose a Multi-Level Recurrent Attention Model (MRAM), a novel hard attention framework that explicitly models the neural hierarchy of human visual processing. By decoupling the function of glimpse location generation and task execution in two recurrent layers, MRAM emergent a balanced behavior between fixation and saccadic movement. Our results show that MRAM not only achieves more human-like attention dynamics, but also consistently outperforms CNN, RAM and DRAM baselines on standard image classification benchmarks.

arXiv:2505.16862v2 Announce Type: replace Abstract: Recent progress in panoramic image generation has underscored two critical limitations in existing approaches. First, most methods are built upon diffusion models, which are inherently ill-suited for equirectangular projection (ERP) panoramas due to the violation of the identically and independently distributed (i.i.d.) Gaussian noise assumption caused by their spherical mapping. Second, these methods often treat text-conditioned generation (text-to-panorama) and image-conditioned generation (panorama outpainting) as separate tasks, relying on distinct architectures and task-specific data. In this work, we propose a unified framework, Panoramic AutoRegressive model (PAR), which leverages masked autoregressive modeling to address these challenges. PAR avoids the i.i.d. assumption constraint and integrates text and image conditioning into a cohesive architecture, enabling seamless generation across tasks. To address the inherent discontinuity in existing generative models, we introduce circular padding to enhance spatial coherence and propose a consistency alignment strategy to improve generation quality. Extensive experiments demonstrate competitive performance in text-to-image generation and panorama outpainting tasks while showcasing promising scalability and generalization capabilities.

arXiv:2505.18991v2 Announce Type: replace Abstract: Pansharpening seeks to fuse high-resolution panchromatic (PAN) and low-resolution multispectral (LRMS) images into a single image with both fine spatial and rich spectral detail. Despite progress in deep learning-based approaches, existing methods often fail to capture global priors inherent in remote sensing data distributions. Diffusion-based models have recently emerged as promising solutions due to their powerful distribution mapping capabilities, however, they suffer from heavy inference latency. We introduce KSDiff, a fast kernel-space diffusion framework that generates convolutional kernels enriched with global context to enhance pansharpening quality and accelerate inference. Specifically, KSDiff constructs these kernels through the integration of a low-rank core tensor generator and a unified factor generator, orchestrated by a structure-aware multi-head attention mechanism. We further introduce a two-stage training strategy tailored for pansharpening, facilitating integration into existing pansharpening architectures. Experiments show that KSDiff achieves superior performance compared to recent promising methods, and with over $500 \times$ faster inference than diffusion-based pansharpening baselines. Ablation studies, visualizations and further evaluations substantiate the effectiveness of our approach. Code will be released upon possible acceptance.

arXiv:2505.20782v2 Announce Type: replace Abstract: Multi-targeted adversarial attacks aim to mislead classifiers toward specific target classes using a single perturbation generator with a conditional input specifying the desired target class. Existing methods face two key limitations: (1) a single generator supports only a limited number of predefined target classes, and (2) it requires access to the victim model's training data to learn target class semantics. This dependency raises data leakage concerns in practical black-box scenarios where the training data is typically private. To address these limitations, we propose a novel Cross-Domain Multi-Targeted Attack (CD-MTA) that can generate perturbations toward arbitrary target classes, even those that do not exist in the attacker's training data. CD-MTA is trained on a single public dataset but can perform targeted attacks on black-box models trained on different datasets with disjoint and unknown class sets. Our method requires only a single example image that visually represents the desired target class, without relying its label, class distribution or pretrained embeddings. We achieve this through a Feature Injection Module (FIM) and class-agnostic objectives which guide the generator to extract transferable, fine-grained features from the target image without inferring class semantics. Experiments on ImageNet and seven additional datasets show that CD-MTA outperforms existing multi-targeted attack methods on unseen target classes in black-box and cross-domain scenarios. The code is available at https://github.com/tgoncalv/CD-MTA.

arXiv:2505.21501v2 Announce Type: replace Abstract: Vision Transformers (ViTs) have emerged as the dominant architecture for visual processing tasks, demonstrating excellent scalability with increased training data and model size. However, recent work has identified the emergence of artifact tokens in ViTs that are incongruous with local semantics. These anomalous tokens degrade ViT performance in tasks that require fine-grained localization or structural coherence. An effective mitigation of this issue is the addition of register tokens to ViTs, which implicitly "absorb" the artifact term during training.Given the availability of existing large-scale pre-trained ViTs, in this paper we seek add register tokens to existing models without needing to re-train from scratch, which is infeasible considering their size. Specifically, we propose Post Hoc Registers (PH-Reg), an efficient self-distillation method that integrates registers into an existing ViT without requiring additional labeled data and full retraining. PH-Reg initializes both teacher and student networks from the same pre-trained ViT. The teacher remains frozen and unmodified, while the student is augmented with randomly initialized register tokens. By applying test-time augmentation to the teacher's inputs, we generate denoised dense embeddings free of artifacts, which are then used to optimize only a small subset of unlocked student weights. We show that our approach can effectively reduce the number of artifact tokens, improving the segmentation and depth prediction of the student ViT under zero-shot and linear probing.