Computer Vision
Solution for UCF UrbanTwin LUMPI Track: Sim-to-Real Urban LiDAR 3D Object Detection
Pu Luo, Cong Xu, Yumei Li et al. (+4 more)
We present our solution to the LUMPI track of the UCF UrbanTwin Sim2Real
LiDAR Challenge at the 6th DriveX Workshop, ECCV 2026. The detector must be trained only on synthetic data and is evaluated on 50 held-out real
LiDAR frames; a separate 50-frame synthetic submission is evaluated for point-cloud realism. Our method addresses the Sim2Real gap at three levels. First, we align synthetic scans to the 50k-point test density and build a 30k-record training pool using UT-LUMPI geometry, RangeLDM-based sampling diversification, rare-class copy-paste, and pedestrian-oriented augmentation. Second, complementary DSVT detectors and Car/Bus PointPillars specialists are trained under the same synthetic-only constraint. Third, predictions are integrated by class-aware routing, asymmetric agreement fusion, constrained residual-recall supplementation, class-coverage
auditing, and selective box-size calibration. The realism branch is optimized independently with radial-density matching, weak affine calibration, and calibrated set mixing. The final submission obtains a Combined Score of 0.4692, a Detection Score of 0.1797, a Realism Score of 0.9035, and 3D mAP@0.5 of 0.1258.
Read the full abstract ▾
All authors Pu Luo, Cong Xu, Yumei Li, Kexin Zhang, Licheng Jiao, Wenping Ma, Lingling Li
Computer Vision
SphereSOD: Geometry-Structure Coupled Learning for 360 Salient Object Detection
Junsong Zhang, Zhijie Shen, Shuai Zheng et al. (+4 more)
360{\deg} salient object detection (SOD) aims to accurately segment salient regions across a full field of view. However, equirectangular projection (ERP) introduces severe spatial distortion when mapping the spherical domain onto a planar representation. Existing methods mainly focus on compensating projection distortion while overlooking the interaction between panoramic geometry and salient object structure during feature perception and prediction refinement. To this end, we propose SphereSOD, an ERP-native framework that couples panoramic geometry with evolving salient structures. Specifically, spherical geometry governs feature sampling and spatial weighting, while coarse-grained saliency and contour prediction influence context aggregation during the progressive decoding process. SphereSOD first initializes deformable sampling based on spherical projection geometry and then employs bounded, content-adaptive offsets, yielding features that are better aligned with the underlying panoramic geometry. Subsequently, the decoder performs structure-guided context aggregation and progressive refinement to recover complete salient regions and accurate boundaries. Extensive experiments on three public 360{\deg} SOD
benchmarks demonstrate state-of-the-art performance and a favorable accuracy-efficiency trade-off, supporting structurepreserving inference directly in ERP space as a promising alternative to projection-heavy panoramic pipelines.
Read the full abstract ▾
All authors Junsong Zhang, Zhijie Shen, Shuai Zheng, Feng Li, Runmin Cong, Yao Zhao, Chunyu Lin
Computer Vision
Heat Kernel Textures: the Geodesic Gaussians That Do Not Splat
Simone Foti, Caner Korkmaz, Stefanos Zafeiriou et al. (+1 more)
3D Gaussian Splatting has recently revolutionised novel view synthesis as well as many other 3D
vision methods and applications. Drawing inspiration from this representation, we now rethink textures to overcome the main issues of UV mapping while considerably lowering their
memory footprint. Heat Kernel Textures (HKTex) eliminate UV unwrapping as well as their persistent issues of wasted UV space, seams, distortions, vertex-duplication, and varying resolution. Grounded in discrete Riemannian geometry and intrinsically defined on any
manifold surface discretised as a triangular mesh, HKTex uses anisotropic heat kernels as geodesic equivalents to Gaussians. Like our kernels, also the optimisation of their position and the adaptive densification strategies were redefined to operate on the surface of the object to be textureised. Our novel representation is also fully integrated with a physically based renderer and can be optimised either from existing textures or multi-view images. Our project page and code are available at circle-group.github.io/research/HeatKernelTextures.
Read the full abstract ▾
All authors Simone Foti, Caner Korkmaz, Stefanos Zafeiriou, Tolga Birdal
Computer Vision
Re-engineering SORT-based algorithms for low-cost small object tracking from omnidirectional footage
Xin Shu, Meegan Gower, Yvonne Buckley et al. (+1 more)
Multi-object tracking (MOT) has advanced rapidly in urban surveillance and autonomous driving, yet many trackers rely on ReID- and
transformer-based appearance encoders and are designed for standard FoV cameras. These assumptions break down for low-cost omnidirectional deployments, where equirectangular projection introduces seam discontinuities and targets appear to be small and fast-moving. We address multi-object tracking of flying animals captured in remote environments using omnidirectional cameras. We propose a lightweight framework that re-engineers SORT-based tracking for this geometry, including (i) a Seam-Aware Motion Model that keeps the Kalman state continuous across the seam, (ii) a composite seam-aware association cost that pairs a wrapped Euclidean term with GIoU, and (iii) OmniSmall, a new
benchmark of omnidirectional wildlife footage. On our new
dataset, with ground-truth detections, our modifications improved over OCSORT by +8.51 HOTA, +9.41 MOTA, and +10.17 IDF1; with YOLOX detections the gain narrows to +1.95 HOTA. Our proposed methods improved tracking performance on OmniSmall and remained competitive on JRDB without adding appearance encoders while keeping the tracking stage CPU-only. Our
dataset and source code are available at: https://github.com/Xin-Shu/OmniSORT.git.
Read the full abstract ▾
All authors Xin Shu, Meegan Gower, Yvonne Buckley, Anil Kokaram
Computer Vision
TeMo: Temperature Modulation for Multimodal Contrastive Learning
Dhimitrios Duka, Bernt Schiele, Hilde Kuehne et al. (+1 more)
Contrastive learning approaches achieve strong performance by training models to bring similar samples closer while pushing dissimilar samples apart. A crucial component of contrastive learning is the temperature hyperparameter $\tau$, which controls the penalty strength applied to negative samples. However, most existing methods either fix this hyperparameter or learn a global value during training. In this paper, we introduce TeMo, Temperature Modulation framework, a similarity-based modulation approach that adaptively adjusts the temperature for each positive-negative pair according to their similarity, enabling more fine-grained
multimodal contrastive learning. Our approach seamlessly integrates temperature-modulated
multimodal and unimodal losses with the standard
multimodal contrastive loss by gradually transitioning between them. This design allows the model to capture both coarse- and fine-grained semantics at different training stages. Extensive experiments demonstrate that each component of TeMo consistently enhances performance across diverse zero-shot
retrieval and classification tasks, establishing new state-of-the-art results.
Read the full abstract ▾
All authors Dhimitrios Duka, Bernt Schiele, Hilde Kuehne, Anna Kukleva
Computer Vision
When Semantically Consistent Encoding Meets View-Label Heterogeneity Modeling: A Unified Framework for Incomplete Multi-View Multi-Label Learning
Chengliang Liu, Bo Li, Bob Zhang et al. (+3 more)
Incomplete multi-view multi-label learning requires not only robust semantic aggregation from partially observed views, but also label-aware exploitation of view-specific evidence. Existing approaches usually emphasize either shared representation learning or decision-level fusion. The former improves robustness against missing views, yet tends to compress label-discriminative view-specific cues into a single latent representation. The latter preserves individual view predictions, but often relies on fixed or globally learned fusion weights, ignoring that different labels of different instances may require different views. To address these limitations, this paper presents V2L, a unified representation-decision framework for incomplete multi-view multi-label classification. On the representation side, V2L constructs semantically consistent variational posteriors from incomplete views through a perturbation-aware encoding mechanism, which provides a stable shared semantic basis. On the decision side, V2L introduces an active view-label relevance modeling strategy that estimates instance-wise and label-wise view contributions, allowing each label prediction to adaptively select useful view-specific evidence. From the perspective of model architecture, these two important strategies are integrated into a unified framework through a hybrid fusion architecture, simultaneously meeting the requirements of cross-view semantic consistency and representational complementarity. Extensive experiments under both incomplete and complete settings show that V2L achieves leading performance on five
benchmarks. Code is available at: https://github.com/justsmart/V2L.
Read the full abstract ▾
All authors Chengliang Liu, Bo Li, Bob Zhang, Yanghao Zhou, Jie Wen, Wenwu Wang
Computer Vision
Topologically Consistent Agricultural Parcel Vectorization with Semantic-Guided Diffusion and Topology-Aware Polygonization
Weiqin Jiao, Xiaolong Zuo and Claudio Persello
Agricultural parcel polygons play a fundamental role in geospatial applications such as precision agriculture, land administration, and crop monitoring. Beyond regular polygon geometry and low vertex redundancy, practical parcel maps should avoid topological conflicts and preserve common boundaries between adjacent fields. Yet this requirement remains largely unresolved:
segmentation-based methods mainly produce parcel masks or raster boundary cues and rely on heuristic raster-to-vector conversion, instance- and contour-based methods reconstruct parcels independently, and recent vector-oriented methods improve polygon regularity but do not explicitly recover adjacent parcels from a shared topological structure. To address this gap, we propose a semantic-guided
diffusion framework for topologically consistent agricultural parcel vectorization. It couples joint edge–vertex latent
diffusion with supervised multi-cue conditioning to generate geometrically regularised parcel-boundary and vertex primitives while suppressing false-positive responses. A
topology-aware parcel polygon reconstruction method then converts these primitives into regular polygons by reconstructing parcel faces from a common planar graph, enabling adjacent predicted parcels to reuse shared boundaries and avoid mutual interior intrusion. Extensive experiments on the AI4SmallFarms and iFLYTEK
datasets evaluate parcel vectorization in terms of pixel-level coverage,
geometric fidelity, object-level correctness, and topological consistency. The results show strong and competitive performance, with zero measured intrusion ratio and the highest shared-edge recall, demonstrating the potential of the proposed framework for accurate, regular, and topologically consistent agricultural parcel vectorization.
Read the full abstract ▾
Computer Vision
PICANet: Physics-Informed Cascaded Asymmetric Network for Infrared Small Target Detection
Jingjing Liu, Yinchao Han, Xianchao Xiu et al. (+2 more)
Infrared small target detection (ISTD) is an important research direction in image processing. However, existing methods are limited by severe background noise propagation and target degradation in high-level semantic features. To address these limitations, this paper proposes a plug-and-play physics-informed cascaded asymmetric network, named PICANet. Specifically, we construct a hierarchical prior decoupling module to explicitly extract low-level and high-level physical information, thereby characterizing target features at different levels rather than relying solely on convolutional extraction. Furthermore, a dual-prior interactive fusion module is developed to dynamically refine target representations while suppressing complex background clutter. Unlike previous work, a multi-level cross-feature
attention module with the cascaded asymmetric mechanism is introduced to achieve precise
alignment between high-level semantics and low-level spatial details. Extensive experiments demonstrate that the proposed PICANet outperforms state-of-the-art ISTD methods, showing satisfactory detection accuracy even against complex backgrounds. Our code is available at https://github.com/xianchaoxiu/PICANet.
Read the full abstract ▾
All authors Jingjing Liu, Yinchao Han, Xianchao Xiu, Jianhua Zhang, Wanquan Liu
Computer Vision
Mitigating Shortcut Learning: Texture-Penalized Prototype Networks
Akshay Anilkumar Girija, Elena Hoemann, Frank Köster et al. (+1 more)
Standard Convolutional Neural Networks (CNNs) exhibit severe performance degradation due to a strong inductive texture bias that prioritizes local, high-frequency patterns over global structural shapes. This dependency causes confident misclassifications during textural changes or environmental effects. To address this flaw, this study introduces the Texture-Penalized Prototype Network (TPPN), a novel architectural framework that shifts this inherent bias without depending on resource-intensive augmented
datasets. Specifically, a Texture-Penalization Branch (TPB) imposes a penalty to suppress the extraction of local texture proxies, forcing the network backbone to discard high-frequency cues and extract purified, shape-biased representations. By evaluating similarities within a prototype-based hypersphere derived from the final convolutional features, the approach enforces strict
geometric constraints, treating objects as compositions of essential parts to achieve robust classification. Evaluations on texture-shape cue-conflict
datasets and synthetic noise
benchmarks demonstrate the stronger shape bias of this structural disentanglement. The proposed framework reduces the inherent texture bias of a baseline ResNet-50 from 55.11% to 29.73%, surpassing the texture-suppression capabilities of an off-the-shelf
Vision Transformer (ViT-B/16). Furthermore, the approach demonstrates robust generalization under cue-conflict conditions, resisting textural shortcut learning when encountering Out-of-Distribution (OOD) shapes. The model maintains stronger shape accuracy against elevated perturbations. On clean validation data, the architecture incurs a minimal drop in accuracy of 0.90 percentage points. This provides a structural, efficient solution to CNN texture bias.
Read the full abstract ▾
All authors Akshay Anilkumar Girija, Elena Hoemann, Frank Köster, Sven Hallerbach
Computer Vision
CrACK: Adversarial Attacks on Cross-Model Consistency in Collaborative Vision Foundation Models
Feifei Liu, Jintao Cheng, Chi Man Vong et al. (+1 more)
Training-free collaborative pipelines that integrate
Vision Foundation Models such as CLIP, SAM, and DINO achieve strong open-vocabulary dense prediction and are increasingly deployed in safety-critical applications. The security of these systems is commonly assumed to follow from the robustness of their individual models. We challenge this assumption. We identify a vulnerability shared by every collaborative pipeline: each model consumes the intermediate output of another without verifying semantic consistency, an unverified premise that we term the semantic-spatial
alignment dependency. Existing
adversarial attacks target a single model and overlook this premise, leaving the inter-model interface entirely unguarded. We propose CrACK (Cross-model
Adversarial Consistency attack), an inference-time attack that exploits this interface without modifying any input pixel, model weight, or training data. CrACK operates in two stages:
Adversarial Affinity Contradiction Injection corrupts the cross-modal affinity
matrix by inverting SAM encoder features under the guidance of CLIP patch-level semantics, and Semantic Interface Poisoning steers the prediction through a max-distance label permutation derived from CLIP text
embeddings. Experiments on four collaborative pipelines across eight
benchmarks show that CrACK causes catastrophic degradation while every individual model continues to produce its unchanged standalone output, rendering per-model defenses structurally blind. The corruption further cascades into large
vision-
language model
reasoning, driving models such as LLaVA to produce erroneous responses from visually intact inputs. Our results show that the security of a collaborative AI system cannot be reduced to the robustness of its components, and that inter-model feature interfaces must be treated as first-class security boundaries.
Read the full abstract ▾
All authors Feifei Liu, Jintao Cheng, Chi Man Vong, Xiaoyu Tang
Computer Vision · Cross-listed from cs.RO
CosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial Movements
Hongxiang Zhao, Mutian Xu, Zeyu Jin et al. (+3 more)
Transferring human hand demonstrations to robotic grippers has recently emerged as a cost-effective solution for
robot learning. However, existing methods are largely confined to simple, planar tasks and fail to handle complex spatial movements (e.g., intricate trajectories involving rotations or flips) that are essential for
robot manipulation. Motivated by this gap, we adopt an implicit, data-driven approach guided by fine-grained hand-pose motions. To this end, we introduce a scalable acquisition pipeline to collect hand-gripper paired demonstrations, governed by a rigorous protocol that prioritizes motion complexity and leverages a handheld gripper for seamless action mimicry. This yields a large-scale paired
dataset comprising 6,189 episodes across 1,254 unique objects, exhibiting significantly higher spatial complexity than existing
benchmarks. However, learning such complex mappings remains challenging. We observe that naive end-to-end generation of full gripper pose sequences is insufficient, as minor trajectory deviations compound rapidly under intricate dynamics. To address this, we propose a two-stage framework: Stage I predicts sparse gripper keyframes (initial and terminal) to simplify the mapping objective, while Stage II generates the full continuous action sequence conditioned on these keyframes. Furthermore, to mitigate cumulative drift, we keep the gripper's orientation being learned while post-optimizing its translation based on the grasping heuristic and kinematic consistency. In both simulation and real-
robot experiments, our framework enables stable and precise hand-to-gripper transfer of complex spatial manipulations, significantly outperforming traditional baselines. Project page: https://cosmoh2g.github.io.
Read the full abstract ▾
All authors Hongxiang Zhao, Mutian Xu, Zeyu Jin, Yiming Hao, Shuguang Cui, Xiaoguang Han
Computer Vision
When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations
Quentin Telnoff, Emanuela Boros, Mickaël Coustaty et al. (+3 more)
Post-hoc explanation methods are widely used to inspect image classifiers, but their reliability depends on design choices that are often treated as implementation details. We study this issue for LIME on document image classification, focusing on the
segmentation step that defines the interpretable units being perturbed. Standard image-based LIME typically relies on natural-image superpixels, which are poorly aligned with document structure such as text regions, layout blocks, and identification codes. Using RVL-CDIP, we compare Quickshift and SLIC with document-aware
segmentations based on OCR bounding boxes and regular grids. Our results show that
segmentation strongly affects explanation consistency, correctness, and local fidelity. Document-aware
segmentations produce more stable and faithful explanations, require fewer perturbations to converge, and expose shortcut behaviour based on document identification codes, a known RVL-CDIP bias that superpixel-based LIME often obscures. These findings show that reliable post-hoc explanation requires domain-aware interpretable representations, and that
segmentation should be treated as part of the explanation method rather than as neutral preprocessing.
Read the full abstract ▾
All authors Quentin Telnoff, Emanuela Boros, Mickaël Coustaty, Robin Jarry, Fabrice Crohas, Antoine Doucet
Computer Vision
Omar Todd, Sooha Kim, Raghav Mehta et al. (+5 more)
Uncertainty arising from inter-observer variability in medical image
segmentation plays an important role in developing treatment plans. Research in this area is inhibited by the lack of multiple annotations for large-scale medical
datasets, especially for volumetric data, which suffers from additional scaling and computational complexity challenges. Flow matching has emerged as a powerful framework for generative modelling and has also been demonstrated to maintain strong performance when working with latent representations of images. In this work, we introduce a latent-to-latent flow technique for
stochastic segmentation of medical volumes via encoded representations of both the image and label space. We evaluate our method on two challenging applications covering delineation uncertainty for radiotherapy planning and multiple organ structure
segmentation, improving efficiency up to 14x compared with full resolution models while maintaining clinically relevant performance.
Read the full abstract ▾
All authors Omar Todd, Sooha Kim, Raghav Mehta, Katherine Mackay, David Bernstein, Alexandra Taylor, Fabio De Sousa Ribeiro, Ben Glocker
Computer Vision
Parser-Free VLM Verification for Federated Weakly Supervised Video Anomaly Detection
Sébastien Thuau, Amira Gran, Siba Haidar et al. (+1 more)
How can
vision-
language models help
video anomaly detection (VAD) when surveillance data remain distributed, weakly labeled, and resource-constrained? Most weakly supervised VAD methods assume centralized training; recent VLM-based extensions further rely on dense inference, generated explanations, or additional adaptation. We introduce a lightweight
federated MIL-VLM cascade in which only a compact MIL scorer is trained across clients, while a frozen VLM verifies high-scoring suspect segments post hoc. We study two VLM feedback interfaces: parsed text-generation decisions and a logit-based interface that extracts a continuous anomaly score from next-
token Yes/No probabilities. Experiments on UCF-Crime with InternVL3.5-2B and Qwen3-VL-2B-Instruct show that text-generation verification can improve frame-level AUC after diagnostic temporal post-processing, but remains sensitive to
prompts, parsers, model choice, and smoothing. In contrast, the logit interface provides a fixed parser-free signal that improves both frame-level AUC and frame-level AP over the MIL baseline across both VLMs, without temporal post-processing in its main configuration. Since suspect segments are updated independently once available, next-
token logit feedback provides a simple segment-local alternative to text-generation verification.
Read the full abstract ▾
All authors Sébastien Thuau, Amira Gran, Siba Haidar, Rachid Chelouah
Computer Vision
AFID: A Unified Open Framework for Automated Fingermark Identification, Quality Assessment and Feature Extraction
Tim Oblak, Rudolf Haraksim and Peter Peer
Automated fingermark identification is the foundation of forensic investigation, yet progress in the field is held back by fragmented, closed-source solutions trained on private or discontinued data. We present AFID, a unified open-source framework for friction ridge image processing that performs recognition, quality assessment, and feature extraction based on a single shared encoder, trained exclusively on publicly available data. At its core is a fixed-length representation learned for identity discrimination, trained under heavy augmentation. Despite applying essentially no preprocessing beyond resizing and padding at inference, AFID sets a new state of the art in fixed-length fingermark recognition, leading identification across NIST SD 27 (67.6% rank-1) , SD 302 (54.9% rank-1), and SD 303 (67.6% rank-1), surpassing a commercial matcher on fingermarks. From the same frozen backbone, a quality assessment module predicts recognition utility more accurately than any compared baseline and generalizes across independent matchers, while lightweight decoders recover minutiae, ridge orientation, and
segmentation competitive with dedicated methods. The framework proves that a single, efficiently trained encoder can support the full fingermark processing pipeline, from recognition through quality assessment all the way to feature extraction. To accelerate research on fingermark analysis even further, we release the code, models, and annotations to the community.
Read the full abstract ▾
Computer Vision
Unified Vision-Centric Pedestrian Crossing Action Prediction via Adaptive Patch Projection and Proactive Spatial Rectification
Yao Tian, Le Yang and Binglu Wang
Vision cues are available and informative for pedestrian action prediction, but obtaining stable target-centric representations from
video frames remains challenging without frame-level external perception cues. Thus, most methods rely on additional perception modules or multi-source information fusion, leaving the reliability of
vision-centric setting an open question. To this end, we propose ViCross, a
vision-centric pedestrian crossing action prediction framework powered by
multimodal large
language models, which maintains target-centric
reasoning from
video frames without additional perception modules beyond first-frame target initialization. While
multimodal large
language models exhibit strong visual understanding, applying them directly to
vision-centric action prediction faces two challenges. First, accurately perceiving target pedestrians often requires high resolution inputs and dense visual tokenization, making full-frame encoding computationally prohibitive. ViCross tackles this with Variable Resolution Patch Mapping module for efficient
token allocation while preserving key pedestrian details. Second, missing spatiotemporal priors hinder consistent cross frame
reasoning. ViCross mitigates this with a Spatial Constraint Enhancement Strategy that captures past motion, future locations, and action semantics for training-time proactive spatial rectification. Extensive experiments show that ViCross delivers clear gains in
vision-centric prediction settings and is competitive with multi-source fusion approaches in several settings. Code is available at https://github.com/2tianyao1/ViCross.git.
Read the full abstract ▾
Computer Vision
Self-Supervised Multi-View 3D Gaze Target Estimation via Probabilistic Ray Marching
Keqi Chen, Vinkle Srivastav and Nicolas Padoy
We present a self-supervised approach, Self-MVGTE, for estimating 3D gaze targets from multiple camera views. Unlike existing methods that independently estimate 2D gaze targets per camera view, Self-MVGTE predicts gaze targets directly in 3D space for the first time. Moreover, it does not require any ground-truth annotations from the target scene and uses only the multi-view input images from a calibrated camera setup, pseudo 2D gaze target labels from a
monocular gaze target estimation model, and 3D gaze vectors from a
monocular 3D gaze estimation model. A key challenge is that these pseudo labels are inherently noisy and multi-view inconsistent. To address this, we propose a probabilistic ray marching framework, which models the uncertainty of these pseudo labels and exploits 3D gaze vectors as
geometric priors. Specifically, these gaze vectors are first integrated into the
monocular gaze target estimation model to improve its generalization to unseen scenes, producing higher-quality pseudo labels. Then, for 3D gaze target estimation, we construct a 3D gaze cone by casting a bundle of rays from the eye position around the gaze vector to strictly constrain the solution space. Within this cone, we propose a depth-guided feature sampling strategy using off-the-shelf DINOv2 and Depth-Anything-3 models, and estimate a spatial likelihood distribution of the gaze target. Finally, we convert the pseudo gaze target labels into a target distribution and softly optimize the network. Extensive experiments on the MVGT
dataset show that Self-MVGTE achieves state-of-the-art performance, surpassing existing fully-supervised baselines.
Read the full abstract ▾
Computer Vision
RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting
Hejun Wang, Jinxi Li, Junwei Jiang et al. (+4 more)
Image relighting is traditionally tackled via complex inverse rendering pipelines, which suffer from ill-posed optimization, or single-image generative models that ignore crucial multi-view cues necessary for understanding 3D geometry and material interactions. To address these limitations, we introduce a feed-forward generative
Transformer for direct single- and multi-view image relighting that entirely bypasses explicit intrinsic property estimation. Adapted from a
video foundation model, our architecture features a latent illumination module that dynamically injects target environment maps into spatial features via cross-
attention. Furthermore, we employ permutation-invariant positional encodings to symmetrically process unordered multi-view inputs without sequential bias. To train this robust data-driven model, we construct the massive Laval Objaverse
Dataset (LOD), comprising 90K objects and 39K unique illuminations. Extensive experiments demonstrate state-of-the-art visual quality, photorealistic relighting quality, and strong zero-shot generalization across single-view, multi-view, and novel-view relighting tasks.
Read the full abstract ▾
All authors Hejun Wang, Jinxi Li, Junwei Jiang, Shiwei Mao, Hu Cheng, Shouwang Huang, Bo Yang
Computer Vision
Multi-label versus multi-class classification of blood cells and their aggregates in microfluidic channels
Igor Zingman, Shada Abuhattum, Sara Kaliman et al. (+8 more)
Deformability cytometry (DC) is a type of imaging flow cytometry, which uses a camera-equipped device to measure cellular stiffness in addition to other cellular properties at high throughput. Cellular properties such as area and elongation can identify
cell types, but this requires prior knowledge of distinguishing properties and cannot be applied to clinically important
cell aggregates. Using DC data, we evaluated conventional multi-class (MC) classification and introduced a multi-label (ML) approach for identifying blood
cells and their aggregates. In particular, an ML classifier can simultaneously assign multiple
cell-type labels to a single imaged event. We show that, unlike MC classification, ML classification can identify
cell aggregates not represented in the training data. It also avoids the need for exhaustive, strictly defined aggregate labels, thereby simplifying and speeding up annotation. Since automated blood analyzers do not reliably analyze
cell aggregates, our approach may help address this clinical gap.
Read the full abstract ▾
All authors Igor Zingman, Shada Abuhattum, Sara Kaliman, Maximilian Schlögel, Paul Müller, Markéta Kubánková, Nadine Ströhlein, Manuela Hauke, Lena Schnörer, Martin Kräter, Jochen Guck
Computer Vision · Cross-listed from cs.LG
Impact of canny edge detection preprocessing on performance of machine learning models for Parkinson's disease classification
Sameer Bhat and Piotr Szczuko
This study investigates the classification of individuals as healthy or at risk of Parkinson's disease using machine learning (ML) models, focusing on the impact of
dataset size and preprocessing techniques on model performance. Four
datasets are created from an original
dataset: DS_0, (normal
dataset), DS_1 (DS_O subjected to Canny edge detection and Hessian filtering), DS_2 (augmented DS_0), and DS_3 (augmented DS_1). We evaluate a range of ML models-Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), XGBoost (XBG), Naive Bayes (NB), Support Vector Machine (SVM), and AdaBoost (AdB)-on these
datasets, analyzing prediction accuracy, model size, and prediction latency. The results show that while larger
datasets lead to increased model
memory footprints and prediction latencies, the Canny edge detection preprocessing supplemented by Hessian filtering (used in DS_1 and DS_3) degrades the performance of most models. In our experiment, we observe that Random Forest (RF) maintains a stable
memory footprint of 61 KB across all
datasets, while models like KNN and SVM show significant increases in
memory usage, from 5.7-7 KB on DS_0 to 102-220 KB on DS_2, and similar increases in prediction time. Logistic Regression, Decision Tree, and Naive Bayes show stable
memory footprints and fast prediction times across all
datasets. XGBoost's prediction time increases from 180-200 ms on DS_0 to 700-3000 ms on DS_2 (truncated)
Read the full abstract ▾
Computer Vision
Federated Binary Gating with Server-Side Vision-Language Inference for Surveillance Anomaly Classification
Côme-Alexis Puech, Sébastien Thuau, Amira Gran et al. (+3 more)
Privacy-sensitive surveillance systems could benefit from large
vision-
language models (VLMs), but such models typically require centralized access to raw
video. In
federated learning settings, this challenge is amplified by non-independent and identically distributed (non-IID) client data, which can make direct multiclass anomaly classification unstable, especially for rare categories. We propose a hybrid two-stage architecture that combines a
federated binary convolutional neural network (CNN) gate with server-side zero-shot VLM inference. The lightweight LiteCNN3D gate performs local anomaly screening and forwards only flagged
videos to Qwen3-VL-8B, which assigns them to four anomaly metaclasses. We evaluate this design on UCF-Crime grouped into five coarse metaclasses and implement the
federated stage in a real three-node heterogeneous deployment. In the studied setting, direct
federated multiclass training collapses, whereas the proposed decomposition yields a better trade-off between classification quality and raw-
video transmission. With fixed-threshold routing, the
federated hybrid pipeline preserves nearly the same macro-averaged F1 score (F1-macro) as its centralized CNN+VLM counterpart while reducing the fraction of transmitted
videos to 51.4%, although with a lower proxy macro receiver operating characteristic area under the curve (ROC AUC) than the centralized hybrid system. A complementary sensitivity-oriented routing operating point increases macro ROC AUC from 0.673 to 0.692 and reduces the false negative rate from 29.3% to 22.9%, but decreases F1-macro from 0.503 to 0.485 while increasing transmission from 51.4% to 57.9%. These results suggest that federation is better suited to coarse local screening, while routing rules can be adjusted to trade server-side VLM usage for higher anomaly sensitivity.
Read the full abstract ▾
All authors Côme-Alexis Puech, Sébastien Thuau, Amira Gran, Arthur Mennessier, Siba Haidar, Rachid Chelouah
Computer Vision
Social Intuition vs. Machine Reasoning: Anticipating Human-Robot Interaction from multiple modalities
Raphael Lorenzo-Louis, Bertrand Luvison and Serena Ivaldi
Anticipating whether a person will interact from one's own perspective is a highly intuitive task for humans, that relies on a combination of cues. We investigate how humans perform at predicting a person's intention to interact from a service
robot's point of view, using pose-only or full
video input, then
benchmark different lightweight pose-based models and state-of-the-art
vision-
language models. We conducted our
benchmark on the HUI360
dataset on a fixed pilot subset of 100 test tracks (25 positive, 75 negative). We found that with pose-only input, human annotators outperform lightweight trained pose models but not by large margins (+0.08 in F1-Score). But when given full
egocentric video with a target bounding box, human annotators perform substantially better and largely outperform the
Vision-
Language Models (+0.2 in F1-Score). We also compared VLMs of different size and under different input conditions, and found that the best results do not correlate with model size. Our result confirms that predicting interactions is a challenging task for social
robots and that
reasoning-capable models are necessary but their actual
reasoning capabilities alone do not suffice to match the social intuition of humans.
Read the full abstract ▾
Computer Vision
TRAIL: Trajectory-Aware Visual Place Recognition against Unordered Databases
Dominik A. Kloepfer and Patrick Wenzel
Modern Visual Place Recognition (VPR) methods excel on standard
benchmarks yet remain brittle in feature-poor environments. By treating each query image in isolation, they discard the sequential context in any real trajectory. We formalize a task that exploits this context: given a query sequence, localize the final image against an unordered reference database – which, unlike sequence-to-sequence methods, requires no sequential structure in the database. We propose TRAIL (TRajectory-Aware Image Localization), a principled framework based on Conditional Random Fields (CRF) that combines learned functions for visual similarity and for camera-motion consistency, refining a distribution over candidate references as each query arrives. A lightweight post-processing layer atop any pre-trained VPR backbone, TRAIL improves a state-of-the-art baseline by up to 8.3 percentage points on our primary
benchmark, transfers to unseen
datasets without retraining, and delivers its largest gains where visual cues are scarce.
Read the full abstract ▾
Computer Vision
DF26: We Cannot Tell Fake From Real Anymore
Severyn Shykula, Andrii Yermakov, Ivan Samarskyi et al. (+3 more)
We introduce DF26, a novel
benchmark for detecting AI-generated
videos containing fully synthetic clips produced by recent text-to-
video and image-to-
video models. The
videos capture single-person public-speaking scenarios, spanning direct-to-camera recordings, official statements, and studio interviews - 271 real and 2,420 synthetic
videos generated by seven modern
video models. The study on DF26 shows that human performance in detecting AI-generated
videos, as well as state-of-the-art deepfake detectors, is close to random chance. Our results highlight the limitations of current evaluation protocols and motivate the need for
benchmarks that explicitly measure robustness to modern generative model distribution shifts.
Read the full abstract ▾
All authors Severyn Shykula, Andrii Yermakov, Ivan Samarskyi, Dmytro Mishkin, Jan Cech, Anastasiia Mishchuk
Computer Vision · Cross-listed from cs.CL
BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints
Zhouyuan Xu, Chen Yang, Linhao Wang et al. (+2 more)
Converting in-service reinforced-concrete (RC) building blueprints into simulation-ready models—structured frame representations that support deterministic FEM export and qualified-engineer review—underpins safety assessment and seismic retrofit, but the process remains manual. Direct prompting of a
multimodal large
language model (MLLM) over a scanned sheet is unreliable: outputs often violate engineering constraints on beam–column support, span count, or 3D continuity. We present BlueprintAgent (BPA), a constraint-triggered
multimodal agent for simulation-ready frame extraction from scanned blueprints. BPA treats the MLLM as the primary reader and decision maker, with OCR and computer
vision supplying localized evidence. Its central mechanism realizes engineering constraints as callable validators whose entity-level conflict reports trigger targeted MLLM revisits over the local region—an inference-time control distinct from fixed pipelines and free-form self-reflection. We evaluate BPA on 300 real scanned blueprint sheets from 20 anonymized RC frame projects, against five baselines and six ablations. BPA reaches a macro-averaged Beam F1 of 0.994, against 0.301 for single-MLLM zero-shot and 0.820 for a fixed pipeline; removing MLLM-led axis adjudication collapses Beam and Column F1 on complex multi-sheet projects. For dense technical drawings, engineering constraints are best deployed as triggers for entity-level targeted revisits rather than as post-hoc output filters.
Read the full abstract ▾
All authors Zhouyuan Xu, Chen Yang, Linhao Wang, Jiansheng Fan, Chen Wang
Computer Vision · Cross-listed from cs.RO
D3ARC: Time-Critical Distributed Disaster Detection for Asynchronous Cooperative Multi-Robot Systems
Nikolaos Koursioumpas, Lina Magoula, Nancy Alonistioti et al. (+1 more)
Climate change is increasing the severity and unpredictability of natural disasters. In time-critical crises such as wildfires, traditional monitoring practices remain limited by coverage, cost, and personnel risk, paving the way for autonomous and adaptive monitoring solutions. Within this context, this paper introduces D3ARC, an asynchronous distributed hierarchical framework for time-aware and reliable wildfire detection. D3ARC integrates multiple robotic
agents that cooperate under uncertainty through distributed perception, shared situational awareness and coordinated actions. A remote controller asynchronously decides upon each
robot's motion, while each robotic
agent senses the environment and decides where and how to execute the wildfire detection. All robotic operations require time, and as time progresses, wildfires continue to spread, reducing the opportunity for early intervention. As such, all
agents share a common objective: to detect a wildfire with a certain performance threshold as fast as possible and within a time limit. D3ARC integrates mechanisms for safe
navigation, coverage efficiency, cooperation and reliability. It introduces a forward-looking capability that allows
agents to anticipate the future by evaluating candidate strategies before execution. The framework is evaluated through realistic robotics simulations, ablation studies, and baseline comparisons, achieving an overall mission success up to 94% with 89.4% detection confidence.
Read the full abstract ▾
All authors Nikolaos Koursioumpas, Lina Magoula, Nancy Alonistioti, Ramin Khalili
Computer Vision
From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment
Saeed Mahmoudpour, Gi-Mun Um, Hyon-Gon Choo et al. (+1 more)
Radiance field representations such as 3D Gaussian Splatting (3DGS) enable high-quality novel view synthesis but can introduce complex, view-dependent artifacts from reconstruction, rendering, and compression. Reliable perceptual quality assessment (QA) is thus essential for evaluating rendered views and guiding the design of perceptually faithful scene representations. Existing full-reference QA metrics require an aligned reference image, while recent cross-reference metrics relax this requirement by comparing a test view with non-aligned references. However, under wide-baseline radiance field settings, selecting a reliable nearby reference can be difficult, particularly when evaluating views along arbitrary trajectories and poses. We propose SCODA, a lightweight scene-conditioned objective QA method that shifts QA from explicit image-to-image comparison to scene-
manifold modeling. High-quality observations of each scene are represented as a multivariate Gaussian distribution in deep feature space, producing a semantic fidelity score that measures deviation from the scene distribution. A weakly-supervised distortion-aware patch discriminator provides a complementary realism signal, and both cues are combined through an unsupervised bounded fusion strategy. Experiments on multiple
benchmarks show strong agreement with human judgments and robust generalization across GS- and NeRF-generated views and trajectories. Code is publicly available at https://gitlab.com/saeedmp/scoda.
Read the full abstract ▾
All authors Saeed Mahmoudpour, Gi-Mun Um, Hyon-Gon Choo, Peter Schelkens
Computer Vision
CRISP: Corneal Confocal Microscopy Real-Time Image Stitching Pipeline
Qincheng Qiao, Puli Zhang, Jian Zhou et al. (+1 more)
Morphology of the sub-basal nerve plexus (SNP) reflects peripheral nerve health, and corneal confocal microscopy (CCM) provides an important means for in vivo, real-time, non-invasive observation of the SNP. However, mainstream CCM devices offer a limited field of view per frame, whereas the SNP is spatially non-uniform; discrete image sampling is therefore sensitive to sampling location and frame selection, which limits the reproducibility and clinical adoption of CCM as a quantitative assessment tool. Wide-field stitching can reconstruct larger SNP mosaics by integrating sequentially acquired CCM images, but existing methods largely rely on offline post-processing, additional hardware, or specific acquisition protocols, and lack open-source real-time solutions for conventional CCM
video streams. This paper presents CRISP (Corneal confocal microscopy Real-time Image Stitching Pipeline), an open-source real-time SNP wide-field stitching framework for conventional CCM examination
video streams. CRISP excludes defocused and discontinuous segments via focus-aware gating, propagates poses through local pairwise registration, and maintains non-redundant spatial coverage with a sparse anchor map; when local temporal continuity is interrupted, the system completes relocalization and subgraph merging through global appearance
retrieval followed by
geometric verification. The framework prioritizes low-latency coverage feedback during examination while outputting accepted frames, poses, and anchor information to initialize offline fine stitching. To our knowledge, CRISP is the first open-source real-time SNP wide-field stitching framework released for conventional CCM
video streams. By lowering the barrier to adoption and reproduction of wide-field stitching, CRISP may help move SNP wide-field imaging from a research tool into routine clinical examination workflows.
Read the full abstract ▾
All authors Qincheng Qiao, Puli Zhang, Jian Zhou, Xinguo Hou
Computer Vision · Cross-listed from cs.AI
Weakly supervised neural network: segmentation of complex structures in X-ray microCT
Daniele Rusconi, Michela Ascolese, Stephanie Fest-Santini et al. (+2 more)
Segmentation of complex structures in X-ray tomographic data is a fundamental task in biomedical research, but it often requires large amounts of precisely annotated data, making fully supervised approaches costly and difficult to scale. In this study, weakly supervised deep learning is investigated as a strategy to reduce annotation effort while maintaining accurate
segmentation. A two-dimensional convolutional neural network based on the nnU-Net framework was adapted to a weak supervision setting using sparse dot-based annotations, complemented by a limited number of fully segmented images. The approach was evaluated on high-resolution microCT slices of rat kidneys, targeting the
segmentation of renal glomeruli, which are small, low-contrast anatomical structures. Results indicate that weak supervision provides a meaningful learning signal, enabling reliable localization of glomeruli even in the absence of dense labels. Incorporating a small set of high-quality annotations substantially improves
segmentation performance, approaching that of a fully supervised model. These findings highlight the potential of weakly supervised learning as an annotation-efficient strategy for the analysis of complex structures in X-ray tomographic data, and suggest that alternative loss formulations tailored to sparse annotations may further enhance performance.
Read the full abstract ▾
All authors Daniele Rusconi, Michela Ascolese, Stephanie Fest-Santini, Alberto Bravin, Maurizio Santini
Computer Vision
KODAMA: Multimodal Digital Twin Reconstruction for Urban RF Propagation Modelling
Maximiliano Wardle and A. Ryo Koblitz
3D reconstruction typically strives for
geometric fidelity or visual plausibility.
Radio frequency digital twins (RFDT) are instead judged by whether communication channels behave in them as they do in the real world. RFDTs promise site-specific channel prediction but current practice forces a choice between coarse automated scenes and hand-built, measurement-calibrated models that take weeks to construct per-site. We present KODAMA, an automated pipeline that reconstructs ray tracing-ready RFDTs at city scale from off-the-shelf geospatial data alone: aerial imagery,
LiDAR, and photogrammetry yield terrain and watertight building meshes, while exposure-weighted multi-view fusion of street-level imagery recovers façade relief, electromagnetic materials, and clutter—all without site visits or calibration. Across three sites spanning 3.6 to 28 GHz, KODAMA's uncalibrated predictions achieve single-digit RMSE, reducing point-to-point error by up to 5.35 dB over automated baselines and coming within 0.22 dB of a measurement-calibrated, hand-built RFDT.
Read the full abstract ▾