WACV 2026

831 papers

VitaGlyph: Vitalizing Artistic Typography with Flexible Dual-branch Diffusion Models

Kailai Feng, Yabo Zhang, Haodong Yu, Zhilong Ji, Jinfeng Bai

Federated Model Synchronization for Diagnostic Redefinition through a Novel Selective Parameter Unlearning

Mayank Kumar Kundalwal, Mamta Mamta, Deepak Mishra, Asif Ekbal

MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data

Siarhei Sheludzko, Dhimitrios Duka, Bernt Schiele, Hilde Kuehne, Anna Kukleva

PredMapNet: Future and Historical Reasoning for Consistent Online HD Vectorized Map Construction

Bo Lang, Nirav Savaliya, Zhihao Zheng, Jinglun Feng, Zheng-Hang Yeh

DiRe: Diversity-promoting Regularization for Dataset Condensation

Saumyaranjan Mohanty, Aravind Reddy, Konda Reddy Mopuri

Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation

Huaying Zhang, Atsushi Hashimoto, Tosho Hirasawa

Learning Group Actions In Disentangled Latent Image Representations

Farhana Hossain Swarnali, Miaomiao Zhang, Tonmoy Hossain

Multi-Modal Soccer Scene Analysis with Masked Pre-Training

Marc Peral, Guillem Capellera, Luis Ferraz, Antonio Rubio, Antonio Agudo

General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood

Roy Betser, Omer Hofman, Roman Vainshtein, Guy Gilboa

Morphing Through Time: Diffusion-Based Bridging of Temporal Gaps for Robust Alignment in Change Detection

Seyedehanita Madani, Vishal M. Patel

AirLock+: Scaling UAV-to-Satellite Image Registration for Target Geolocalization and Geospatial Augmented Reality

Zhiyun Deng, Austin Case, Luis Sentis

DreamMakeup: Face Makeup Customization using Latent Diffusion Models

Geon Yeong Park, Inhwa Han, Serin Yang, Yeobin Hong, Seongmin Jeong

Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models

Masayuki Kawarada, Kosuke Yamada, Antonio Tejero-De-Pablos, Naoto Inoue

MARS: a Multimodal Alignment and Ranking System for Few-Shot Segmentation

Nico Catalano, Stefano Samele, Paolo Pertino, Matteo Matteucci

Fine-grained Defocus Blur Control for Generative Image Models

Ayush Shrivastava, Connelly Barnes, Xuaner Zhang, Lingzhi Zhang, Andrew Owens

LENVIZ: A High-Resolution Low-Exposure Night Vision Benchmark Dataset

Manjushree Aithal, Rosaura G VidalMata, Manikandtan Kartha, Gong Chen, Eashan Adhikarla

T2LF: LLM-Guided Multimodal Diffusion for Text-to-Light Field Synthesis

Soyoung Yoon, Namhyuk Ahn, In Kyu Park

FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair

Arya Fayyazi, Mehdi Kamal, Massoud Pedram

ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corpora

Nikolas Adaloglou, Diana Petrusheva, Mohamed Asker, Felix Michels, Markus Kollmann

Beyond Realism: Learning the Art of Expressive Composition with StickerNet

Haoming Lu, David Kocharian, Humphrey Shi

4D Multimodal Co-attention Fusion Network with Latent Contrastive Alignment for Alzheimer's Diagnosis

Yuxiang Wei, Yanteng Zhang, Xi Xiao, Tianyang Wang, Xiao Wang

GroupPortrait: Multi-ID Portrait Generation with High Identity Preservation and Fine-Grained Control

Meijia Huang, Ruida Li, Bing Ma, Liangwei Jiang, Shuo Fang

Graph Query Networks for Object Detection with Automotive Radar

Loveneet Saini, Hasan Tercan, Tobias Meisen

ProtoGMVAE: A Variational Auto-Encoder with True Gaussian Mixture Prior for Prototypical-based Self-Explainability

Martin Blanchard, Christophe Ducottet, Damien Muselet, Olivier Delézay

Learning Spatio-temporal Feature Representations for Video-based Gaze Estimation

Alexandre Personnic, Mihai Bâce

Motion-Aware Graph Fusion Network for 3D Human Pose Estimation

Yen Pham, Xiaohui Yuan, Chengyuan Zhuang

Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA Adapters

Pin-Yen Chiu, I-Sheng Fang, Jun-Cheng Chen

Detecting Social Engagement of Elderly From Lifelog Image-streams to Identify Effective Cues for Autobiographic Recall

Vengateswaran Subramaniam, Vigneshwaran Subbaraju, Debaditya Roy, Pramath Krishna, Thivya Kandappu

OSEG: Improving Diffusion sampling through Orthogonal Smoothed Energy Guidance

Masud An Nur Islam Fahim, Nazmus Saqib, Joon-Min Gil

PerVL-Bench: Benchmarking Multimodal Personalization for Large Vision-Language Models

Minsung Kim

FARF-Net: Frequency-guided Adaptive Receptive Field Network for Edge-enhanced Polyp Segmentation

Xue Li, Aiwen Jiang, Hongqian Yu, Yang Xiao

Yue-Gao Lu, Hong-Jie Xing, Chun-Guo Li

Flood-LDM: Generalizable Latent Diffusion Models for rapid and accurate zero-shot High-Resolution Flood Mapping

Sun Han Neo, Sachith Seneviratne, Herath Mudiyanselage Viraj Vidura Herath Herath, Abhishek Saha, Sanka Rasnayaka

FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy

Haochen Zhang, Nirav Savaliya, Faizan Siddiqui, Enna Sachdeva

WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fields

Sadra Safadoust, Fabio Tosi, Fatma Guney, Matteo Poggi

Understanding the Visual Projection Space of Multimodal LLMs

SungHeon Jeong, Yoojeong Song, Hyungjoon Kim

GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving

William Ljungbergh, Adam Lilja, Adam Tonderski, Arvid Laveno Ling, Carl Lindström

Dronaquatics: Real-time Swimming Analytics Using Drone Captured Imagery

Thu Tran, Harold Abraham Joseph, Kichang Lee, Kenny Tsu Wei Choo, Dong Ma

F-INR: Functional Tensor Decomposition for Implicit Neural Representations

Sai Karthikeya Vemuri, Tim Büchner, Joachim Denzler

Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction

Ce Zhang, Yale Song, Ruta Desai, Michael Louis Iuzzolino, Joseph Tighe

Odo: Depth-Guided Diffusion for Identity-Preserving Body Reshaping

Siddharth Khandelwal, Sridhar Kamath, Arjun Jain

Multi-Grained Text-Guided Image Fusion for Multi-Exposure and Multi-Focus Scenarios

Mingwei Tang, Jiahao Nie, Guang Yang, Ziqing Cui, Jie Li

Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model

Sangjune Park, Inhyeok Choi, Donghyeon Soon, Youngwoo Jeon, Kyungdon Joo

SFMNet: Sparse Focal Modulation for 3D Object Detection

Oren Shrout, Ayellet Tal

TopoRec: Point Cloud Recognition Using Topological Data Analysis

Anirban Ghosh, Iliya Kulbaka, Ian Dahlin, Ayan Dutta

CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning

Zeyuan Chen, Xiang Zhang, Haiyang Xu, Jianwen Xie, Zhuowen Tu

Controllable Long-term Motion Generation with Extended Joint Targets

Eunjong Lee, Eunhee Kim, Sanghoon Hong, Eunho Jung, Jihoon Kim

Can Image Splicing and Copy-Move Forgery Be Detected by the Same Model? Forensim: An Attention-Based State-Space Approach

Soumyaroop Nandi, Prem Natarajan

ODEt(ODEl): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling

Denis Gudovskiy, Wenzhao Zheng, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer

3D Gaussian Point Encoders

Jim James, Benjamin Wilson, Simon Lucey, James Hays

A-V Representation Learning via Audio Shift Prediction for Multimodal Deepfake Detection and Temporal Localization

Ashutosh Anshul, Eng Siong Chng, Deepu Rajan

DocWaveDiff: A Predict-and-Refine approach for Document Image Enhancement with Wavelet U-Nets and Diffusion models

Matteo Marulli, Marco Bertini

LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization

Jie Li, Kwan-Yee K. Wong, Kai Han

Revisiting Layer Normalization for Point Cloud Test Time Adaptation

Moslem Yazdanpanah, Ali Bahri, Mehrdad Noori, Sahar Dastani, Samuel Barbeau

Hymavi : A Hybrid Mamba-Attention Network in Multi-View Framework for Volumetric Medical Image Segmentation

Sy Dat Tran, Jin Kyu Gahm

Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding

Shristi Das Biswas, Efstathia Soufleri, Arani Roy, Kaushik Roy

ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance

Congjia Chen, Shen Yan, Yufu Qu

DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection

Paul Hill, Zhiming Liu, Alin Achim, David Bull, Nantheera Anantrasirichai

MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction

Akshit Sharma, Prashant W Patil

NAPP: Noise-Adaptive Prototype Perturbation for Few-Shot Learning

Ilhwan Kim, Sangwoo Yun, Dongheon Lee, Seongsu Kim, Joonki Paik

False Alarm Rectification for Early Smoke Segmentation

Hongjin Zhao, Weihao Li, Ge-Peng Ji, Nick Barnes

CLoCKDistill: Consistent Location and Context aware Knowledge Distillation for DETRs

Qizhen Lan, Qing Tian

QCFace: Image Quality Control for boosting Face Representation & Recognition

Duc-Phuong Doan-Ngo, Thanh-Dang Diep, Thanh Nguyen-Duc, Thanh-Sach LE, Nam Thoai

GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring

Maximilian Schall, Felix Leonard Knöfel, Noah Elias König, Jan Jonas Kubeler, Maximilian von Klinski

DreamCatcher: Efficient Multi-Concept Customization via Representation Finetuning

Jungwon Lee, Changhun Lee, Eunhyeok Park

MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection

Saad Lahlali, Alexandre Fournier-Mongieux, Nicolas Granger, Herve Le Borgne, Quoc-Cuong Pham

AusSmoke meets MultiNatSmoke: a fully-labelled diverse smoke segmentation dataset

Weihao Li, Hongjin Zhao, Gao Zhu, Ge-Peng Ji, Nicholas Wilson

OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models

Ryoto Miyamoto, Xin Fan, Fuyuko Kido, Tsuneo Matsumoto, Hayato Yamana

CommonForms: A Large, Diverse Dataset for Form Field Detection

Joe Barrow

Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models

Mohamad Zamini, Diksha Shukla

VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework

Donglin Huang, Yongyuan Li, Tianhang Liu, Junming Huang, Xiaoda Yang

Feature-Disentangling RGB-NIR Fusion Network for Remote Driver Physiological Measurement

Tayssir Bouraffa, Ziyuan Wang, Daniel Strüber

Visibility guided Self-Supervised Occlusion-Resilient Human Pose Estimation

Arindam Dutta, Sarosij Bose, Rohit Kundu, Calvin-Khang Ta, Saketh Bachu

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening

Guanhong Tao, Siyuan Cheng, Guangyu Shen, Yingqi Liu, Shengwei An

Timestamp Query Transformer for Temporal Action Segmentation

Tieqiao Wang, Sinisa Todorovic

BiNAR: A Bi-Modal Framework for Non-Aligned RGB-IR 3D Reconstruction via Gaussian Splatting

Zhongwen Wang, Han Ling, Weihao Zhang, Yinghui Sun, Quansen Sun

High-Level Semantics and Low-Level Features Fusion for Multi-Scale Object Detection in Dynamic Construction Environments

Mahdi Bonyani, Maryam Soleymani, Chao Wang

High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization

Masih Aminbeidokhti, Heitor Rapela Medeiros, Srikanth Muralidharan, Eric Granger, Marco Pedersoli

Beyond Faces: A Multimodal Person Clustering for Unconstrained Environments

Sahngmin Yoo, Sangwon Lee, Seongin Jo

AortaDiff: A Unified Multitask Diffusion Framework for Contrast-Free AAA Imaging

Yuxuan Ou, Ning Bi, Jiazhen Pan, Jiancheng YANG, Boliang Yu

HyperPose: Hyper-pose Embeddings for 3D-Aware Generative Models with Self-Supervised Disentangling of Pose and Scene

Mijeong Kim, Namgi Kim, Bohyung Han

CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video

Xinyi Wang, Angeliki Katsenou, Junxiao Shen, David Bull

SSMRadNet : A Sample-wise State-Space Framework for Efficient and Ultra-Light Radar Segmentation and Object Detection

Anuvab Sen, Mir Sayeed Mohammad, Saibal Mukhopadhyay

Align Video Diffusion Model with Online Video-Centric Preference Optimization

Jiacheng Zhang, Jie Wu, Weifeng Chen, Yatai Ji, Xuefeng Xiao

NerVast: Compression-Efficient Scaling of Implicit Neural Video Representations via Scene-based Parameter-sharing

Yunheon Lee, Juncheol Ye, Jaehong Kim, Dongsu Han

Curve Skeletonization in Continuous domain for Meshes and Point Clouds

Jai Bardhan, Ramya Hebbalaguppe, Aravind Udupa

Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning

Sungrae Hong, Sol Lee, Jisu Shin, Jiwon Jeong, Mun Yong Yi

MageBench: Bridging Large Multimodal Models to Agents

Miaosen Zhang, Qi Dai, Yifan Yang, Jianmin Bao, Dongdong Chen

Hybrid State Representation for Video Procedure Planning

Woo Suk Choi, Youwon Jang, Minsu Lee, Byoung-tak Zhang

Trajectory Tactics: When Transformers Learn Exploration to Generate Online Signature

Anurag Pandey, Aditya Nigam, Arnav Bhavsar, Ashutosh Sharma, Basu Verma

Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting

Hao-Jen Chien, Yi-Chuan Huang, Chung-Ho Wu, Wei-Lun Chao, Yu-Lun Liu

Streaming Real-Time Trajectory Prediction Using Endpoint-Aware Modeling

Alexander Prutsch, David Schinagl, Horst Possegger

CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion

Ayan Banerjee, Nityanand Mathur, Josep Lladós, Umapada Pal, Anjan Dutta

DPBridge: Latent Diffusion Bridge for Dense Prediction

Haorui Ji, Taojun Lin, Hongdong Li

MoSCo: Real-time and Efficient Text-to-Motion Synthesis via Delta Training

Zhiyuan Zhang, Lingqiao Liu

Latent Uncertainty-Aware Multi-View SDF Scan Completion

Faezeh Zakeri, Lukas Ruppert, Raphael Braun, Hendrik P.A. Lensch

Q-Former Autoencoder: A Modern Framework for Medical Anomaly Detection

Francesco Dalmonte, Emirhan Bayar, Emre Akbas, Mariana-Iuliana Georgescu

How to Design and Train Your Implicit Neural Representation for Video Compression

Matthew Gwilliam, Roy Zhang, Namitha Padmanabhan, Hongyang Du, Abhinav Shrivastava

RampWatch: An In-the-Wild Dataset and Text-Guided Detection Framework for Recreational Vessels

Malik Muhammad Asim, Claire B. Smallwood, Abdullah Tariq, Johnny Lo, Syed Zulqarnain Gilani

Human Pose Aggregation for Multi-View Temporal Video Alignment

Fabien Delattre, Tsung-Wei Huang, Guan-Ming Su, Erik Learned-Miller