Skip to content
AI Atlas
Research

Papers

Publications linked to models, labs and benchmarks. Authors, venues and abstracts come from arXiv and publisher pages.

191 total

Reset
Papers
TitleAuthorsPublishedCategoriesOrganization / venueQuality
HiPerViT: A Hierarchical Perceiver-Vision Transformer Architecture for Multi-Scale Texture RecognitionarXiv:2609.10917Jo\~ao Pedro C. A. de S\'a, Odemir Martinez Bruno11 Sept 2026cs.CV—89
CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie GenerationarXiv:2609.10943Yang Wu, Stefano Petrangeli, Ishita Dasgupta +111 Sept 2026cs.CV—89
Toward Interpretable Multimodal Fusion: Heat Conduction Modeling for Hyperspectral and LiDAR Joint ClassificationarXiv:2609.11040Kan Wei, Jiahui Cui, Jing Yao +211 Sept 2026cs.CV—89
Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World ConditionsarXiv:2609.11126Dieuwertje Alblas, Alma M. Liezenga, Jan Erik van Woerden +211 Sept 2026cs.CV—89
ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and ModulationarXiv:2609.11129Jiarui Liu, Heng Li, Weiyu Li +211 Sept 2026cs.CV—89
LAION-Mobile: Evaluating Deepfake Detectors On One Million Smartphone PhotosarXiv:2609.11134Achim von Stryk, Janis Keuper11 Sept 2026cs.CV—89
UniH$^3$: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image RestorationarXiv:2609.11156Zhiwen Yang, Jiayin Li, Chengyu Liu +211 Sept 2026cs.CV—79
Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEvalarXiv:2609.11172Yilin Long, Chenming Zhu, Zitang Gou +211 Sept 2026cs.CV—89
A Multi-View and Confusion-Guided Ensemble Framework for Robust Synthetic Image AttributionarXiv:2609.11188Zuomin Qu11 Sept 2026cs.CV—89
CEM-TUDASR: Computationally efficient multi-modality transformer based unsupervised domain adaptive super-resolution approacharXiv:2609.11201Anjali Sarvaiya, Jay Kadel, Kishor Upla +111 Sept 2026cs.CV—89
Tri-DehazeGS: Scene--Medium Decoupled Gaussian Splatting with Transmittance-Aware OptimizationarXiv:2609.11223Kui Jiang, Yang Gu, Jiacheng Liu +211 Sept 2026cs.CV—89
When is Test-Time Adaptation Identifiable From Unlabeled Evidence?arXiv:2609.11235Kartik Jhawar, Lipo Wang11 Sept 2026cs.CV—89
HALDETECT at ImageEval 2026 Shared Tasks: Answer-First Contrastive Grounding with QLoRAarXiv:2609.11236Syed Mohaiminul Hoque, Md Sakhawat Hossain11 Sept 2026cs.CV—89
SCINTILLA-SNN: A Spiking Multi-Scale Selective Aggregation Network for Perineural Invasion PredictionarXiv:2609.11237Youngung Han, Yului Jeong, Kyeonghun Kim +211 Sept 2026cs.CV—89
Fast and Accurate Monomodal 3D High Resolution Deep Registration of Drosophila Larval Brain VolumesarXiv:2609.11240Daniel Reisenb\"uchler, Yousef Sadegheih, Michael Dittrich +211 Sept 2026cs.CV—89
From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative ModelsarXiv:2609.11242Meng Luo, Yicheng Liu, Jiahao Wang +211 Sept 2026cs.CV—89
Uncertainty DMD: Restoring Diversity in Few-Step Autoregressive Video DistillationarXiv:2609.11265Zixuan Duan, Xunzhi Xiang, Yabo Chen +211 Sept 2026cs.CV—89
Order-Aware 2.5D Multiple Instance Learning for Preoperative MRI-Based Perineural Invasion Risk Assessment in Intrahepatic CholangiocarcinomaarXiv:2609.11271Hyunsu Go, Youngung Han, Kyeonghun Kim +211 Sept 2026cs.CV—89
SAMV-DUSt3R: Instance-Centric 3D Scene Decoupling from Sparse Multi-ViewsarXiv:2609.11279Langxu Zhao, Zuan Gu, Yingdan Zhang +211 Sept 2026cs.CV—89
GRIPNet: Gaussian Radial Intensity Prior Guided Architecture for Pulmonary Nodule Detection in CTarXiv:2609.11312Haojie Yang, Ran Su11 Sept 2026cs.CV—89
Mi-Ripple: Restoring Images Degraded by Iterative AI EditingarXiv:2609.11317Jiayin Chen, Yicheng Xu, Muting Wang11 Sept 2026cs.CV—79
Predictive Multi-Landmark OCT Tracking for Increased Motion RobustnessarXiv:2609.11330Konrad Reuter, Suresh Guttikonda, Chaitali Uday Karekar +211 Sept 2026cs.CV—89
R4Tun: LLM-guided adaptive segmental tunnel lining segmentation in point cloudsarXiv:2609.11360Xinghui Tao, Zehao Ye, Guangming Wang +211 Sept 2026cs.CV—89
Vision Transformer-Based Multi-Level Feature Fusion for Multi-Label Sewer Defect ClassificationarXiv:2609.11375Xu Fang, Zhuoran Wang, Qing Li +211 Sept 2026cs.CV—89
Brain-PACE: A Deep Siamese MRI Framework for Modelling Longitudinal Brain AccelerationarXiv:2609.11378Samuel Maddox (School of Computing Sciences, University of East Anglia), Jacob Newman (School of Computing Sciences +211 Sept 2026cs.CV—89
DINO-Med: A Unified Patch-Based Adaptation Framework for Multi-Modal Medical Image Analysis Applied to Liver Fibrosis StagingarXiv:2609.11380Boya Wang, Ruizhe Li, Chao Chen +111 Sept 2026cs.CV—89
Multi-Modal Controlled Coherent Motion GenerationarXiv:2609.11439Yifei Liu, Qiong Cao, Hongwei Yi +211 Sept 2026cs.CV—89
BruNet: A Cross-Domain Transfer Framework for Bruise SegmentationarXiv:2609.11463Qiming Wang, Richard J. Motley, Ebube E. Obi +211 Sept 2026cs.CV—89
BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable RegistrationarXiv:2609.11472Qianliang Wu, Haobo Jiang, Guangwei Gao +211 Sept 2026cs.CV—89
Pre- and Post-Treatment Brain Metastases Segmentation Using nnU-Net with Post-Processing for BraTS 2026arXiv:2609.11477Haobin Liu, Xin Wang11 Sept 2026cs.CV—89
FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow EstimationarXiv:2609.11486Vladislav Bargatin, Alexander Yakovenko, Khaled Abud +111 Sept 2026cs.CV—80
Recursive Code World Models: Building Complex Worlds through Recursive Scene ProgramsarXiv:2609.11499Zhiqi Li, Yuxuan Liao, Bo Zhu11 Sept 2026cs.CV—81
UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from UltrasoundarXiv:2609.11506Weiying Chen, Yuchong Gao, Siyuan Li +211 Sept 2026cs.CV—89
Harnessing Intrinsic Subject-Aware Attention for Controllable Multi-Subject Video GenerationarXiv:2609.11507Niange Yu, Ye Tian, Biaolong Chen +211 Sept 2026cs.CV—89
Prototype Matters: Modality-unified Prototype Self-distillation for Unsupervised Visible-infrared Person Re-identificationarXiv:2609.11514Menglin Wang, Xiaojin Gong11 Sept 2026cs.CV—89
LoopVAE: Recurrent Depth Across Scales for Visual TokenizationarXiv:2609.11516Zhiying Lu11 Sept 2026cs.CV—89
Learning Interaction between Image and Layout Priors for Joint Image-Layout Generation in Design TemplatesarXiv:2609.11519Shirong Yang, Bo Yang, Ying Cao11 Sept 2026cs.CV—89
World in World: Explore the World with World ModelsarXiv:2609.11548Chenxi Song, Yanming Yang, Chi Zhang11 Sept 2026cs.CV—81
A Comparative Evaluation of Pre-trained Convolutional Neural Networks for Melanoma DetectionarXiv:2609.11550Wagner Moreno Schmitz, Marco Antonio de Castro Barbosa, Thiago Magalh\~aes Amaral +211 Sept 2026cs.CV—89
Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary RepresentationsarXiv:2609.11573Heinrich Jiang, Hager Yasser Mohamed, Alexander Hitt +211 Sept 2026cs.CV—89

Author lists and categories are copied from the paper's own metadata (arXiv, publisher). Each paper page shows the abstract, related models and every source snapshot.