Schedule Mon Tue Wed Thu

BMVC conference papers, supplementary material and video presentations can be found at: BMVC Papers (To be added)

BMVC workshop papers can be found at: BMVC Workshop Papers (To be added)

Keynote 2 - Marc Pollefeys
09:00 - 10:00
09:00 - 10:00 Title: Spatial AI

Abstract: In this talk we’ll discuss how to build rich 3D representations of the environment to assist people and robots to perform tasks. We’ll first discuss how to build visual 3D maps of environments and use those for visual (re)localization, spatial data access and navigation. We’ll cover recent methods based on geometry, learning and combining both. One of the questions we will consider is what is best learned and where we should use explicit geometric concepts. We’ll also discuss how to build rich 3D semantic representations that enable queries and interactions with the scene. Our approach allows open vocabulary queries by leveraging foundation models. While these models are very powerful in recognizing arbitrary objects, there are some aspects that are still missing to enable robotic interactions. We’ll also briefly cover some of our work on action recognition which is key in building AI assistants and could also be useful to enable robots to learn from examples.

Location: Main Hall, Cutlers' Hall
Poster Session 3 - 3D Scene Analysis and Understanding
10:00 - 11:45
10:00 - 11:45
Papers Presented
630Incremental Multi-Scene Modeling via Continual Neural Graphics PrimitivesPrajwal Singh, Ashish Tiwari, Gautam Vashishtha, Shanmuganathan Raman
1257End-to-End LiDAR optimization for point cloud registrationSiddhant Katyan, Marc-Andre Gardner, Jean-Francois Lalonde
238Capture and Reconstruct 3D Clothed Human from ImagesOnat Vuran, Hsuan-I Ho
1220Hair Strand Reconstruction based on 3D Gaussian SplattingYimin Pan, Matthias Nießner, Tobias Kirschstein
195Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape ClassificationShuxian Ma, Zihao Dong, Runmin Cong, Sam Tak-Wu Kwong, Xiuli Shao
18Volumetric Temporal Texture for Smoke Stylization using Dynamic Radiance FieldsDongqing Wang, Ehsan Pajouheshgar, Yitao Xu, Tong Zhang, Sabine Süsstrunk
1035Superpixel Anything: A general object-based framework for accurate yet regular superpixel segmentationJulien Walther, Rémi Giraud, Michaël Clément
787C3-GS: Learning Context-aware, Cross-dimension, Cross-scale Feature for Generalizable Gaussian SplattingYuxi Hu, Jun Zhang, Kuangyi Chen, Zhe Zhang, Friedrich Fraundorfer
548Pandora: Articulated 3D Scene Graphs from Egocentric VisionAlan Yu, Yun Chang, Christopher Xie, Luca Carlone
367RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene ReconstructionZhuodong Jiang, Haoran Wang, Guoxi Huang, Brett Seymour, Nantheera Anantrasirichai
1110Robust Human Registration with Body Part Segmentation on Noisy Point CloudsKai Lascheit, Francis Engelmann, Daniel Barath, Marc Pollefeys, Leonidas Guibas
328DepthHMR: Leveraging Depth Around Humans for Multi-Human Mesh GenerationNikhil Sharma, Jiachen Tao, Junyi Wu, Yan Yan
603Dual-Stream Adapters for Open-Set Segmentation in Driving ScenesShyam Nandan Rai, Massimiliano Mancini, Barbara Caputo, Carlo Masone
851Asymmetric Event-Image Stereo with Temporal Feature Gating and Iterative Structure-Detail RefinementHao Zhuang, Yan Yang, Liyuan Pan
6563D Curvix: From Multiview 2D Edges to 3D Curve SegmentsQiwu Zhang, Chiang-Heng Chien, Benjamin Kimia, Ricardo Fabbri
81SSNeRF: Sparse View Semi-supervised Neural Radiance Fields with AugmentationXiao Cao, Beibei Lin, Bo Wang, Zhiyong Huang, Robby T. Tan
1096LED: Light Enhanced Depth Estimation at NightSimon de Moreau, Yasser Almehio, Andrei Bursuc, Hafid EL IDRISSI, Bogdan Stanciulescu, Fabien Moutarde
12Part Segmentation and Motion Estimation for Articulated Objects with Dynamic 3D GaussiansJun-Jee Chao, Qingyuan Jiang, Volkan Isler
136Lang4D: Weakly Supervised Learning of 4D Language SplattingMana Masuda, Taiki Sekii
543Temporally Compressed 3D Gaussian Splatting for Dynamic ScenesSaqib Javed, Ahmad Jarrar Khan, Corentin Dumery, Chen Zhao, Mathieu Salzmann
310PME3D: An Adaptive and Efficient Multi-modal Feature Extraction Plug-in for 3D Object DetectionTianyi Yu, Lei Yu
981Ev4DGS: Novel-view Rendering of Non-Rigid Objects from Monocular Event StreamsTakuya Nakabayashi, Navami Kairanda, Hideo Saito, Vladislav Golyanik
540OptSplat: Recurrent Optimization for Generalizable Reconstruction and Novel View RenderingsVemburaj Chockalingam Yadav, Alain Pagani, Didier Stricker
516Making Rotation Averaging Fast and Robust with Anisotropic Coordinate DescentYaroslava Lochman, Carl Olsson, Christopher Zach
359SteerPose: Simultaneous Extrinsic Camera Calibration and Matching from ArticulationSang-Eun Lee, Ko Nishino, Shohei Nobuhara
402Log NeRF: Comparing Spaces for Learning Radiance FieldsSihe Chen, Luv Verma, Bruce A. Maxwell
427Interactive Occlusion Boundary Estimation through Exploitation of Synthetic DataLintao XU, Chaohui Wang
24MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian DetectionTaiga Yamane, Satoshi Suzuki, Ryo Masumura, Shota Orihashi, Tomohiro Tanaka, Mana Ihori, Naoki Makishima, Naotaka Kawata
3993D Shape Reconstruction from Autonomous Driving RadarsSamah Hussein, Junfeng Guan, Swathi Shree Narashiman, Saurabh Gupta, Haitham Al Hassanieh
915DualDistill: A Unified Cross-Modal Knowledge Distillation Framework for Camera-Based BEV RepresentationGaeun Kim, Daeil Han, Yeong Jun Koh, Hanul Kim
391Depth Inconsistency-based spatial-channel attention gate for Mirror SegmentationRitsuki Kurohiji, Hirotaka Hachiya
694Occam's LGS: An Efficient Approach for Language Gaussian SplattingJiahuan Cheng, Jan-Nico Zaech, Luc Van Gool, Danda Pani Paudel
1156Hierarchical Image-Guided 3D Point Cloud Segmentation in Industrial Scenes via Multi-View Bayesian FusionYu Zhu, Naoya Chiba, Koichi Hashimoto
835Cloud-Stereo: A Dataset and Benchmark for Reconstructing Atmospheric Clouds from Stereo ImagesJacob Lin, Edward Gryspeerdt, Ronald Clark
289CHIP: A multi-sensor dataset for 6D pose estimation of chairs in industrial settingsMattia Nardon, Mikel Mujika Agirre, Ander González Tomé, Daniel Sedano Algarabel, Josep Rueda Collell, Ana Paola Caro, Andrea Caraffa, Fabio Poiesi, Paul Ian Chippendale, Davide Boscaini
Location: Cutlers' Hall
Oral Session 3 - 3D Scene Analysis and Understanding
11:45 - 13:00
Chair: To be announced 11:45 827
MonoTracker: Monocular RGB-Only 6D Tracking of Unknown Object
Zilong Deng, Shaochang Tan, Zuria Bauer, Daniel Barath, Marc Pollefeys
12:00 690
MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction
Kunyi Li, Michael Niemeyer, Zeyu Chen, Nassir Navab, Federico Tombari
12:15 649
Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes
Xinhao Xiang, Kuan-Chuan Peng, Suhas Lohit, Michael J. Jones, Jiawei Zhang
12:30 1077
Towards Sharper Object Boundaries in Self-Supervised Depth Estimation
Aurélien Cecille, Stefan Duffner, Franck Davoine, Rémi Agier, Thibault Neveu
12:45 133
M$^2$StyleGS: Multi-Modality 3D Style Transfer with Gaussian Splatting
Xingyu Miao, Xueqi Qiu, Haoran Duan, Yawen Huang, Xian Wu, Jingjing Deng, Yang Long
Location: Main Hall, Cutlers' Hall
Poster Session 4 - Medical and Biological Image Analysis and Real World Applications and Systems
14:00 - 15:45
14:00 - 15:45
Papers Presented
1029PrIINeR: Towards Prior-Informed Implicit Neural Representations for Accelerated MRIZiad Al-Haj Hemidi, Eytan Kats, Mattias P. Heinrich
1196IoSR: End-to-End Intraoral Scans RepairingManel Farhat, Achraf Ben-hamadou, Ahmed rekik, Ons Abida, Oussama smaoui
1121MIAS-SAM: Medical Image Anomaly Segmentation without thresholdingMarco Colussi, Dragan Ahmetovic, Sergio Mascetti
122Distribution-guided Generative Replay with Semantic Prompts for Class-Incremental Chest X-ray DiagnosisJayant Mahawar, Devi Prasad Maharathy, Angshuman Paul
121BOTM: Echocardiography Segmentation via Bi-directional Optimal Token MatchingZhihua Liu, Lei Tong, Xilin He, Che Liu, Rossella Arcucci, Chen Jin, Huiyu Zhou
943HEAL: Learning-Free Source Free Unsupervised Domain Adaptation for Cross-Modality Medical Image SegmentationYulong Shi, Jiapeng Li, Lin Qi
940Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology SegmentationNguyen Lan Vi Vu, Thanh-Huy Nguyen, Thien Nguyen, Daisuke Kihara, Tianyang Wang, Xingjian Li, Min Xu
1061IPGPhormer: Interpretable Pathology Graph-Transformer for Survival AnalysisGuo Tang, Songhan Jiang, Jinpeng Lu, Linghan Cai, Yongbing Zhang
1004RP-SAM2: Refining Point Prompts for Stable Surgical Instrument SegmentationNuren Zhaksylyk, Ibrahim Almakky, Jay Nitin Paranjape, S. Swaroop Vedula, Shameema Sikder, Vishal M. Patel, Mohammad Yaqub
960A Hybrid Framework Bridging CNN and ViT based on Theory of Evidence for Diabetic Retinopathy GradingJunlai Qiu, Yunzhu Chen, Hao Zheng, Yawen Huang, Yuexiang Li
1072Controllable Garment Generation with Multi-Modal Diffusion GuidanceSanhita Pathak, Vinay Kaushik, Brejesh Lall
1062Calibration-Aware Prompt Learning for Medical Vision-Language ModelsAbhishek Basu, Fahad Shamshad, Ashshak Sharifdeen, Karthik Nandakumar, Muhammad Haris Khan
218Bridging Visual-Textual Modalities: Weakly Supervised Histopathology SegmentationSicong Gao, Matthew AB Baker, Maurice Pagnucco, Zhiwei Gao, Yang Song
173CellMamba: Adaptive Mamba for Accurate and Efficient Cell DetectionRuochen Liu, Yi.Tian, Jiahao Wang, Hongbin Liu, Xianxu Hou, Jingxin Liu
938Grad-CL: Source Free Domain Adaptation with Gradient Guided Feature DisalignmentRini Smita Thakur, Rajeev Ranjan Dwivedi, Vinod K. Kurmi
313OctreeNCA: Single-Pass 184 MP Segmentation on Consumer HardwareNick Lemke, John Kalkhof, Niklas Babendererde, Anirban Mukhopadhyay
102STAIN: Smooth Tile-Aware Instance Normalisation for Virtual StainingDavid Armstrong, Iain B Styles, Niall McLaughlin
1095Supervised Segmentation Model for Improved Detection of OSSN using Slit Lamp ImagesKajal Singh, Shagun Bhatt, Ramkailash Gujar, Arnav Bhavsar, Dinesh Singh
486FreqSelect: Frequency-Aware fMRI-to-Image ReconstructionJunliang Ye, Lei Wang, Md Zakir Hossain
1076CLFSeg: A Fuzzy-Logic based Solution for Boundary Clarity and Uncertainty Reduction in Medical Image SegmentationAnshul Kaushal, Kunal Jangid, Vinod K. Kurmi
1013SALT: Parameter-Efficient Fine-Tuning via Singular Value Adaptation with Low-Rank TransformationAbdelrahman Elsayed, Sarim Hashmi, Mohammed Elseiagy, Hu Wang, Mohammad Yaqub, Ibrahim Almakky
751TPA: Temporal Prompt Alignment for Fetal Congenital Heart Defect ClassificationDarya Taratynova, Alya Almsouti, Beknur Kalmakhanbet, Numan Saeed, Mohammad Yaqub
646Towards Data-Efficient Medical Imaging: A Generative and Semi-Supervised FrameworkMosong Ma, Tania Stathaki, Michalis Lazarou
887QWD-GAN: Quality-aware Wavelet-driven GAN for Unsupervised Medical Microscopy Images DenoisingQijun Yang, Yating Huang, Lintao Xiang, Hujun Yin
1109AKD-BNN: Adaptive Kernel Dynamic Bayesian Neural Networks for Enhanced Medical Image Segmentation with Uncertainty EstimationQianying He, Xuan Liu, Wenjian Liu
528OmniSegNet: Towards Scalable, Efficient & Universal Medical Image SegmentationSoma Dasgupta, Swarnava Dey, Arijit Mukherjee, Arpan Pal
1224RASALoRE: Region Aware Spatial Attention with Location-based Random Embeddings for Weakly Supervised Anomaly Detection in Brain MRI ScansBheeshm Sharma, Karthikeyan Jaganathan, Balamurugan Palaniappan
461FSF3A: Federated Spatial Feature Alignment and Adaptive Aggregation for Heterogeneous Brain Tumor SegmentationPeketi Divya, Krishna Mohan Chalavadi, Sobhan Babu, Sumanth Yenduri
29SPARTAN: Spatiotemporal Pose-Aware Retrieval for Text-guided Autonomous NavigationXiangyu Bai, Sai Anish Sreeramagiri, Sai Siddhartha Vivek Dhir Rangoju, Bishoy Galoaa, Eric C Mortin, Sarah Ostadabbas
1177Binarizing Severely Degraded Ancient Bamboo Slips: Dataset and BaselineChongsheng ZHANG, Wanwan Fu, Qilong Li, SAMRA ZAFAR, Zhanshuo Zhang, Qiyan Li, Gaojuan Fan, Christian Heumann
507Robust and Label-efficient Deep Waste DetectionHassan Abid, Khan Muhammad, Muhammad Haris Khan
1134TRUDI and TITUS: A Multi-Perspective Dataset and A Three-Stage Recognition System for Transportation Unit IdentificationEmre Gülsoylu, André Peter Kelm, Lennart Bengtson, Matthias Hirsch, Christian Wilms, Tim Rolff, Janick Edinger, Simone Frintrop
502DefectGPT: Towards Multi-Class Defect Detection with Limited Electrical SamplesZhuoyi Lin, Kaixin Xu, Aye Phyu Phyu Aung, Wen Qiu, Bernice Zee, Jiann Min Chin, Jayavelu Senthilnath
499One target to align them all: LiDAR, RGB and event cameras extrinsic calibration for Autonomous DrivingAndrea Bertogalli, Giacomo Boracchi, Luca Magri
1036Benchmarking Vision Foundation Models for Input Monitoring in Autonomous DrivingMert Keser, Halil Ibrahim Orhan, Niki Amini-Naieni, Gesina Schwalbe, Alois C. Knoll, Matthias Rottmann
478Bézier Curve-Based Stroke Extraction for Handwritten CharactersYuxuan TENG, Takuya Matsuzaki
716Size-aware Contrastive Imitation Learning for Language-conditioned Multi-task Robotic ManipulationJiakai Huang, Weiping Zheng
988Ink Enhancement for Ancient Bamboo Manuscripts Using Iterative Restoration-Degradation Adversarial LearningChongsheng ZHANG, Junchao Ma, Wenhao Zhang, Kamel Aouaidjia, Qilong Li, Gaojuan Fan, Christian Heumann
423JDATT: A Joint Distillation Framework for Atmospheric Turbulence Mitigation and Target DetectionZhiming Liu, Paul Hill, Nantheera Anantrasirichai
59CMAMRNet: A Contextual Mask-Aware Network Enhancing Mural Restoration Through Comprehensive Mask GuidanceYingtie Lei, Fanghai Yi, Yihang Dong, Weihuang Liu, Xiaofeng Zhang, Zimeng Li, Chi-Man Pun, Xuhang Chen
745Mapping like a Skeptic: Probabilistic BEV Projection for Online HD MappingFatih Erdoğan, Merve Rabia Barin, Fatma Guney
131Dual-Stream Attention with Multi-Modal Queries for Object Detection in Transportation ApplicationsNoreen Anwar, Guillaume-Alexandre Bilodeau, Wassim Bouachir
986Visible Structure Retrieval for Lightweight Image-Based RelocalisationFereidoon Zangeneh, Leonard Bruns, Amit Dekel, Alessandro Pieropan, Patric Jensfelt
976Advancing Utility Pole and Sign Detection Through Deep LearningCarl Dickinson, Gaetano Di Caterina
39DocAttentionRect: Attention-Guided Document Image RectificationPooja Kumari, Sukhendu Das
228Dual-Expert Collaborative Network for Fake News Detection with External Knowledge IntegrationWenxin Luo, Zhu Teng, Wei Zhang, Baopeng Zhang
948Tracking Meets Large Multimodal Models for Driving Scenario UnderstandingAyesha Ishaq, Jean Lahoud, Fahad Shahbaz Khan, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer
1127ALFred: An Active Learning Framework for Real-world Semi-supervised Anomaly Detection with Adaptive ThresholdsShanle Yao, Ghazal Alinezhad Noghre, Armin Danesh Pazho, Hamed Tabkhivayghan
405HVLO-YOLO: An Ultra-Lightweight Detection Model for High-voltage Line ObstaclesWeichao Pan, Xu Wang, Chengze Lv, Zicheng Lin, Gongrui Wang, Xuening Zhang, Yi Sun, Xingbo Liu
736EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World ModelsYue Hu, Siyuan Huang, Yue Liao, Shengcong Chen, Pengfei Zhou, Liliang Chen, Guanghui Ren, Maoqing Yao
Location: Cutlers' Hall
Oral Session 4 - Medical and Biological Image Analysis
15:45 - 16:45
Chair: To be announced 15:45 902
ITC-RWKV: Interactive Tissue–Cell Modeling with Recurrent Key-Value Aggregation for Histopathological Subtyping
Yating Huang, Qijun Yang, Lintao Xiang, Hujun Yin
16:00 168
PSScreen: Partially Supervised Multiple Retinal Disease Screening
Boyi Zheng, Qing Liu
16:15 989
MedOpenSeg: Open-World Medical Segmentation with Memory-Augmented Transformers
Luisa Vargas, Eleonora Poeta, Tania Cerquitelli, Elena Baralis, Maria A Zuluaga
16:30 1199
AULUNet: An Adaptive Ultra-Lightweight U-Net Framework for Efficient Skin Lesion Segmentation in Resource-Constrained Environments
Md Maklachur Rahman, Soon Ki Jung, Tracy Hammond
Location: Main Hall, Cutlers' Hall
Oral Session 5 - Real World Applications and Systems
17:00 - 18:00
Chair: To be announced 17:00 698
SAMWave: Adapting Segment Anything Model to difficult tasks
Saurabh Yadav, Avi Gupta, Koteswar Rao Jerripothula
17:15 1135
The Trauma THOMPSON Dataset for Real-World Emergency AI
Yupeng Zhuo, Eddie Zhang, Xiangchen Yu, Aditya Pachpande, Andrew Wallace Kirkpatrick, Kyle Couperus, Jessica Mckee, Juan Wachs
17:30 1058
Atomizer: Generalizing to unseen modalities by breaking images down to a set of scalars
Hugo Riffaud de Turckheim, Diego Marcos, Roberto Interdonato, Sylvain Lobry
17:45 596
TopoMortar: A Dataset to Evaluate Topology Accuracy in Image Segmentation
Juan Miguel Valverde, Motoya Koga, Nijihiko Otsuka, Anders Dahl
Location: Main Hall, Cutlers' Hall