Schedule Mon Tue Wed Thu

BMVC conference papers, supplementary material and video presentations can be found at: BMVC Papers

BMVC workshop papers can be found at: BMVC Workshop Papers

Keynote - Margarita Chli
09:00 - 10:00
09:00 - 10:00 Title: Vision-based robotic perception: are we there yet?

Abstract: As vision plays a key role in how we interpret a situation, developing vision-based perception for robots promises to be a big step towards robotic navigation and intelligence, with a tremendous impact on automating robot navigation. This talk will discuss our recent progress in this area at the Vision for Robotics Lab of the University of Cyprus and ETH Zurich (http://www.v4rl.com), and some of the biggest challenges we are faced with.

Location: M1
Poster Sessions
10:00 - 11:45 / 14:00 - 15:45
10:00 - 11:45
Papers Presented
15 Sequential Amodal Segmentation via Cumulative Occlusion Learning Jiayang Ao, Qiuhong Ke, Krista A. Ehinger
18 MeTTA: Single-View to 3D Textured Mesh Reconstruction with Test-Time Adaptation Kim Yu-Ji, Hyunwoo Ha, Kim Youwang, Jaeheung Surh, Hyowon Ha, Tae-Hyun Oh
19 Few-shot Multispectral Segmentation with Representations Generated by Reinforcement Learning Dilith Jayakody, Thanuja Ambegoda
22 HDRSplat: Gaussian Splatting for High Dynmaic Range 3D Scene Reconstruction from Raw Images Shreyas Singh, Aryan Garg, Kaushik Mitra
25 AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation Damian Sójka, Bartłomiej Twardowski, Tomasz Trzcinski, Sebastian Cygert
26 Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN Jiawei Yao, Tong Wu, Xiaofeng Zhang
33 Self-Supervised Real-World Denoising by Jointly Learning Visible and Invisible Noise Shaoyu Wang, Changze Zhou, Bolin Song, Yiyang Wang
41 Local Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolution Minghong Duan, Linhao Qu, Shaolei Liu, Manning Wang
43 Learning to Segment Publicly Accessible Green Spaces with Visual and Semantic Data Jian Gao, Niall McLaughlin, Joanna Sara Valson, Neil Anderson, Ruth Hunter
54 InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning Babak Ehteshami Bejnordi, Gaurav Kumar, Amelie Royer, Christos Louizos, Tijmen Blankevoort, Mohsen Ghafoorian
64 Multi-Modal Information Bottleneck Attribution with Cross-Attention Guidance Danilo Mandic, Emmanuelle Bourigault, Pauline Bourigault
66 Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Models Eman Ali, Muhammad Haris Khan
85 Textual Attention RPN for Open-Vocabulary Object Detection Tae-Min Choi, Inug Yoon, Jong-Hwan Kim, Juyoun Park
101 Interactive Image Segmentation with Temporal Information Augmented Qiaoqiao Wei, Hui Zhang, Jun-Hai Yong
142 Recovering Global Data Distribution Locally in Federated Learning Ziyu Yao
150 AISE: Adaptive Input Sampling for Explanation of Black-box Models Evgeny Tsykunov, Wonju Lee, Minje Park
152 Retinex-Inspired Cooperative Game Through Multi-Level Feature Fusion for Robust, Universal Image Restoration Rongxin Cui, Ruiqi Mao
164 Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds Yuyang Zhao, Na Zhao, Gim Hee Lee
165 Learning Object Placement via Convolution Scoring Attention Yibin Wang, Yuchao Feng, Jianwei Zheng
168 Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation Xiaoyue Mi, Fan Tang, Yepeng Weng, Danding Wang, Juan Cao, Sheng Tang, Peng Li, Yang Liu
203 S³-Match: Common-View Aligned Image Matching via Self-Supervised Keypoint Selection Shizhen Li, Jingcheng Liu, Jianwu Fang, DeZheng Gao, Jianru Xue
207 Feature Splatting for Better Novel View Synthesis with Low Overlap Tomas Berriel Martins, Javier Civera
210 BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimation Kieran Ryan Saunders, Luis J Manso, George Vogiatzis
215 AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains Krzysztof Lis, Matthias Rottmann, Annika Mütze, Sina Honari, Pascal Fua, Mathieu Salzmann
217 GeoFormer: A Multi-Polygon Segmentation Transformer Maxim Khomiakov, Michael Riis Andersen, Jes Frellsen
223 AUPIMO: Redefining Anomaly Localization Benchmarks with High Speed and Low Tolerance João P. C. Bertoldo, Dick Ameln, Ashwin Vaidya, Samet Akcay
227 Cost-Sensitive Learning for Long-Tail Temporal Action Segmentation Zhanzhong Pang, Fadime Sener, Shrinivas Ramasubramanian, Angela Yao
240 SAM Helps SSL: Mask-guided Attention Bias for Self-supervised Learning Kensuke Taguchi, Takehiko Kawai, Wataru Imaeda, Hironobu Fujiyoshi
249 Transferable Learned Image Compression-Resistant Adversarial Perturbations Yang Sui, Zhuohang Li, Ding Ding, Xiang Pan, Xiaozhong Xu, Shan Liu, Zhenzhong Chen
250 Deep Unfolding Network with Spatial-spectral Perception Enhanced for Pan-sharpening Mengjiao Zhao, Mengting Ma, Xiangdong Li, Ao Gao, Siyang Song, Wei Zhang
256 IncreLM: Incremental 3D Line Mapping Xulong Bai, Hainan Cui, Shuhan Shen
262 Toward Highly Efficient Semantic-Guided Machine Vision for Low-Light Object Detection Xin Feng, Junxian Zeng, Siping Wang, Zhenwei He
267 Depth-Guided Privacy-Preserving Visual Localization Using 3D Sphere Clouds Heejoon Moon, Jongwoo Lee, Jeonggon Kim, Je Hyeong Hong
290 Are Sparse Neural Networks Better Hard Sample Learners? Qiao Xiao, Boqian Wu, Lu Yin, Christopher Neil Gadzinski, Tianjin Huang, Mykola Pechenizkiy, Decebal Constantin Mocanu
295 MxT: Mamba x Transformer for Image Inpainting Shuang Chen, Amir Atapour-Abarghouei, Haozheng Zhang, Hubert P. H. Shum
297 Generalizing Teacher Networks for Effective Knowledge Distillation Across Student Architectures Kuluhan Binici, Weiming Wu, Tulika Mitra
12 CLIP Adaptation by Intra-Modal Overlap Reduction Alexey Kravets, Vinay P. Namboodiri
77 PT43D: A Probabilistic Transformer for Generating 3D Shapes from Single Highly-Ambiguous RGB Images Yiheng Xiong, Angela Dai
304 Interpretable Representation Learning from Videos using Nonlinear Priors Marian Longa, Joao F. Henriques
557 Hybrid-CSR: Coupling Explicit and Implicit Reconstruction of Cortical Surface shanlin sun, Tung Le, Pooya Khosravi, Chenyu You, Kun Han, Haoyu Ma, Deying Kong, Xiangyi Yan, Xiaohui Xie
763 Horospherical Learning with Smart Prototypes Paul Berg, Björn Michele, Minh Tan Pham, Laetitia Chapel, Nicolas Courty
Location: Hall 2
14:00 - 15:45
Papers Presented
37 DRAFT: Direct Radiance Fields Editing with Composable Operations Zhihan Cai, Kailu Wu, Dapeng Cao, Feng Chen, Kaisheng Ma
39 HFGS: 4D Gaussian Splatting with Emphasis on Spatial and Temporal High-Frequency Components for Endoscopic Scene Reconstruction Haoyu Zhao, Xingyue Zhao, Lingting Zhu, Weixi Zheng, Yongchao Xu
45 D³Nav: Data-Driven Driving Agents for Autonomous Vehicles in Unstructured Traffic Aditya Nalgunda Ganesh, Gowri Srinivasa
46 FFR-UNet: Feature Filter-Refinement UNet for Medical Image Segmentation Weixin Xu
60 Advancing Medical Image Segmentation: Morphology-Driven Learning with Diffusion Transformer Sungmin Kang, Jaeha Song, Jihie Kim
100 Painterly Image Harmonization via Bi-Transformation with Dynamic Kernels Zhangliang Sun, Hui Zhang
166 Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection Yunsong Wang, Na Zhao, Gim Hee Lee
183 Hierarchical Prompt Learning for Scene Graph Generation XuHan Zhu, Yifei Xing, Ruiping Wang, Yaowei Wang, Xiangyuan Lan
185 Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion Zeyu Zhang, Yiran Wang, Biao Wu, Shuo Chen, Zhiyuan Zhang, SHIYA HUANG, Wenbo Zhang, Meng Fang, Ling Chen, Yang Zhao
199 A Revisit to the Decoder for Camouflaged Object Detection Seung Woo Ko, Joopyo Hong, Suyoung Kim, Seungjai Bang, Sungzoon Cho, Nojun Kwak, Hyung-Sin Kim, Joonseok Lee
263 Improving Object Detection via Local-global Image-translation Danai Triantafyllidou, Sarah Parisot, Ales Leonardis, Steven McDonagh
319 Annotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation Qing En, Yuhong Guo
342 Unsupervised Domain Adaptation for Tubular Structure Segmentation Across Different Anatomical Sources Yuxiang An, Dongnan Liu, Weidong Cai
365 Cascade Masked Generative Distillation for Dense Prediction Tasks Xie Yu, Wentao Zhang
392 Label Smoothing++: Enhanced Label Regularization for Training Neural Networks Sachin Chhabra, Hemanth Venkateswara, Baoxin Li
401 Decoupling Forgery Semantics for Generalizable Deepfake Detection Wei Ye, Xinan He, Feng Ding
417 Kernel Representation for Dynamic Networks Yichen Zhou, Teck Khim Ng/td>
424 RETRO: Reusing teacher projection head for efficient embedding distillation on Lightweight Models via Self-supervised Learning Khanh-Binh Nguyen, Chae Jung Park
472 SAM-EG: Segment Anything Model with Egde Guidance framework for efficient Polyp Segmentation Quoc-Huy Trinh, Hai-Dang Nguyen, Nguyen Ngoc Bao Tram, Debesh Jha, Ulas Bagci, Minh-Triet Tran
480 Disparity Estimation Using a Quad-pixel Sensor Zhuofeng Wu, Doehyung Lee, Zihua Liu, Kazunori Yoshizaki, Yusuke Monno, Masatoshi Okutomi
500 Future Does Matter: Boosting 3D Object Detection with Temporal Motion Estimation in Point Cloud Sequences Rui Yu, Runkai Zhao, Cong Nie, Heng Wang, HuaiCheng Yan, Meng Wang
533 TraIL-Det: Transformation-Invariant Local Feature Networks for 3D LiDAR Object Detection with Unsupervised Pre-Training Li Li, Tanqiu Qiao, Hubert P. H. Shum, Toby P. Breckon
601 Training-Free Zero-Shot Semantic Segmentation with LLM Refinement Yuantian Huang, Satoshi Iizuka, Kazuhiro Fukui
622 The Attempt on Combining Three Talents by KD with Enhanced Boundary in Co-salient Object Detection Ziyi Cao, Shengye Yan, Wei Zheng
630 CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement Yijie Li, Hewei Wang, Aggelos Katsaggelos
637 3D Point Cloud Network Pruning: When Some Weights Do not Matter Amrijit Biswas, Md. Ismail Hossain, M M Lutfe Elahi, Ali Cheraghian, Fuad Rahman, Nabeel Mohammed, Shafin Rahman
642 Revitalizing Legacy Video Content: Deinterlacing with Bidirectional Information Propagation Zhaowei Gao, Mingyang Song, Christopher Schroers, Yang Zhang
648 3D Blur Kernel on Gaussian Splatting Yongchao Lin, Xiangdong Su, Yuhan Yang
667 ICAF-4: An Integrated Framework of Category-level Articulated Object Perception and Manipulation for Embodied Intelligence WenBo Xu, Li Zhang, Qiankun Li, Qi Wu, Lin Yuanbo Wu, Liu Liu
685 Boundary Contrastive Learning for Label-Efficient Medical Image Segmentation Satoshi Kamiya, Kota Yamashita, Kazuhiro Hotta
697 Inverse Rendering of Outdoor Scenes with under Time-variant Illumination Xiaoxue Chen, Hao Zhao, Guyue Zhou, Ya-Qin Zhang
737 Pseudo Labelling for Enhanced Masked Auto Encoders Srinivasa Rao Nandam, Sara Atito, Zhenhua Feng, Josef Kittler, Muhammad Awais
762 Open-World Semi-Supervised Learning under Compound Distribution Shifts Shijia Xu, Lin Zhao, Jialiang Tang, Guangyu Li, Chen Gong
797 Calibration of 2D LiDAR sensors using cylindrical target Tamás Tófalvi, Bandó Kovács, Levente Hajder
854 CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection Yu-Hsuan Hsieh, Shang-Hong Lai
895 Self-Evolving Depth-Supervised 3D Gaussian Splatting from Rendered Stereo Pairs Sadra Safadoust, Fabio Tosi, Fatma Guney, Matteo Poggi
897 topK dice loss for medical image segmentation Seyed mohsen hosseini
53 NCA-Morph: Medical Image Registration with Neural Cellular Automata Amin Ranem, John Kalkhof, Anirban Mukhopadhyay
528 SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries Sebastian Janampa, Marios Pattichis
663 Unsupervised Point Cloud Registration with Self-Distillation Christian Löwens, Thorben Funke, André Wagner, Alexandru Paul Condurache
729 Reconstructing Spheres by Fitting Planes Erol Ozgur, Mohammad Alkhatib, Youcef Mezouar, Adrien Bartoli
779 Outlier detection by ensembling uncertainty with negative objectness Anja Delić, Matej Grcic, Siniša Šegvić
Location: Hall 2
Oral Session 1 - Explainability in Vision
11:45 - 13:00
Chair: Paul Henderson 11:45 12
CLIP Adaptation by Intra-Modal Overlap Reduction
Alexey Kravets, Vinay P. Namboodiri
12:00 77
PT43D: A Probabilistic Transformer for Generating 3D Shapes from Single Highly-Ambiguous RGB Images
Yiheng Xiong, Angela Dai
12:15 304
Interpretable Representation Learning from Videos using Nonlinear Priors
Marian Longa, Joao F. Henriques
12:30 227
Cost-Sensitive Learning for Long-Tail Temporal Action Segmentation
Zhanzhong Pang, Fadime Sener, Shrinivas Ramasubramanian, Angela Yao
12:45 763
Horospherical Learning with Smart Prototypes
Paul Berg, Björn Michele, Minh Tan Pham, Laetitia Chapel, Nicolas Courty
Location: M1
Oral Session 2 - Cyberphysical Vision
15:45 - 17:00
Chair: Nicolas Pugeault 15:45 53
NCA-Morph: Medical Image Registration with Neural Cellular Automata
Amin Ranem, John Kalkhof, Anirban Mukhopadhyay
16:00 528
SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries
Sebastian Janampa, Marios Pattichis
16:15 663
Unsupervised Point Cloud Registration with Self-Distillation
Christian Löwens, Thorben Funke, André Wagner, Alexandru Paul Condurache
16:30 729
Reconstructing Spheres by Fitting Planes
Erol Ozgur, Mohammad Alkhatib, Youcef Mezouar, Adrien Bartoli
16:45 779
Outlier detection by ensembling uncertainty with negative objectness
Anja Delić, Matej Grcic, Siniša Šegvić
Location: M1

sponsors-logos