29.September MiCo room Amber 1, Milano, Italy

AIM 2024

Advances in Image Manipulation workshop

in conjunction with ECCV 2024

Sponsors (TBU)






Call for papers

Image manipulation is a key computer vision tasks, aiming at the restoration of degraded image content, the filling in of missing information, or the needed transformation and/or manipulation to achieve a desired target (with respect to perceptual quality, contents, or performance of apps working on such images). Recent years have witnessed an increased interest from the vision and graphics communities in these fundamental topics of research. Not only has there been a constantly growing flow of related papers, but also substantial progress has been achieved.

Each step forward eases the use of images by people or computers for the fulfillment of further tasks, as image manipulation serves as an important frontend. Not surprisingly then, there is an ever growing range of applications in fields such as surveillance, the automotive industry, electronics, remote sensing, or medical image analysis etc. The emergence and ubiquitous use of mobile and wearable devices offer another fertile ground for additional applications and faster methods.

This workshop aims to provide an overview of the new trends and advances in those areas. Moreover, it will offer an opportunity for academic and industrial attendees to interact and explore collaborations.

This workshop builds upon the success of Advances in Image Manipulation (AIM) workshop at ECCV 2022, ICCV 2021, ECCV 2020,ICCV 2019, Mobile AI (MAI) workshop at CVPR 2023, CVPR 2023 , CVPR 2022 , CVPR 2021 , Perceptual Image Restoration and Manipulation (PIRM) workshop at ECCV 2018 , Graphics, Vision, Graphics and AI for Streaming (AIS) workshop at CVPR 2024, Perceptual Image Restoration and Manipulation (PIRM) workshop at ECCV 2018 , the workshop and Challenge on Learned Image Compression (CLIC) editions at DCC 2024,CVPR 2018-2022, and the New Trends in Image Restoration and Enhancement (NTIRE) editions at CVPR 2017-2024 and at ACCV 2016. Moreover, it relies on the people associated with the PIRM, CLIC, MAI, AIM, AIS and NTIRE events such as organizers, PC members, distinguished speakers, authors of published papers, challenge participants and winning teams.

Papers addressing topics related to image/video manipulation, restoration and enhancement are invited. The topics include, but are not limited to:

  • Image-to-image translation
  • Video-to-video translation
  • Image/video manipulation
  • Perceptual manipulation
  • Image/video generation and hallucination
  • Image/video quality assessment
  • Image/video semantic segmentation
  • Perceptual enhancement
  • Multimodal translation
  • Depth estimation
  • Saliency and gaze estimation
  • Image/video inpainting
  • Image/video deblurring
  • Image/video denoising
  • Image/video upsampling and super-resolution
  • Image/video filtering
  • Image/video de-hazing, de-raining, de-snowing, etc.
  • Demosaicing
  • Image/video compression
  • Removal of artifacts, shadows, glare and reflections, etc.
  • Image/video enhancement: brightening, color adjustment, sharpening, etc.
  • Style transfer
  • Hyperspectral imaging
  • Underwater imaging
  • Aerial and satellite imaging
  • Methods robust to changing weather conditions / adverse outdoor conditions
  • Image/video manipulation on mobile devices
  • Image/video restoration and enhancement on mobile devices
  • Studies and applications of the above.

AIM 2024 challenges

One needs to check the corresponding Codalab competition(s) in order to learn more about and to register to access the data and participate in the challenge(s) of interest.

Important dates



Challenges Event Date (always 23:59 CET)
Site online May 1, 2024
Release of train data and validation data May 10, 2024
Validation server online May 15, 2024
Final test data release, validation server closed July 24, 2024 (EXTENDED)
Test phase submission deadline July 29, 2024
Fact sheets, code/executable submission deadline July 29, 2024
Preliminary test results release to the participants July 31, 2024
Paper submission deadline for entries from the challenges August 18, 2024(EXTENDED)
Workshop Event Date (always 23:59 CET)
Paper submission deadline July 24, 2024(EXTENDED)
Paper decision notification August 14, 2024
Paper submission deadline (only for methods from AIM 2024 challenges and papers reviewed elsewhere!) August 18, 2024(EXTENDED)
Late & challenge paper decision notification August 21, 2024
Camera ready deadline August 29, 2024 23:59 PDT(EXTENDED)
Workshop day September 29, 2024

Submit



Instructions and Policies
Format and paper length

A paper submission has to be in English, in pdf format, and at most 14 pages (excluding references) in single-column, ECCV style. The paper format must follow the same guidelines as for all ECCV 2024 submissions.
AIM 2024 and ECCV 2024 author guidelines

Double-blind review policy

The review process is double blind. Authors do not know the names of the chair/reviewers of their papers. Reviewers do not know the names of the authors.

Dual submission policy

Dual submission is not allowed. If a paper is submitted also to ECCV and accepted, the paper cannot be published both at the ECCV and the workshop.

Submission site

https://cmt3.research.microsoft.com/AIMWC2024/

Proceedings

Accepted and presented papers will be published after the conference in ECCV Workshops proceedings together with the ECCV2024 main conference papers.

Author Kit

The author kit provides a LaTeX2e template for paper submissions.
Please refer to https://eccv.ecva.net/Conferences/2024/SubmissionPolicies for detailed formatting instructions.

People



Organizers (TBU)

  • Radu Timofte, University of Wurzburg,
  • Andrey Ignatov, AI Benchmark and ETH Zurich,
  • Marcos V. Conde, University of Wurzburg,
  • Dmitriy Vatolin, Moscow State University,
  • Eduardo Pérez-Pellitero, Noah's Ark Lab London,


PC Members (TBU)

  • Mahmoud Afifi, Google
  • Codruta Ancuti, UPT
  • Boaz Arad, Ben-Gurion University of the Negev
  • Siavash Arjomand Bigdeli, DTU
  • Michael S. Brown, York University
  • Christophe De Vleeschouwer, Université Catholique de Louvain
  • Jianrui Cai, The Hong Kong Polytechnic University
  • Chia-Ming Cheng, MediaTek
  • Cheng-Ming Chiang, MediaTek
  • Sunghyun Cho, Samsung
  • Marcos V. Conde, University of Wurzburg
  • Chao Dong, SIAT
  • Weisheng Dong, Xidian University
  • Touradj Ebrahimi, EPFL
  • Paolo Favaro, University of Bern
  • Graham Finlayson, University of East Anglia
  • Corneliu Florea, University Politechnica of Bucharest
  • Peter Gehler, Zalando / Amazon
  • Bastian Goldluecke, University of Konstanz
  • Shuhang Gu, University of Electronic Science and Technology of China
  • Christine Guillemot, INRIA
  • Felix Heide, Princeton University & Algolux
  • Chiu Man Ho, OPPO,
  • Hiroto Honda, Mobility Technologies Co Ltd.
  • Andrey Ignatov, ETH Zurich
  • Eddy Ilg, Saarland University
  • Aggelos Katsaggelos, Northwestern University
  • Jan Kautz, NVIDIA
  • Furkan Kınlı, Özyeğin University
  • Christian Ledig, University of Bamberg
  • Seungyong Lee, POSTECH
  • Kyoung Mu Lee, Seoul National University
  • Juncheng Li, The Chinese University of Hong Kong
  • Yawei Li, ETH Zurich
  • Stephen Lin, Microsoft Research
  • Guo Lu, Beijing Institute of Technology
  • Kede Ma, City University of Hong Kong
  • Vasile Manta, Technical University of Iasi
  • Rafal Mantiuk, University of Cambridge
  • Zibo Meng, OPPO
  • Yusuke Monno, Tokyo Institute of Technology
  • Subrahmanyam Murala, Trinity College Dublin
  • Hajime Nagahara, Osaka University
  • Vinay P. Namboodiri, University of Bath/li>
  • Michael Niemeyer, Google
  • Sylvain Paris, Adobe Research
  • Federico Perazzi, Bending Spoons
  • Fatih Porikli, Qualcomm CR&D
  • Rakesh Ranjan, Meta
  • Antonio Robles-Kelly, Deakin University
  • Aline Roumy, INRIA
  • Christopher Schroers, Disney Research | Studios
  • Nicu Sebe, University of Trento
  • Eli Shechtman, Creative Intelligence Lab at Adobe Research
  • Gregory Slabaugh, Queen Mary University of London
  • Sabine Süsstrunk, EPFL
  • Yu-Wing Tai, Kuaishou Technology & HKUST
  • Robby T. Tan, Yale-NUS College
  • Masayuki Tanaka, Tokyo Institute of Technology
  • Hao Tang, ETH Zurich & CMU
  • Jean-Philippe Tarel, G. Eiffel University
  • Qi Tian, Huawei Cloud & AI
  • Radu Timofte, University of Wurzburg
  • George Toderici, Google
  • Luc Van Gool, ETH Zurich & KU Leuven
  • Longguang Wang, National University of Defense Technology
  • Yingqian Wang, National University of Defense Technology
  • Zhou Wang, University of Waterloo
  • Gordon Wetzstein, Stanford University
  • Ming-Hsuan Yang, University of California at Merced & Google
  • Ren Yang, Microsoft
  • Wenjun Zeng, Microsoft Research
  • Kai Zhang, Nanjing University
  • Yulun Zhang, Shanghai Jiao Tong University
  • Jun-Yan Zhu, Carnegie Mellon University
  • Wangmeng Zuo, Harbin Institute of Technology

Invited Talks



Yawei Li

ETH Zurich

Title: On the Compression and Design of Foundation Models

Abstract: In recent years, foundation models have significantly sparked innovation in the fields of vision and language. However, from a practical application perspective, two major challenges emerge for these models including data scarcity and model complexity. Typically, foundation models are trained with vast amounts of data sourced from the Internet, which may not be readily available for specialized applications like robotics and biomedical fields. Moreover, the rapid increase in model size leads to increased computational costs and demands on computing devices. In this presentation, I will discuss how data simulation can address the issue of data scarcity for biosignals. For instance, our data simulation pipeline is physically informed and tailored to synthesize raw frequency ultrasound signals, paving the way for developing foundation models for this specific type of signal. Additionally, I will present a novel quantization method aimed at compressing large language models (LLMs). This mixed-precision quantization approach determines the optimal bit-width and quantizers for the weights of LLMs and minimizes quantization error by focusing more on salient weights.

Bio: Dr. Yawei Li is a Lecturer at ETH Zurich. His research lies at the intersection between computer vision, machine learning, and artificial intelligence algorithms. He earned his Ph.D. from the Computer Vision Laboratory at ETH Zurich, with a dissertation focused on the optimization and acceleration of efficient deep neural networks in computer vision. Dr. Li's research encompasses the design of efficient AI neural networks, algorithms, hardware, and systems, with applications in vision problems, biomedical signal processing, and language models. He has proposed deep neural network compression methods, such as pruning, quantization, low-rank decomposition, neural network architecture search methods, graph neural network optimization methods, and novel attention mechanisms for Transformer networks. Dr. Li's research has been published in top-tier computer vision conferences and journals, including CVPR, ICCV, ECCV, and T-PAMI.


All the accepted AIM workshop papers have poster presentation or oral presentation.
All the accepted AIM workshop papers are published under the book title "European Conference on Computer Vision Workshops (ECCVW)" by

Springer




papers (pdf, suppl. mat) available at https://eccv2024.ecva.net/


AIM 2024 papers with oral presentation:

Paper#W26_ 81 [00:10 UTC] 02:10PM AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Content ( oral )
Marcos V. Conde (University of Würzburg & Sony PlayStation)*; Zhijun Lei (Meta); Wen Li (Meta); Ioannis Katsavounidis (Meta); Radu Timofte (University of Wurzburg) et al.
Paper#W26_ 79 [00:20 UTC] 02:20PM Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results ( oral )
Marcos V. Conde (University of Würzburg & Sony PlayStation)*; Florin-Alexandru Vasluianu (Computer Vision Lab, University of Wurzburg); Jinhui Xiong (Meta); Wei Ye (Facebook); Rakesh Ranjan (Meta); Radu Timofte (University of Wurzburg) et al.
Paper#W26_ 78 [00:30 UTC] 02:30PM AIM 2024 Challenge on UHD Blind Photo Quality Assessment et al. ( oral )
Vlad Hosu (Sony AI); Marcos V. Conde (University of Würzburg & Sony PlayStation)*; Radu Timofte (University of Wurzburg); Lorenzo Agnolucci (University of Florence); Saman Zadtootaghaj (Sony Interactive Entertainment); Nabajeet Barman (SIE) et al.
Paper#W26_ 62 [00:40 UTC] 02:40PM Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency ( oral )
Wei Sun (Shanghai Jiao Tong Unviersity)*; Weixia Zhang (Shanghai Jiao Tong University); Yuqin Cao (Shanghai Jiao Tong university); linhan cao (shanghai jiaotong university); Jun Jia (Shanghai Jiao Tong University); Zijian Chen (Shanghai Jiao Tong University); Zicheng Zhang (Shanghai Jiaotong university); Xiongkuo Min (Shanghai Jiao Tong University); Guangtao Zhai (Shanghai Jiao Tong University)
Paper#W26_ 57 [00:50 UTC] 02:50PM AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark ( oral )
Michal Nazarczuk (Huawei Noah's Ark Lab); Thomas Tanay (Huawei Noah's Ark Lab); Sibi Catley-Chandar (Huawei Noah's Ark Lab); Richard Shaw (Huawei Noah's Ark Lab); Radu Timofte (University of Wurzburg); Eduardo Pérez-Pellitero (Huawei Noah's Ark Lab)*
Paper#W26_ 56 [00:55 UTC] 02:55PM AIM 2024 Sparse Neural Rendering Challenge: Methods and Results ( oral )
Michal Nazarczuk (Huawei Noah's Ark Lab); Sibi Catley-Chandar (Huawei Noah's Ark Lab); Thomas Tanay (Huawei Noah's Ark Lab); Richard Shaw (Huawei Noah's Ark Lab); Eduardo Pérez-Pellitero (Huawei Noah's Ark Lab)*; Radu Timofte (University of Wurzburg) et al.
Paper#W26_ 72 [01:05 UTC] 03:05PM Advancing Few-Shot Novel View Synthesis with Teacher-Student Guided Scene Geometry Refinement ( oral )
Yan Xing (Hefei University of Technology); Pan Wang (hefei university of technology)*; Yali Guo (hefei university of technology); Yongxin Wu (hefei university of technology); Youcheng Cai (University of Science and Technology of China)
Paper#W26_ 10 [01:15 UTC] 03:15PM Diffusion-based Light Field Synthesis ( oral )
Ruisheng Gao (University of Science and Technology of China); Yutong liu (University of Science and Technology of China ); Zeyu Xiao (University of Science and Technology of China); Zhiwei Xiong (University of Science and Technology of China)*
Paper#W26_ 71 [03:00 UTC] 05:00PM AIM 2024 Challenge on Video Saliency Prediction: Methods and Results ( oral )
Andrey Moskalenko (AIRI)*; Alexey Bryntsev (Moscow State University); Dmitriy S Vatolin (Lomonosov Moscow State University); Radu Timofte (University of Wurzburg) et al.
Paper#W26_ 70 [03:10 UTC] 05:10PM AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results ( oral )
Ivan Molodetskikh (Lomonosov Moscow State University)*; Artem Borisov (Lomonosov Moscow State University); Dmitriy S Vatolin (Lomonosov Moscow State University); Radu Timofte (University of Wurzburg) et al.
Paper#W26_ 65 [03:20 UTC] 05:20PM SR-VQA: Super-Resolution Video Quality Assessment Model ( oral )
Yuqin Cao (Shanghai Jiao Tong university)*; Wei Sun (Shanghai Jiao Tong Unviersity); Weixia Zhang (Shanghai Jiao Tong University); Yinan Sun (Shanghai Jiaotong University); Ziheng Jia (Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University); Yuxin Zhu (Shanghai Jiao Tong University); Xiongkuo Min (Shanghai Jiao Tong University); Guangtao Zhai (Shanghai Jiao Tong University)
Paper#W26_ 74 [03:30 UTC] 05:30PM AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results ( oral )
Maksim Smirnov (Lomonosov Moscow State University)*; Aleksandr Gushchin (Lomonosov Moscow State University); Anastasia Antsiferova (Lomonosov Moscow State University); Dmitriy S Vatolin (Lomonosov Moscow State University); Radu Timofte (University of Wurzburg) et al.
Paper#W26_ 60 [03:40 UTC] 05:40PM Compression-RQ-VQA: Leveraging Rich Quality-aware Features for Compressed Video Quality Assessment ( oral )
Ziheng Jia (Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University)*; Jiaying Qian (Institute of lmage Communication and Network Engineering, Shanghai Jiao Tong University); Wei Sun (Shanghai Jiao Tong Unviersity); Zicheng Zhang (Shanghai Jiaotong university); Yuqin Cao (Shanghai Jiao Tong university); Yinan Sun (Shanghai Jiaotong University); Yuxin Zhu (Shanghai Jiao Tong University); Xiongkuo Min (Shanghai Jiao Tong University); Guangtao Zhai (Shanghai Jiao Tong University)



AIM 2024 papers with poster presentation:
(There are no poster panel IDs -- any poster panel from Amber 1 room or Gold Foyer can be picked and used during the poster session.)


Paper#W26_ 7 [01:30 UTC] 03:30PM Satellite Image Dehazing Via Masked Image Modeling and Jigsaw Transformation (poster # any )
Guisik Kim (Korea Electronics Technology Institute, Korea); Choongsang Cho (Korea Electronics Technology Institute); Junseok Kwon (Chung-Ang Univ., Korea)*
Paper#W26_ 9 [01:30 UTC] 03:30PM UHD-IQA Benchmark Database: Pushing the Boundaries of Blind Photo Quality Assessment (poster # any )
Vlad Hosu (Sony AI)*; Lorenzo Agnolucci (Sony AI); Oliver Wiedemann (University of Konstanz); Daisuke Iso (Sony Research Inc.); Dietmar Saupe (University of Konstanz)
Paper#W26_ 12 [01:30 UTC] 03:30PM Diffusion-Promoted HDR Video Reconstruction (poster # any )
yuanshen guan (University of Science and Technology of China); Ruikang Xu (University of Science and Technology of China); Mingde Yao (The Chinese University of Hong Kong); Ruisheng Gao (University of Science and Technology of China); Lizhi Wang (Beijing Institute of Technology); Zhiwei Xiong (University of Science and Technology of China)*
Paper#W26_ 13 [01:30 UTC] 03:30PM Lightweight Deep Learning Model for Defective Pixel Detection and Recovery from the Image Sensors (poster # any )
Ganzorig Gankhuyag (KETI)*; Byoung-Il Mun (KETI); Changyun Cho (KETI); Jinman Park (KETI); Haengseon Son (Korea Electronics Technology institute); Kyoungwon Min (Korea Electronics Technology Institute)
Paper#W26_ 15 [01:30 UTC] 03:30PM IPAdapter-Instruct: Resolving Ambiguity in Image-based Conditioning using Instruct Prompts (poster # any )
Ciara Rowles (Unity Technologies); Shimon Vainer (Unity); Dante De Nigris (Unity Technologies); Slava Elizarov (Unity Technologies); Konstantin Kutsy (Unity Technologies); Simon Donné (Unity Technologies)*
Paper#W26_ 16 [01:30 UTC] 03:30PM Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models (poster # any )
Jun Xiao (The Hong Kong Polytechnic University)*; Zihang Lyu (The Hong Kong Polytechnic University); Hao Xie (The Hong Kong Polytechnic University); Cong Zhang (The Hong Kong Polytechnic University); Yakun Ju (Nanyang Technological University); Changjian Shui (Vector Institute ); Kin-Man Lam (The Hong Kong Polytechnic University)
Paper#W26_ 17 [01:30 UTC] 03:30PM MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance (poster # any )
Debin Meng (Queen Mary University of London)*; Christos Tzelepis (City, University of London); Ioannis Patras (Queen Mary University of London); Georgios Tzimiropoulos (Queen Mary University of London)
Paper#W26_ 18 [01:30 UTC] 03:30PM RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content (poster # any )
Tianhao peng (University of Bristol)*; Chen Feng (University of Bristol); Duolikun Danier (University of Bristol, University of Edinburgh); Fan Zhang (University of Bristol); Benoit Quentin Arthur Vallade (Amazon); Alex Mackin (Amazon Prime Video); David Bull (University of bristol)
Paper#W26_ 19 [01:30 UTC] 03:30PM Detecting Forged Sentinel-2 Images Through Parallax-Based Cloud Analysis (poster # any )
Matthieu Serfaty (Centre Borelli, ENS Paris-Saclay)*; Tina Nikoukhah (Centre Borelli, ENS Paris-Saclay); Quentin Bammey (École Normale Supérieure Paris-Saclay); Rafael Grompone von Gioi (Centre Borelli, ENS Paris-Saclay); Carlo de Franchis (Kayrros SAS)
Paper#W26_ 20 [01:30 UTC] 03:30PM PRISM: Progressive Restoration for Scene Graph-based Image Manipulation (poster # any )
Pavel Jahoda (Technical University of Munich); Yousef Yeganeh (Technical University of Munich ); Ehsan Adeli (Stanford University); Nassir Navab ("TU Munich, Germany"); Azade Farshad (Technical University of Munich)*
Paper#W26_ 21 [01:30 UTC] 03:30PM DAVIDE: Depth-Aware Video Deblurring (poster # any )
German F. Torres Vanegas (Tampere University)*; Jussi Kalliola (Tampere University); Soumya Tripathy (Tampere University of Technology); Erman Acar (Huawei Technologies Oy (Finland) Co. Ltd); Joni-Kristian Kamarainen (Tampere University)
Paper#W26_ 22 [01:30 UTC] 03:30PM RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verification (poster # any )
Nikolina Kubiak (University of Surrey)*; Elliot Wortman (University of Surrey); Armin Mustafa (University of Surrey); Graeme Phillipson (BBC); Stephen Jolly (BBC); Simon Hadfield (University of Surrey)
Paper#W26_ 23 [01:30 UTC] 03:30PM Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion model (poster # any )
Jonas Brenig (Universität Würzburg)*; Radu Timofte (University of Wurzburg)
Paper#W26_ 27 [01:30 UTC] 03:30PM Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applications (poster # any )
Brayan Monroy (Universidad Industrial de Santander); Kebin A Contreras (Universidad del Cauca); Jorge Bacca (Universidad Industrial de Santander)*
Paper#W26_ 28 [01:30 UTC] 03:30PM QSD: Query-Selection Denoising score for Image Edit-ing in Latent Diffusion Model (poster # any )
jungmin hwang (Student at University of ottawa)*; Changwon Lim (Chung-Ang University); WonSook Lee (University of Ottawa)
Paper#W26_ 29 [01:30 UTC] 03:30PM PDB Unet: A spatio temporal video Fixed Pattern Noise removal network (poster # any )
Arnaud Barral (ENS Paris Saclay)*; Axel Davy (ENS Paris-Saclay); Pablo Arias (Universitat Pompeu Fabra)
Paper#W26_ 30 [01:30 UTC] 03:30PM Reversible and Cascaded Lightweight Colour Constancy: Jointly Addressing Illumination Correction and White Balance (poster # any )
Zihao Guo (Fujitsu Research & Development Center Co., Ltd.)*; Fei Li (Fujitsu Research & Development Center Co., Ltd.); Rujie Liu (Fujitsu Research & Development Center Co., Ltd.); Arisu Endo (Fujitsu Research); Takashi Kikuchi (Fujitsu Research); Shun Takeuchi (Fujitsu Research)
Paper#W26_ 32 [01:30 UTC] 03:30PM Hybrid Spatial-spectral Neural Network for Hyperspectral Image Denoising (poster # any )
Hao Liang (WuHan University)*; Chengjie Ke (WuHan University); Kun Li (Wuhan University)
Paper#W26_ 33 [01:30 UTC] 03:30PM Solving Inverse Problem With Unspecified Forward Operator Using Diffusion Models (poster # any )
Jialing Zhang (Shanghai Jiaotong University)*; Chongxuan Li (Renmin University of China); Dequan Wang (Shanghai Jiao Tong University)
Paper#W26_ 34 [01:30 UTC] 03:30PM A Disentangled Approach to Predict the Aesthetic Outcomes of Breast Cancer Treatment (poster # any )
Helena Montenegro (INESC TEC, Faculty of Engineering of the University of Porto)*; Maria João Cardoso (Champalimaud Foundation, Faculty of Medicine of the University of Lisbon); Jaime S Cardoso (INESC Porto, Universidade do Porto)
Paper#W26_ 35 [01:30 UTC] 03:30PM LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Model (poster # any )
Nasim Jamshidi Avanaki (Independent Researcher)*; Abhijay Ghildyal (Portland State University); Nabajeet Barman (SIE); Saman Zadtootaghaj (Sony Interactive Entertainment)
Paper#W26_ 36 [01:30 UTC] 03:30PM Pushing Joint Image Denoising and Classification to the Edge (poster # any )
Thomas Markhorst (Delft University of Technology)*; Jan C van Gemert (Delft University of Technology); Osman Semih Kayhan (Delft University of Technology)
Paper#W26_ 38 [01:30 UTC] 03:30PM Self-Supervised HDR Imaging from Motion and Exposure Cues (poster # any )
Michal Nazarczuk (Huawei Noah's Ark Lab)*; Sibi Catley-Chandar (Huawei Noah's Ark Lab); Ales Leonardis (University of Birmingham); Eduardo Pérez-Pellitero (Huawei Noah's Ark Lab)
Paper#W26_ 39 [01:30 UTC] 03:30PM Closer to Ground Truth: Realistic Shape and Appearance Labeled Data Generation for Unsupervised Underwater Image Segmentation (poster # any )
Andrei Jelea (NORCE Norwegian Research Centre AS)*; Nabil Belbachir (NORCE Norwegian Research Centre AS); Marius Leordeanu (University "Politehnica" of Bucharest)
Paper#W26_ 40 [01:30 UTC] 03:30PM Edge-aware Consistent Stereo Video Depth Estimation (poster # any )
Elena Kosheleva (K|Lens GmbH); Sunil Jaiswal (K|Lens GmbH)*; Faranak Shamsafar (K|Lens GmbH); Noshaba Cheema (Max-Planck Institute for Informatics & DFKI); Klaus Illgner (K|Lens GmbH ); Philipp Slusallek (German Research Center for Artificial Intelligence (DFKI) & Saarland University)
Paper#W26_ 42 [01:30 UTC] 03:30PM Low-Cost Stereoscopic Optical-Coding Design for Depth Estimation Using End-to-End Optimization (poster # any )
Jhon E Lopez (Universidad Industrial de Santander)*; Edwin M Vargas (Universidad Industrial de Santander); Andrés Jerez (Universidad Industrial de Santander); Henry Arguello (Universidad Industrial Santander)
Paper#W26_ 44 [01:30 UTC] 03:30PM 360U-Former: HDR Illumination Estimation with Panoramic Adapted Vision Transformers (poster # any )
Jack O Hilliard (CVSSP)*; Adrian Hilton (University of Surrey); Jean-Yves Guillemaut (University of Surrey)
Paper#W26_ 55 [01:30 UTC] 03:30PM MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge Distillation (poster # any )
Zewen Chen (School of Artificial Intelligence, University of Chinese Academy of Sciences); Sunhan Xu (Beijing Union University); Yun Zeng (China University of Petroleum); haochen guo (河北大学); Jian Guo (College of Robotics, Beijing Union University); Shuai Liu (Beijing Union University); Juan Wang (Institute of Automation, Chinese Academy of Sciences); Bing Li (National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences)*; Weiming Hu (Institute of Automation,Chinese Academy of Sciences); dehua Liu (重庆传音科技有限公司); hesong Li (传音控股有限公司)
Paper#W26_ 59 [01:30 UTC] 03:30PM Unsupervised Anomaly Segmentation at High Resolution with Patch-Divide-and-Conquer and Self-Ensembling (poster # any )
Hendrik Meininger (Julius-Maximilians-Universität Würzburg)*; Radu Timofte (University of Wurzburg)
Paper#W26_ 61 [01:30 UTC] 03:30PM Learning from Strong to Weak - An Enhanced Quality Comparison Network via Efficient Transfer Learning (poster # any )
yunchen zhang (ZTE)*; Xu Xiangkai (ZTE Corporation); Hong Gao (ZTE Corporation); Ji Shi (ZTE corp); Yiming Bao (Shanghai Jiao Tong University); Xiugang Dong (ZTE Corporation ); Xiangsheng Zhou (ZTE Corporation ); Yaofeng Tu (ZTE Corporation)
Paper#W26_ 64 [01:30 UTC] 03:30PM AVSal: Enhancing Video Saliency Prediction through Audio-Visual Fusion and Temporal Aggregation (poster # any )
Yuxin Zhu (Shanghai Jiao Tong University)*; Yinan Sun (Shanghai Jiaotong University); Huiyu Duan (Shanghai Jiao Tong University); Yuqin Cao (Shanghai Jiao Tong university); Ziheng Jia (Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University); Qiang Hu (Shanghai Jiao Tong University); Xiongkuo Min (Shanghai Jiao Tong University); Guangtao Zhai (Shanghai Jiao Tong University)
Paper#W26_ 76 [01:30 UTC] 03:30PM TASOD: A Data Collection for Tiny and Small Object Detection (poster # any )
Lars Fichtel (Technical University of Applied Sciences Würzburg-Schweinfurt)*; Dominik Erbacher (University of applied sciences würzburg-schweinfurt); Dennis Grünwald (Technical University of Applied Sciences Würzburg-Schweinfurt); Leon Heller (Technical University of Applied Sciences Würzburg-Schweinfurt); Christian Bachmeir (Hochschule Würzburg-Schweinfurt); Radu Timofte (University of Wurzburg)
Paper#W26_ 77 [01:30 UTC] 03:30PM Effective Prior Regularized Sparse Learning (poster # any )
Junting Li (The Hong Kong Polytechnic University); Yanghong Zhou (The Hong Kong Polytechnic University); Jintu Fan (The Hong Kong Polytechnic University); Dahua Shou (The Hong Kong Polytechnic University); Sa Xu (Lunaler Healthy Technology Co., Ltd.); P. Y. Mok (The Hong Kong Polytechnic University)*