ICCV - arXivDaily 期刊&会议

2508.11616 2025-08-18 cs.CV cs.AI cs.CL cs.LG

Controlling Multimodal LLMs via Reward-guided Decoding

Oscar Mañas, Pierluca D'Oro, Koustuv Sinha, Adriana Romero-Soriano, Michal Drozdzal, Aishwarya Agrawal

机构 * Mila - Quebec AI Institute（魁北克AI研究院）； Université de Montréal（蒙特利尔大学）； McGill University（麦吉尔大学）； Meta FAIR ； Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）

Comments Published at ICCV 2025

2508.11502 2025-08-18 cs.CV

AIM: Amending Inherent Interpretability via Self-Supervised Masking

Eyad Alshami, Shashank Agnihotri, Bernt Schiele, Margret Keuper

机构 * Max-Planck-Institute for Informatics（马克斯·普朗克研究所（信息学））； RTG Neuroexplicit Models of Language, Vision, and Action（神经显性语言、视觉和行动模型研究组）； Data and Web Science Group（数据与网络科学小组）； University of Mannheim（曼海姆大学）

Comments Accepted at International Conference on Computer Vision (ICCV) 2025

2508.11446 2025-08-18 cs.CV cs.AI

Inside Knowledge: Graph-based Path Generation with Explainable Data Augmentation and Curriculum Learning for Visual Indoor Navigation

Daniel Airinei, Elena Burceanu, Marius Leordeanu

机构 * National University of Science and Technology POLITEHNICA Bucharest（波兰堡国立科学与技术大学）； Bitdefender（Bitdefender公司）

Comments Accepted at the International Conference on Computer Vision Workshops 2025

2508.11265 2025-08-18 cs.CV

Domain-aware Category-level Geometry Learning Segmentation for 3D Point Clouds

Pei He, Lingling Li, Licheng Jiao, Ronghua Shang, Fang Liu, Shuang Wang, Xu Liu, Wenping Ma

机构 * Xidian University（西电大学）

Comments to be published in International Conference on Computer Vision, ICCV 2025

2508.11185 2025-08-18 cs.CV cs.LG

CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector

Abhinav Kumar, Yuliang Guo, Zhihao Zhang, Xinyu Huang, Liu Ren, Xiaoming Liu

机构 * Michigan State University（密歇根州立大学）； Bosch Research North America（博世北美研究部）； Bosch Center for AI（博世人工智能中心）

Comments ICCV 2025

2508.11074 2025-08-18 cs.SD cs.AI cs.CV eess.AS

LD-LAudio-V1: Video-to-Long-Form-Audio Generation Extension with Dual Lightweight Adapters

Haomin Zhang, Kristin Qi, Shuxin Yang, Zihao Chen, Chaofan Ding, Xinhan Di

机构 * Giant Network, China（中国巨网）； Computer Science, University of Massachusetts Boston（马萨诸塞大学波士顿分校计算机科学系）

Comments Gen4AVC@ICCV: 1st Workshop on Generative AI for Audio-Visual Content Creation

2508.11049 2025-08-18 cs.RO cs.CV

GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning

Kelin Yu, Sheng Zhang, Harshit Soora, Furong Huang, Heng Huang, Pratap Tokekar, Ruohan Gao

机构 * University of Maryland, College Park（马里兰大学 College Park分校）

Comments Published at ICCV 2025

2508.09824 2025-08-18 cs.CV

Reverse Convolution and Its Applications to Image Restoration

Xuhong Huang, Shiqi Liu, Kai Zhang, Ying Tai, Jian Yang, Hui Zeng, Lei Zhang

机构 * Nanjing University（南京大学）； The Hong Kong Polytechnic University（香港理工大学）； OPPO Research Institute（OPPO研究院）

Comments ICCV 2025; https://github.com/cszn/ConverseNet

2508.09597 2025-08-18 cs.CV

SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing

Heyi Sun, Cong Wang, Tian-Xing Xu, Jingwei Huang, Di Kang, Chunchao Guo, Song-Hai Zhang

机构 * Tsinghua University（清华大学）； Tencent Hunyuan project page（腾讯混元项目）

Comments Accepted by ICCV 2025. Project page: https://heyy-sun.github.io/SVG-Head/