We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot class-agnostic segmentation models. Contrasted to prior 3D scene segmentation approaches that rely on video object tracking or contrastive learning methods, Gaga utilizes spatial information and effectively associates object masks across diverse camera poses through a novel 3D-aware memory bank. By eliminating the assumption of continuous view changes in training images, Gaga demonstrates robustness to variations in camera poses, particularly beneficial for sparsely sampled images, ensuring precise mask label consistency. Furthermore, Gaga accommodates 2D segmentation masks from diverse sources and demonstrates robust performance with different open-world zero-shot class-agnostic segmentation models, significantly enhancing its versatility. Extensive qualitative and quantitative evaluations demonstrate that Gaga performs favorably against state-of-the-art methods, emphasizing its potential for real-world applications such as 3D scene understanding and manipulation.
SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking
Charles University, Prague(布拉格查理大学);Czech Technical University in Prague(布拉格捷克理工大学);University of Oxford(牛津大学);EquiLibre Technologies, Inc.(EquiLibre科技有限公司)
TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank
Shenyang Institute of Automation, Chinese Academy of Sciences(中国科学院沈阳自动化研究所);Liaoning Liaohe Laboratory(辽宁省辽河实验室);Key Laboratory on Intelligent Detection and Equipment Technology(智能检测与装备技术重点实验室);University of Chinese Academy of Sciences(中国科学院大学);College of Automation Science and Engineering(自动化科学与工程学院);State Key Laboratory of Robotics and Intelligent Systems(机器人与智能系统国家重点实验室);South China University of Technology(华南理工大学)
Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation
South China University of Technology(南方科技大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Beijing National Research Center for Information Science and Technology, Tsinghua University(北京信息科学研究中心,清华大学);Department of Automation, BNRist, Tsinghua University(清华大学自动化系,北京信息科学研究中心)
GMBFormer: An NDVI-Guided Global Memory Bank Transformer for Urban Green-Space Extraction from Ultra-High-Resolution Imagery
College of Geophysics, Chengdu University of Technology(成都理工大学地球物理学院);National Engineering Research Center for Geomatics, Aerospace Information Research Institute, Chinese Academy of Sciences, and University of Chinese Academy of Sciences(中国科学院测绘学部国家工程研究中心、航天信息研究院、中国科学院大学)
REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence
National Key Laboratory of Multispectral Information Intelligent Processing Technology(多光谱信息智能处理技术国家重点实验室);School of Artificial Intelligence and Automation(人工智能与自动化学院);Huazhong University of Science and Technology(华中科技大学)
Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank
School of Artificial Intelligence and Data Science, University of Science and Technology of China(人工智能与数据科学学院,中国科学技术大学);Shanghai Jiao Tong University(上海交通大学);HKU(香港大学);CUHK(香港大学);Fudan University(复旦大学);Nanjing University(南京大学)
Bridging the Gap between Labeled and Unlabeled Data via Unified Flow with Feature Memory Bank
City University of Macau(澳门城市大学);Southeast University(东南大学);Ocean University of China(中国海洋大学);Nantes Université(南特大学);Ecole Centrale Nantes(南特中央理工学院);CAPACITES SAS;CNRS(法国国家科学研究中心);LS2N(南特数字科学实验室)
Learning Quality-aware Dynamic Memory for Video Object Segmentation
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院,清华大学);Huawei Technologies(华为技术有限公司);University College London(伦敦大学学院)
CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval
Kuaishou Technology(快播科技);Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University(教育部多媒体可信感知与高效计算重点实验室,厦门大学)
Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic
School of Computer Science and Engineering, Sun Yat-sen University, China(中山大学计算机科学与工程学院);Guangdong Province Key Laboratory of Information Security Technology, China(广东省信息安全技术重点实验室);Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China(教育部机器智能与先进计算重点实验室)
Noise-resistant Deep Metric Learning with Ranking-based Instance Selection
Nanyang Technological University (NTU)(南洋理工大学);Alibaba Group(阿里巴巴集团);Shandong University (SDU)(山东大学);Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR)(山东大学-南洋理工大学人工智能联合研究中心)
STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);University of Science and Technology of China(中国科学技术大学)