arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

图像生成

图像生成、文生图、图像编辑、扩散模型和可控生成。

共收录 4236 信号源:cs.CV, cs.GR, cs.MM

1. 可控生成 4236 篇

1612.01928 2016-12-07 cs.CL cs.CV cs.LG cs.SD stat.ML 57%

Invariant Representations for Noisy Speech Recognition

Dmitriy Serdyuk, Kartik Audhkhasi, Philémon Brakel, Bhuvana Ramabhadran, Samuel Thomas, Yoshua Bengio

专题命中 可控生成 :image generation(abstract);分类 cs.CV

Comments 5 pages, 1 figure, 1 table, NIPS workshop on end-to-end speech recognition

详情

展开后加载摘要…

URL PDF HTML 收藏
1612.00215 2016-12-02 cs.CV 57%

Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts

Levent Karacan, Zeynep Akata, Aykut Erdem, Erkut Erdem

专题命中 可控生成 :image synthesis(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
1603.07442 2016-11-29 cs.CV cs.AI 57%

Pixel-Level Domain Transfer

Donggeun Yoo, Namil Kim, Sunggyun Park, Anthony S. Paek, In So Kweon

专题命中 可控生成 :image generation(abstract);分类 cs.CV

Comments Published in ECCV 2016. Code and dataset available at dgyoo.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏
1509.01788 2016-11-17 cs.CV 57%

Joint Color-Spatial-Directional clustering and Region Merging (JCSD-RM) for unsupervised RGB-D image segmentation

Md. Abul Hasnat, Olivier Alata, Alain Trémeau

专题命中 可控生成 :image generation(abstract);分类 cs.CV

Comments submitted to the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

详情

展开后加载摘要…

URL PDF HTML 收藏
1610.02454 2016-10-11 cs.CV cs.NE 57%

Learning What and Where to Draw

Scott Reed, Zeynep Akata, Santosh Mohan, Samuel Tenka, Bernt Schiele, Honglak Lee

专题命中 可控生成 :image synthesis(abstract);分类 cs.CV

Comments In NIPS 2016

详情

展开后加载摘要…

URL PDF HTML 收藏
1607.02748 2016-09-23 cs.CV 57%

Adversarial Training For Sketch Retrieval

Antonia Creswell, Anil Anthony Bharath

专题命中 可控生成 :image generation(abstract);分类 cs.CV

Comments Accepted to ECCV2016 VisArt Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
1604.08164 2016-04-28 cs.CV 57%

Understanding Human-Centric Images: From Geometry to Fashion

Edgar Simo-Serra

专题命中 可控生成 :diffusion(abstract);分类 cs.CV

Comments PhD Thesis, May 2015. BarcelonaTech. 169 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
1603.01768 2016-03-08 cs.CV 57%

Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks

Alex J. Champandard

专题命中 可控生成 :image synthesis(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
1103.2539 2015-03-18 math.OC cs.CV 57%

SO(3)-invariant asymptotic observers for dense depth field estimation based on visual data and known camera motion

Nadege Zarrouati, Emanuel Aldea, Pierre Rouchon

专题命中 可控生成 :diffusion(abstract);分类 cs.CV

Comments Submitted

详情

展开后加载摘要…

URL PDF HTML 收藏
1201.0566 2013-09-20 cs.CV 57%

Learning joint intensity-depth sparse representations

Ivana Tosic, Sarah Drewes

专题命中 可控生成 :inpainting(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
1211.4499 2012-11-20 cs.CV 57%

Rate-Distortion Analysis of Multiview Coding in a DIBR Framework

Boshra Rajaei, Thomas Maugey, Hamid-Reza Pourreza, Pascal Frossard

专题命中 可控生成 :inpainting(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
1204.6563 2012-05-03 cs.CV 57%

Parametric annealing: a stochastic search method for human pose tracking

Prabhu Kaliamoorthi, Ramakrishna Kakarala

专题命中 可控生成 :diffusion(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.11364 2026-03-10 cs.RO 56%

ActivePose: Active 6D Object Pose Estimation and Tracking for Robotic Manipulation

ActivePose: 用于机器人操作的主动6D物体姿态估计与跟踪

Sheng Liu, Zhe Li, Weiheng Wang, Han Sun, Heng Zhang, Hongpeng Chen, Yusen Qin, Arash Ajoudani, Yizhao Wang

机构 * Karlsruhe Institute of Technology(卡尔斯鲁厄理工大学) Shanghai Jiao Tong University(上海交通大学) Istituto Italiano di Tecnologia(意大利理工学院) The Hong Kong Polytechnic University(香港理工大学) D-Robotics(D-机器人)

专题命中 可控生成 :diffusion(abstract,comments)

AI总结 ActivePose通过结合视觉-语言模型与机器人想象力,实现主动6D物体姿态估计与跟踪,提升机器人操作的可靠性。

Comments 6D Pose, Diffusion Policy, Robot Learning

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.18664 2023-05-31 math.OC math.PR 56%

Stochastic Control/Stopping Problem with Expectation Constraints

Erhan Bayraktar, Song Yao

专题命中 可控生成 :diffusion(abstract,comments)

Comments Keywords: Stochastic control/stopping problem with expectation constraints, martingale-problem formulation, enlarged canonical space, Polish space of diffusion controls, Polish space of stopping times, dynamic programming principle, regular conditional probability distribution, measurable selection

详情

展开后加载摘要…

URL PDF HTML 收藏
1706.03564 2017-09-26 math.AP 56%

Sliding mode control for a phase field system related to tumor growth

Pierluigi Colli, Gianni Gilardi, Gabriela Marinoschi, Elisabetta Rocca

专题命中 可控生成 :diffusion(abstract,comments)

Comments Key words: sliding mode control, Cahn-Hilliard system, reaction-diffusion equation, tumor growth, nonlinear boundary value problem, state-feedback control law

详情

展开后加载摘要…

URL PDF HTML 收藏
1009.3247 2016-08-02 math.OC math.PR q-fin.RM 56%

Optimal control of risk process in a regime-switching environment

Chao Zhu

专题命中 可控生成 :diffusion(abstract,comments)

Comments Keywords: Regime switching diffusion, continuity of the value function, exit time control, viscosity solution

详情

展开后加载摘要…

URL PDF HTML 收藏
1004.4250 2016-08-02 math.OC math.PR q-bio.PE 56%

On Optimal Harvesting Problems in Random Environments

Qingshuo Song, Richard Stockbridge, Chao Zhu

专题命中 可控生成 :diffusion(abstract,comments)

Comments Keywords: Regime-switching diffusion, singular stochastic control, quasi variational inequality, viscosity solution, verification theorem

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.27151 2026-08-28 cs.RO 新提交 50%

Planning a Shared Modular Fixture Layout Across Robotic Disassembly Stages

面向机器人拆卸阶段的共享模块化夹具布局规划

Haohui Pan, Takuya Kiyokawa, Kensuke Harada

机构 * The University of Osaka(大阪大学) The National Institute of Advanced Industrial Science and Technology (AIST)(日本国立先进工业科学技术研究所(AIST))

专题命中 可控生成 :diffusion(abstract)

AI总结 该研究针对机器人拆卸中支撑布局需适配阶段变化的问题,提出基于去噪扩散概率模型与贝叶斯优化的模块化真空夹具系统,实现螺丝刀、剃须刀拆卸的共享布局,稳定裕度达66.9%和81.6%,验证了方案的可行性与稳定性。

Comments 15 pages, 9 figures. Submitted to IEEE Transactions on Automation Science and Engineering (T-ASE)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.16153 2026-08-28 cs.RO 版本更新 50%

Unified Condition-Action Modeling for Accurate One-Step Action Generation

用于精准单步动作生成的统一条件-动作建模

Xinyu Zhou, Zikun Cai, Kuangji Zuo, Gen Li, Boyu Ma, Yanshuo Lu, Yutong Song, Mingqi Yuan, Jiayu Chen, Jianfei Yang

机构 * NTU(南洋理工大学) HKU(香港大学)

专题命中 可控生成 :diffusion(abstract)

AI总结 该研究提出UCA-Flow统一条件-动作建模框架,通过共享令牌空间与改进双路监督方案,提升机器人单步动作生成的成功率与推理速度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.27947 2026-08-27 cs.RO 版本更新 50%

SANTS: A State-Adaptive Scheduler for World Action Models

SANTS:面向世界动作模型的状态自适应调度器

Yirui Sun, Guangyu Zhuge, Keliang Liu, Jie Gu, Shiqin Dai, Xinyu Bing, Zhongxue Gan, Chunxu Tian

机构 * Fudan University(复旦大学) Harbin Institute of Technology(哈尔滨工业大学) Deep Computing Era Technology Co., Ltd(深计算时代科技有限公司)

专题命中 可控生成 :diffusion(abstract)

AI总结 提出状态自适应噪声轨迹调度器(SANTS),通过根据视频状态动态选择去噪深度来优化视频到动作的扩散策略,在保持控制性能的同时大幅降低推理延迟。

Comments 13 pages, 5 figures, 8 tables. Project page: https://advanced-robotics-lab.github.io/SANTS/

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.24319 2026-08-26 cs.AI cs.LG cs.SY eess.SY 新提交 50%

Can a Dynamic Internal Field Govern a Transformer's Cognition? Certifiability, not Superiority, in Homeostatic Compute Control

动态内部场能否调控Transformer的认知?稳态计算控制中的可认证性,而非优越性

Francisco M. Arrabal-Campos, Ignacio Fernandez, Francisco G. Montoya, Alfredo Alcayde

机构 * University of Almería(阿尔梅里亚大学) Research Centre CIAIMBITAL(CIAIMBITAL研究中心)

专题命中 可控生成 :diffusion(abstract)

AI总结 该研究探究动态内部场能否调控Transformer认知,证明其具有可认证的运行时稳定性,虽未提升认知能力,但可作为可行的计算调控器。

Comments 22 pages, 4 figures. Companion paper: "Where Cognition Lives" (arXiv:2608.22347). Code, preregistrations and results: https://github.com/fmarrabal/miuracognitive

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.09712 2026-08-26 math.PR 版本更新 50%

Spectral Equality for Novikov Integrability: Recursive Criticality and Unbounded Asymptotic Depth

非线性均值回复扩散过程的精确指数矩阈值

Jaewoo Lee

专题命中 可控生成 :diffusion(abstract)

AI总结 该研究针对常数波动率的非线性均值回复一维扩散过程,推导了Novikov准则中积分平方漂移项指数矩的精确阈值,明确了不同回复率下矩的有限性条件及临界边界。

Comments 48 pages, 3 figures. Ancillary numerical Python script included

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.22367 2026-08-25 cs.CL 新提交 50%

Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMs

上下文感知集群解码:dMLLMs中的语义锚驱动连贯性

Yikai Zhao, Qiyan Zhao, Jiaquan Zhang, Xiaofeng Zhang, Xiaosong Yuan, Pengzhou Cheng

机构 * Sun Yat-sen University(中山大学) Shanghai Jiao Tong University(上海交通大学) University of Electronic Science and Technology of China(电子科技大学) Alibaba Group(阿里巴巴集团) Shanghai University(上海大学)

专题命中 可控生成 :diffusion(abstract)

AI总结 针对 dMLLMs 生成长文本时的语义漂移与重复问题,提出上下文感知集群解码方法,结合置信度与邻域邻近度评分,在多模型多基准上实现质量提升并减少幻觉。

Comments This paper is accepted by EMNLP 2026. 19 pages, 12 figures, 13 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.18699 2026-08-25 cs.CL cs.AI 版本更新 50%

Semantic Substrate Dynamics Theory: An Operator-Theoretic Framework for Geometric Semantic Drift

语义基质理论:几何语义漂移的算子理论框架

Stephen Russell

机构 * Intelligent Systems and Robotics Department(智能系统与机器人系)

专题命中 可控生成 :diffusion(abstract)

AI总结 本文提出语义基质理论,通过算子理论框架分析几何语义漂移,引入桥质量预测未来邻居重排,并提供理论与测试合同。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.19709 2026-08-21 cs.NI 新提交 50%

RFWM: Physics-Guided World Model for Dynamic Wireless Radiance Field Generation

RFWM:用于生成动态无线辐射场的物理引导世界模型

Zijiu Yang, Qianqian Yang

专题命中 可控生成 :diffusion(abstract)

AI总结 本研究针对动态未知环境下RF场建模泛化难的问题,提出物理引导的RF世界模型RFWM,采用两阶段训练策略,在新构建的基准上实现了优于现有最优方法的RF场生成性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.19023 2026-08-20 math.OC cs.NA math.AP math.NA 新提交 50%

Local null controllability of a quasi-linear system and related numerical experiments

一类拟线性系统的局部零能控性及相关数值实验

Enrique Fernández-Cara, Juan Límaco, Yuri Thamsten, Denilson Menezes

专题命中 可控生成 :diffusion(abstract)

AI总结 本文针对扩散系数依赖状态梯度的拟线性抛物系统,通过线性化系统估计与局部逆定理证明其局部零能控性,提出拟牛顿型迭代算法并经数值实验验证。

Comments 31 pages, 16 figures, 9 tables

Journal ref ESAIM: Control, Optimisation and Calculus of Variations 29 (2023) 27

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.18282 2026-08-20 math.OC cs.LG cs.SY eess.SY 新提交 50%

Self-supervised In-context Operator Learning for Stochastic Mean-Field Control

面向随机平均场控制的自监督上下文算子学习

Suyi Gao, Mo Zhou, Rongjie Lai

机构 * Purdue University(普渡大学) University of California, Los Angeles(加利福尼亚大学洛杉矶分校)

专题命中 可控生成 :diffusion(abstract)

AI总结 本研究提出首个无网格自监督神经算子NFIST,通过结合概率流ODE与可逆归一化流Transformer解决随机平均场控制问题,可实现未见任务的一次前向求解,在多任务上展现零样本泛化并降低计算成本。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.18249 2026-08-20 astro-ph.GA astro-ph.EP astro-ph.HE astro-ph.SR 新提交 50%

Accretion of AGN Stars under Influence of Disk Geometry II: The Adiabatic Regime and Runaway Collapse Induced by Self-gravity

吸积盘几何影响下的AGN恒星吸积 II:绝热 regime 与自引力诱导的坍缩

Yi-Xian Chen, Yan-Fei Jiang, Jeremy Goodman

专题命中 可控生成 :diffusion(abstract)

AI总结 该研究通过三维流体动力学模拟,探究AGN盘内恒星吸积的绝热 regime,发现高热质量比下会触发包层强激波,近自引力盘内满足条件时会发生自引力诱导的失控坍缩,可形成~10⁵M_⊙的超大质量恒星。

Comments Accepted to ApJ

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.26635 2026-08-20 math.OC 版本更新 50%

Equilibrium for regular-singular control under mean-variance criterion: A unified approach via control laws

均值方差准则下正则-奇异控制的均衡问题

Zongxia Liang, Xiaodong Luo, Jiayu Zhang

专题命中 可控生成 :diffusion(abstract)

AI总结 本文针对均值方差准则下的混合正则-奇异控制问题,在个人内博弈框架中提出新均衡概念,推导了均衡的数学刻画,并为再保险问题构造了显式耦合均衡解,退化情形下解可简化为独立单控制均衡组合。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.30006 2026-08-18 physics.flu-dyn 版本更新 50%

Exact analytical solutions for the piston effect in supercritical fluids under post-acoustic approximation -- Short-time asymptotics, thermal penetration depth and comparison with the Spacelab D-2 experiments

超临界流体中活塞效应的精确解析解:声学近似后的短时渐近、热穿透深度及与Spacelab D-2实验的比较

Mátyás Szücs

专题命中 可控生成 :diffusion(abstract)

AI总结 针对超临界流体中的活塞效应,在线性后声学近似下推导了直角和球坐标中一维问题的精确解析解,分析了短时渐近和热穿透深度,并通过考虑容器热容与Spacelab D-2实验数据良好吻合。

Comments 33 pages, 12 figure

详情

展开后加载摘要…

URL PDF HTML 收藏