无需训练的开放世界对象放置新方法，想象搜索机制兼顾效率与表现，视觉生成必读。
arXiv:2608.21543v1 Announce Type: cross Abstract: Object placement is critical in image composition, requiring spatially and semantically coherent pos…
全球首款自主打网球机器人亮相，0.1秒锁定50km/h来球，正手成功率超90%，人机混双对决尽显具身智能新高度。
IT之家 8 月 22 日消息，据央视新闻今天报道，全球首款自主打网球的机器人今晚在第二届世界人形机器人运动会亮相。 据介绍，这款机器人来自银河通用，名为“银河星仔”。IT之家了解到， 这款机器人身高约 1.75 米 ，搭载 LATENT 智能规控算法，不依赖预编程，通过深度强化学习自主掌握网球技能…
全面梳理大模型在赛事分析、运动表现与体育媒体中的前沿应用，附数据集与挑战总结。
arXiv:2608.14377v1 Announce Type: new Abstract: Sports have witnessed growing global enthusiasm in recent years, serving as a vital force for physical…
将传感器噪声信息融入逐点协方差建模，为结构光3D成像带来更可靠的精度提升。
arXiv:2608.10888v1 Announce Type: new Abstract: Per-point uncertainty models are important in structured-light 3D reconstruction for probabilistic reg…
把混合专家模型用于乳腺钼靶检测，提升模型鲁棒性，医学影像AI值得一看的新思路。
arXiv:2608.10437v1 Announce Type: new Abstract: Breast lesion detection in mammography remains a challenging task due to variations in image quality, …
脑电信号与多模态AI融合，解码人类动作理解的前沿研究。
arXiv:2506.01353v3 Announce Type: replace Abstract: The integration of brain-computer interfaces (BCIs), in particular electroencephalography (EEG), w…
用隐式神经表示给散斑噪声做“大扫除”，9页9图带你解锁高精度去噪新姿势。
arXiv:2608.06574v1 Announce Type: cross Abstract: Speckle fundamentally limits coherent imaging by introducing multiplicative, spatially correlated no…
跳出帧采样旧范式，重新思考多模态大模型如何真正理解长视频。
arXiv:2608.05592v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong progress in video understanding, yet it …
这项研究将3D建模与空间推理解耦，为AI生成更精细的3D场景提供新思路。
arXiv:2608.05242v1 Announce Type: new Abstract: In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D …
视觉编码器新思路：利用大语言模型进行分层预训练，提升视觉特征学习效率，CVPR 收录论文值得关注。
arXiv:2604.00086v2 Announce Type: replace-cross Abstract: The field of computer vision has experienced significant advancements through scalable visio…
热成像与纹理重建结合新思路，稀疏扰动实现高质量跨模态成像，视觉领域前沿突破
arXiv:2608.02192v1 Announce Type: new Abstract: Thermal imaging remains effective under adverse illumination, yet passive long-wave infrared (LWIR) me…
事件相机直接生成全景图像？E2Pano提出端到端重建方案，突破高动态场景下的成像限制。
arXiv:2608.00694v1 Announce Type: new Abstract: Event cameras offer microsecond-level temporal resolution and high dynamic range, potentially facilita…
前馈式水下3D重建新方法WAT3R，突破水下图像畸变与散射限制，实现快速高精度三维重建。
arXiv:2607.21023v1 Announce Type: new Abstract: Reliable feedforward underwater 3D reconstruction remains challenging due to severe light attenuation …
提出一种简单域泛化方法，显著增强现代视觉语言模型下像素级图像篡改检测的鲁棒性。
arXiv:2607.18230v1 Announce Type: cross Abstract: Modern vision-language models (VLMs) have significantly improved image generation and editing capabi…
管理安卓Nearby Connections API的在线配置工具，帮你轻松关闭App自动开启Wi-Fi/蓝牙功能，提升设备隐私控制。
IT之家 7 月 21 日消息，谷歌宣布将于今年底调整 Nearby Connections API 默认行为，届时无论是谷歌自家 App 还是第三方 App，在设备关闭 Wi-Fi 或蓝牙的情况下，API 都不再自动开启相应功能。 公开信息显示，Nearby Connections 是谷歌提供的一…
解耦模型与人数据不确定性，让面部年龄估计更可靠——这项研究为AI人性化提供了新视角。
arXiv:2607.16378v1 Announce Type: cross Abstract: Estimating the apparent age of individuals from facial images is challenging due to the subjective n…
提出混合显式平移平均方法，提升全局SfM的鲁棒性与精度，是三维视觉领域的新进展。
arXiv:2607.15912v1 Announce Type: new Abstract: Global Structure-from-Motion (SfM) offers advantages over incremental methods in terms of efficiency a…
多智能体协作与前馈架构结合，单目视频秒变3D模型，视觉重建技术新突破
arXiv:2607.15211v1 Announce Type: new Abstract: This paper presents MAGiSt3R, a multi-agent 3D reconstruction framework performing reconstruction and …
自回归模型也能拍电影？这篇论文教你用AI自动生成视频蒙太奇，颠覆传统剪辑思路。
arXiv:2607.14645v1 Announce Type: new Abstract: This work introduces FilmGPT, an autoregressive transformer designed to address the challenge of video…
基于事件相机的合成孔径重建新方法，突破传统成像局限，为高速场景和高动态范围提供创新解决方案。
arXiv:2607.15073v1 Announce Type: cross Abstract: Event cameras report asynchronous polarity events when changes in log--radiance exceed a fixed contr…