1
OpenAI 升级 ChatGPT 购物体验，新增 AI 衣服虚拟试穿体验
IT之家 10 月 2 日消息，OpenAI 宣布进一步升级 ChatGPT 的购物功能，新增虚拟试穿和 Favorites（收藏）两项功能，用户现在可以上传自己的照片，让 ChatGPT 生成穿着特定服饰或配饰后的效果图，同时也可以将感兴趣的商品保存下来，方便之后继续查看。 IT之家注意到，去年 …
2
ShellMaker: Language-Guided Exterior Completion under Structural Constraints
ECCV 2026论文，用语言引导在结构约束下完成3D物体外表面补全，突破传统几何修复限制。
arXiv:2606.31680v1 Announce Type: new Abstract: Despite advances in indoor scene generation, synthesizing coherent building exteriors consistent with …
3
EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
物体移除新方法，利用MLLM驱动前景排除与背景聚合，无需数据集即可重建遮挡区域。
arXiv:2512.21545v2 Announce Type: replace Abstract: Object removal must prevent the masked target from reappearing and reconstruct the occluded backgr…
4
RoboScience机器科学发布Visics通用具身大模型，实现跨本体、跨物体、跨任务｜最前线
作者｜黄楠 编辑｜袁斯来 6月24日，通用具身智能企业RoboScience机器科学通用具身大模型发布，首次完整披露自研Visics大模型的技术架构VLOA（Vision-Language-Object-Action），并展示了模型在家具拼装、灵巧抓取、动态流水线等多项真实场景的应用。 大语言模型有…
5
Geometry-Instructed Video Editing
首次实现视频中物体平移、旋转、缩放等3D几何编辑，突破生成式视频编辑的可靠性瓶颈
arXiv:2606.24225v1 Announce Type: new Abstract: Object-level geometric edits, including translating, rotating, scaling, duplicating, or removing an ob…
6
A US military exercise in space got underway with barely anyone noticing
美国太空军秘密展开军事演习，一颗新卫星从新西兰悄悄升空，几乎无人察觉。
The Space Force wants to cut the time to field new satellites from years to weeks, days, or hours.
7
Show HN: Remove Anything – AI Background Removal Tool
AI一键擦除照片中多余物体、背景和水印，输出透明PNG，高效实用。
Remove background from any image in 3 seconds using AI. Free, no watermarks, runs in browser. https://remove-anything.com --- https://remove-anything.…
8
苹果 iOS / macOS / iPadOS 27 图标重绘：叠层之间会产生折射，主打独特美感
AI动嘴修图？Clipdrop 让你说句话就能智能移除物体或更换背景，所见即所得。
IT之家 6 月 9 日消息，在今天的 WWDC26 上，苹果正式宣布 iOS / macOS / iPadOS 27 图标重绘， 相较于前代设计更加统一 ，主打视觉宽阔。 据介绍，苹果将额外的液体玻璃层直接集成到图标本身中， 叠层之间还会产生折射 ，为图标带来独特美感。 IT之家注意到，苹果还加入…
9
苹果专利构想 Vision Pro 配件：通过 Apple Pencil 触觉感知虚拟物体
IT之家 6 月 3 日消息，科技媒体 Appleinsider 昨日（6 月 2 日）发布博文，报道称苹果获批一项新专利，在配合 Vision Pro 头显使用时，Apple Pencil 通过触觉反馈传递虚拟物体的摩擦、纹理和粗糙感。 IT之家援引博文介绍，最新获批专利名称为《表面纹理检测与模拟…
10
Mitigating Object Hallucinations via Sentence-Level Early Intervention
句子级早期干预方法精准抑制大模型物体幻觉，显著提升多模态生成可靠性
arXiv:2507.12455v3 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continu…
11
ComPose: When to Trust Hands for Object Pose Tracking
物体姿态追踪遇手部遮挡？新方法揭示何时能信任手部线索，助力机器人操作
arXiv:2605.23523v1 Announce Type: new Abstract: Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipula…
12
PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media
视觉物体移除评估新基准，解决感知一致性难题，比现有指标更贴近人类判断。
arXiv:2605.14534v1 Announce Type: cross Abstract: Evaluating object removal in images and videos remains challenging because the task is inherently on…
13
Overlap-aware segmentation for topological reconstruction of obscured objects
高能物理实验中的新方法：用重叠感知分割实现被遮挡物体的精准拓扑重建，突破视觉遮挡难题。
arXiv:2510.06194v2 Announce Type: replace-cross Abstract: The separation of overlapping objects presents a significant challenge in scientific imaging…
14
ART: Articulated Reconstruction Transformer
类别无关的前馈模型，仅凭稀疏多状态RGB图像快速重建完整3D铰接物体。
arXiv:2512.14671v3 Announce Type: replace Abstract: We introduce ART, Articulated Reconstruction Transformer -- a category-agnostic, feed-forward mode…
15
PinpointQA: A Dataset and Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos
首个聚焦室内视频小物体空间理解的数据集与评测基准，直击多模态大模型在细小物体感知上的短板
arXiv:2604.08991v2 Announce Type: replace-cross Abstract: Small object-centric spatial understanding in indoor videos remains a significant challenge …
16
Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting
抱歉，您提供的内容是一篇学术论文的摘要，而非一个具体可用的在线工具。请提供一个您希望我推荐的在线工具链接或名称，我将按照指定格式为您生成推荐。
arXiv:2605.16065v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3D-GS) enables real-time 3D scene reconstruction but lacks robust segmentatio…