1
有史以来最大更新：苹果发布 Core Image RAW 9 处理管线，提升 RAW 图像质量
苹果RAW处理管线最大更新，支持784款相机，RAW画质飞跃式提升
IT之家 6 月 12 日消息，苹果在 WWDC26 上发布了 Core Image RAW 9 处理管线及其 API。 IT之家获悉，这是自 2017 年 RAW 8 发布以来，Core Image RAW 的首次重大版本更新。苹果工程师将其称之为“ 有史以来最大的一次更新 ”。 官方表示，来自任…
2
Apple’s Image Playground Just Caught Up to ChatGPT and Gemini
苹果最新系统更新让Image Playground的AI图像生成能力大幅提升，与ChatGPT和Gemini同台竞技。
I might actually start using Image Playground now.
3
比亚迪公布车底活体检测专利：车辆下电后建立基准图像比对识别
IT之家 6 月 13 日消息，国家知识产权局于 6 月 12 日公开了一项比亚迪关于“车底活体检测方法、计算机程序产品、电子设备及车辆”的发明专利。 专利摘要显示，该检测方法的核心思路是在车辆下电时，将当前的车底图像作为基准图像；此后系统会基于该基准图像与车底的实时图像进行比对，确定存在差异区域的…
4
Let ViT Speak: Generative Language-Image Pre-training
ViT也能开口说话？全新生成式语言-图像预训练框架，让视觉与语言深度融合！
arXiv:2605.00809v2 Announce Type: replace Abstract: In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-traini…
5
FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching
脑龄预测新方法：小波流匹配生成高质量3D脑MRI，解决数据不平衡难题
arXiv:2601.05212v2 Announce Type: replace Abstract: Brain Magnetic Resonance Imaging (MRI) plays a central role in studying neurological development, …
6
Scary ChatGPT Bug: AI Generates Nightmarish Images from a Simple Prompt Trick
只需一个简单提示，ChatGPT就能生成让人毛骨悚然的噩梦图像，比恐怖片还吓人！
A newly discovered glitch in ChatGPT is sending shivers down users' spines. By using a simple prompt to retrieve a non-existent image, the AI falls in…
7
Causal Transfer in Medical Image Analysis
因果迁移学习如何提升医学图像分析的鲁棒性和可解释性？这篇论文给出系统性探索。
arXiv:2603.24388v2 Announce Type: replace Abstract: Medical imaging models frequently fail when deployed across hospitals, scanners, populations, or i…
8
HDRAgent: An Agentic Framework for Multi-Exposure HDR Imaging
用大模型代理自动化多曝光HDR成像流程，HDRAgent框架让复杂影像合成更智能。
arXiv:2606.09110v1 Announce Type: new Abstract: Most existing multi-exposure HDR methods follow a fixed feed-forward reconstruction paradigm, making t…
9
Show HN: RunAPI – one API for AI video, image, music, audio, and LLMs
一个API搞定10+AI服务，视频图像音乐音频LLM全囊括，开发者效率利器。
After building a few SaaS apps, I found that connecting many AI model APIs at the same time gets messy very quickly. So I built RunAPI, which lets you…
10
Leveraging NeRF-Rendered Images for 3D Gaussian Splatting
巧妙融合NeRF高质量渲染与3DGS高速渲染，利用互补优势提升新视角合成性能。
arXiv:2606.09034v1 Announce Type: new Abstract: Neural radiance field (NeRF) and 3D Gaussian splatting (3DGS) are two mainstream approaches for novel …
11
Apple’s Image Playground doesn’t suck anymore
苹果Image Playground升级后不再鸡肋，WWDC 2026带来AI图像生成新体验，支持多人照片变风格。
Apple's AI image generator is getting a makeover that could make it more competitive.
12
Show HN: Luminous – fast image viewer in Rust, SAM 3 and CLIP support
基于Rust的极速图像浏览器，集成SAM 3与CLIP，跨平台开源且支持插件扩展。
Hey HN! I built a fast native cross-platform open-source image viewer called Luminous in Rust/Slint UI. The main features: - Mainly focused on perform…
13
Ask HN: Why isn't AI image generation closely linked with graphics code gen?
讨论AI图像生成与图形代码生成割裂的根源，启发开发者思考工具融合新方向
For example, when making an iOS game, you might want to ask the AI look at a screenshot of your game and to generate images with improved graphics. Yo…
14
Asd: A fast, AI-native cat replacement written in Go
用Go打造的AI原生压缩文件浏览器，支持在终端内探索zip/tar/7z并显示图片。
Article URL: https://github.com/orchestrator-dev/asd Comments URL: https://news.ycombinator.com/item?id=48395218 Points: 1 # Comments: 1
15
Grok Imagine Video 1.5 on AI Gateway
xAI新模型上线：单次同步生成带音频视频，从图片到影视级片段一步到位。
Grok Imagine Video 1.5 from xAI is now available on AI Gateway. The model generates video from an input image with synchronized audio in a single pass…
16
MiniMax M3一手实测：老黄PPT上74个Logo，我以为能难住它
实测MiniMax M3：能准确识别老黄PPT上74个Logo，甚至纠正路径逻辑，闭源模型中也仅“御三家”能做到。
还能带你打卡老黄同款南锣路线
17
OpenAI's ChatGPT returns another user's response when I paste an image
用户反馈ChatGPT粘贴图片后返回他人回复，疑似数据混淆，引发隐私担忧
Not sure if this is happening to others, but sometimes when I paste an image, I get an answer completely different from what I attached. It also somet…
18
Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images
合成图像无处遁形？用颜色统计特征高效分辨真假图像，方法新颖且实用。
arXiv:2606.02224v1 Announce Type: new Abstract: The evolution and dissemination of AI-synthesized images is occurring at an unprecedented rate. Image …
19
ToolFG: Towards Well-Grounded Fine-Grained Image Classification
基于细粒度图像分类的新框架ToolFG，强调分类结果的可靠性与可解释性，推进视觉基础模型在细粒度场景的应用。
arXiv:2606.02518v1 Announce Type: new Abstract: Fine-grained image classification (FGIC) has broad applications and has attracted significant research…
20
今天起，无限期免费！全球首个全模态API开放，Top 10 AI Lab出手
全球首个全模态API无限期免费开放，Top 10 AI Lab出品，支持图像、视频、文本与3D特效生成，细节拉满。
文本图像视频都能用