正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Excited to release the first worldwide aerial image localization method (and demo!) Take an aerial or satellite image from anywhere in the world, and AstroLoc can (probably) find its location, and provide a precise footprint! Links to paper, demo and full-length (5 min) video ⬇️

Gabriele Berton

15,396 subscribers

34,062 次观看 • 1 年前 •via X (Twitter)

科学技术新闻政治教育

Anya Rossi• Live Now

Private livecam show

13 条评论

Gabriele Berton 的头像

Gabriele Berton1 年前

AstroLoc is an image retrieval model trained on 5M satellite images and 300k photos by astronauts on the ISS. We use two contrastive losses, one with pairs of satellite-astronaut photos, and one with only satellite images, mined as per the distribution of astronaut photos.

Gabriele Berton 的头像

Gabriele Berton1 年前

How does the demo work? It uses a worldwide database of over 50M images, multiple resolutions (mpp) and orientations, in order to work also for non-north-up images. The predictions are post-processed with EarthMatch, using matchers like RoMa and LightGlue

Gabriele Berton 的头像

Gabriele Berton1 年前

Strengths and limitations? AstroLoc works well for very unusual images, including photos of wildfires, old images taken by the Space Shuttle and more. The demo is limited...

Gabriele Berton 的头像

Gabriele Berton1 年前

to images with land area between 10 km2 and 2M km2 (yes, it spans 6 orders of magnitudes!), so it won't be able to localize photos taken by a standard low altitude drone. Increasing this range is a potential future work.

Gabriele Berton 的头像

Gabriele Berton1 年前

Why is it useful? The main reason for this project is for NASA to geo-locate millions of photos taken by astronauts on the ISS. You read that right! Part of being an astronaut on the ISS is to take photos of Earth, which have unique...

Gabriele Berton 的头像

Gabriele Berton1 年前

characteristics and are complimentary to more common satellite images. Check out @DonPetit, who’s on ISS right now, for some awesome recent examples.

Gabriele Berton 的头像

Gabriele Berton1 年前

Why do astronauts on the ISS take photos of Earth and why do we need to localize them? Many reasons, ranging from natural disaster management (for which footprint localization is really important) and climate change studies. More info on the paper and here

Gabriele Berton 的头像

Gabriele Berton1 年前

If you're more curious about how they take photos, check out this video from @smartereveryday, where he's interviewing ISS astronaut @dominickmatthew on the subject

Gabriele Berton 的头像

Gabriele Berton1 年前

And if you want to know why they take these photos, check out this video from @NASA @NASAEarth

Gabriele Berton 的头像

Gabriele Berton1 年前

A big thanks to AstroLoc's co-authors! @AlexStoken @masone_carlo The demo is built with @Gradio, such an amazing tool!

Gabriele Berton 的头像

Gabriele Berton1 年前

Link to demo (the link to the demo expires in 3 days, then I'll post a new link): Link to paper: Link to full-length (5 minutes) demo video:

Gabriele Berton 的头像

Gabriele Berton1 年前

And tagging some people that I think might like the demo @robmarkcole @isaaccorley_ @AshFunction @Mouthofmorrison @normconstant @d_kerkow @Cgeoconsulting @stian_h_haugen @yohaniddawela @theepicmap

ARK Electronics 的头像

ARK Electronics2 年前

Excited about the latest tech for your drone product? Our NDAA-compliant, US-made flight controllers are designed to accelerate your path to market and provide a solid platform for developing your autonomous software. Check them out! #Drones #UAV #UAS #Robotics #MadeInUSA

相关视频

𝐒𝐔𝐏𝐈𝐑: An advanced image restoration method that combines generative prior and model scaling,using a 20-million image dataset, and can manipulate restorations with textual prompts. Kudos to Fanghua Yu Jinjin Gu Xintao Wang et al🚀 SUPIR supports Gradio demo in repo [links👇]

𝐒𝐔𝐏𝐈𝐑: An advanced image restoration method that combines generative prior and model scaling,using a 20-million image dataset, and can manipulate restorations with textual prompts. Kudos to Fanghua Yu Jinjin Gu Xintao Wang et al🚀 SUPIR supports Gradio demo in repo [links👇]

Gradio

56,351 次观看 • 2 年前

The AI Georeferencer in QGIS is now publicly available 1. Aerial imagery georeferences to satellite near the QGIS map canvas 2. The full georeferencer reads coordinates, buildings, streets, PLSS, cities, and other features humans use Rotated aerial image support is coming soon

The AI Georeferencer in QGIS is now publicly available 1. Aerial imagery georeferences to satellite near the QGIS map canvas 2. The full georeferencer reads coordinates, buildings, streets, PLSS, cities, and other features humans use Rotated aerial image support is coming soon

Brendan Ashworth

36,676 次观看 • 1 年前

I created an AI assistant to help me read papers quickly. 1. Open AK 's daily paper recommendations 2. Screenshot the first page of the paper 3. Paste the image into the AI assistant and generate a summary The assistant: Watch the demo video 👇

I created an AI assistant to help me read papers quickly. 1. Open AK 's daily paper recommendations 2. Screenshot the first page of the paper 3. Paste the image into the AI assistant and generate a summary The assistant: Watch the demo video 👇

Jiayuan (JY) Zhang

24,095 次观看 • 2 年前

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Dreaming Tulpa 🥓👑

270,942 次观看 • 2 年前

Today, we’re launching Reve 2.0, the best 4K image model in the world. We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.

Today, we’re launching Reve 2.0, the best 4K image model in the world. We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.

Reve

11,915,225 次观看 • 1 个月前

The training code for Hunyuan World 1.1 (WorldMirror) is released now!🔥🔥🔥 This release provides researchers and developers the full stack for customization and fine-tuning: 📷 Your video to 3D worlds in 1 second. 🪄ANY input (image, video, 3D prior) to ANY output (3DGS, depth, cameras, normal, points) Start customizing your model and exploring the demo! Online demo: Code:

The training code for Hunyuan World 1.1 (WorldMirror) is released now!🔥🔥🔥 This release provides researchers and developers the full stack for customization and fine-tuning: 📷 Your video to 3D worlds in 1 second. 🪄ANY input (image, video, 3D prior) to ANY output (3DGS, depth, cameras, normal, points) Start customizing your model and exploring the demo! Online demo: Code:

Tencent Hy

67,843 次观看 • 8 个月前

✨ Introducing 3 new ways to build with real-world imagery and AI → From the fine details of a city street to a bird's eye view of the planet, at Cloud Next we revealed new ways that businesses can use our Street View, aerial and satellite imagery, and tap into our comprehensive view of the physical world including: 🏙️ Use Maps Imagery Grounding in Gemini Enterprise Agent Platform to generate location-specific assets at scale, anchored in real-world Street View imagery 🌍 Unlock a new perspective with Aerial and Satellite Insights, part of Earth AI, in BigQuery and Agent Platform to quickly extract detailed info about our changing planet 🛰️ Build custom apps with Aerial and Satellite models in Model Garden from Earth AI that easily identify specific objects or scenes Read the blog at the link above and sign up for early access.

✨ Introducing 3 new ways to build with real-world imagery and AI → From the fine details of a city street to a bird's eye view of the planet, at Cloud Next we revealed new ways that businesses can use our Street View, aerial and satellite imagery, and tap into our comprehensive view of the physical world including: 🏙️ Use Maps Imagery Grounding in Gemini Enterprise Agent Platform to generate location-specific assets at scale, anchored in real-world Street View imagery 🌍 Unlock a new perspective with Aerial and Satellite Insights, part of Earth AI, in BigQuery and Agent Platform to quickly extract detailed info about our changing planet 🛰️ Build custom apps with Aerial and Satellite models in Model Garden from Earth AI that easily identify specific objects or scenes Read the blog at the link above and sign up for early access.

Google Maps Platform

11,689 次观看 • 2 个月前

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

Timothy Young

10,093 次观看 • 2 年前

The Story Demo and Battle Demo for #TrailsbeyondtheHorizon are now available on PlayStation 4 and PlayStation 5! Start the game from the beginning with the Story Demo and transfer your save data to the full game, or see what combat looks like later in your adventure with the Battle Demo!

The Story Demo and Battle Demo for #TrailsbeyondtheHorizon are now available on PlayStation 4 and PlayStation 5! Start the game from the beginning with the Story Demo and transfer your save data to the full game, or see what combat looks like later in your adventure with the Battle Demo!

NISAmerica

257,645 次观看 • 6 个月前

[1/2] We’ve released the code for #pix2pixturbo and #CycleGANTurbo. These conditional GANs are able to adapt a text-to-image model such as SD-Turbo for both paired and unpaired image translation with a single step (0.11 sec on A100 and 0.29 sec on A6000). Try our code and the Gradio demo. Paper: Code: Demo: This is a joint work with Gaurav Parmar (the leading author), Taesung Park, and Srinivasa Narasimhan. This work shows that a pre-trained one-step model can be easily adapted to conditional GANs frameworks for downstream image editing and synthesis tasks. #Edges2Cats

[1/2] We’ve released the code for #pix2pixturbo and #CycleGANTurbo. These conditional GANs are able to adapt a text-to-image model such as SD-Turbo for both paired and unpaired image translation with a single step (0.11 sec on A100 and 0.29 sec on A6000). Try our code and the Gradio demo. Paper: Code: Demo: This is a joint work with Gaurav Parmar (the leading author), Taesung Park, and Srinivasa Narasimhan. This work shows that a pre-trained one-step model can be easily adapted to conditional GANs frameworks for downstream image editing and synthesis tasks. #Edges2Cats

Jun-Yan Zhu

36,488 次观看 • 2 年前

I built software to cut docker image sizes by more than 80%. It uses dynamic analysis and and has a LOT more room for improvement. The demo here shows an ETL workflow docker image, cut down from 1.28GB to 193MB (-85%)! If large docker image sizes are becoming a production problem, I'd be happy to explore how we can help.

I built software to cut docker image sizes by more than 80%. It uses dynamic analysis and and has a LOT more room for improvement. The demo here shows an ETL workflow docker image, cut down from 1.28GB to 193MB (-85%)! If large docker image sizes are becoming a production problem, I'd be happy to explore how we can help.

omkaar

353,176 次观看 • 1 年前

AI can potentially be used to identify and track car make and model just from a grainy satellite image 👇

AI can potentially be used to identify and track car make and model just from a grainy satellite image 👇

Daniel Heinen

145,239 次观看 • 8 个月前

Figma > Edit Image can take the JSON style code inputs for retexturing any image on canvas • demo ↓

Figma > Edit Image can take the JSON style code inputs for retexturing any image on canvas • demo ↓

Rahul Chakraborty

31,968 次观看 • 1 年前

Here's a demo of the gpt-4-vision API that I built in Bubble in 30 min. It takes a URL, converts it to an image, and sends it through the Vision API to respond with custom landing page optimization suggestions.

Here's a demo of the gpt-4-vision API that I built in Bubble in 30 min. It takes a URL, converts it to an image, and sends it through the Vision API to respond with custom landing page optimization suggestions.

Seth Kramer

953,992 次观看 • 2 年前

Following the release of Wan2.7-Image, Alibaba has launched Wan2.7-Video, its video generation model. By bringing together text, image, video, and audio inputs, addressing gaps in narrative coherence and multi-shot consistency. Watch the video and explore its capabilities!

Following the release of Wan2.7-Image, Alibaba has launched Wan2.7-Video, its video generation model. By bringing together text, image, video, and audio inputs, addressing gaps in narrative coherence and multi-shot consistency. Watch the video and explore its capabilities!

Alibaba Cloud

3,675,713 次观看 • 2 个月前

Here is an image of the offending placard from the demo on Saturday and a video of the arrest. If anyone knowns the man who was arrested, please get in touch (or ask him to get in touch direct), as we (Left Legal Fighting Fund) may be able to assist.

Here is an image of the offending placard from the demo on Saturday and a video of the arrest. If anyone knowns the man who was arrested, please get in touch (or ask him to get in touch direct), as we (Left Legal Fighting Fund) may be able to assist.

David Miller

29,812 次观看 • 1 年前

🔥 DreamEngine revolutionizes image generation with its text-guided object fusion capabilities! The demo and code for Text Guided Object Fustion are released! Let's unlock the Imaginations! Run it locally now in: Paper:

🔥 DreamEngine revolutionizes image generation with its text-guided object fusion capabilities! The demo and code for Text Guided Object Fustion are released! Let's unlock the Imaginations! Run it locally now in: Paper:

Liang Chen

11,357 次观看 • 1 年前

Project Light Touch from Adobe enables you to modify the lighting in any image. You can move the lighting anywhere within a scene in 3D space, adjusting its color, position, depth, and brightness.

Project Light Touch from Adobe enables you to modify the lighting in any image. You can move the lighting anywhere within a scene in 3D space, adjusting its color, position, depth, and brightness.

CHRIS FIRST

107,325 次观看 • 8 个月前

Dreamina Seedance 2.0 is by far the best video model I've tried, and Dreamina makes it even better. You can try it in the link below. It's not just about the quality of the output, but about how much control you have over your video's look. Watch my video here. I'm attaching reference images and asking the model to generate a video using them. I can reference each image using the @ symbol to instruct the model which image to use. You can even upload a clip and use its camera movement, styles from an image, and audio vibe from a track. By the way, you can take an existing video and replace, remove, or add elements to it while the model preserves everything else. This is the closest we've gotten to "editing videos like photos".

Dreamina Seedance 2.0 is by far the best video model I've tried, and Dreamina makes it even better. You can try it in the link below. It's not just about the quality of the output, but about how much control you have over your video's look. Watch my video here. I'm attaching reference images and asking the model to generate a video using them. I can reference each image using the @ symbol to instruct the model which image to use. You can even upload a clip and use its camera movement, styles from an image, and audio vibe from a track. By the way, you can take an existing video and replace, remove, or add elements to it while the model preserves everything else. This is the closest we've gotten to "editing videos like photos".

Santiago

45,143 次观看 • 3 个月前