Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Calculating pothole volume from a 2D image is challenging but possible: > Assign each pothole an ID to avoid duplication. > Use basic trigonometry to convert pixels to real-world meters. > Apply a novel algorithm to estimate depth using road engineering data.

Marco Franzon

8,170 subscribers

133,860 Aufrufe • vor 9 Monaten •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Pothole detection on the road in real time using Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AI

Pothole detection on the road in real time using Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AI

Muhammad Rizwan Munawar

30,677 Aufrufe • vor 3 Monaten

Helldivers 2 inspired game but AI is a Real Human! Wishlist on Steam to support me >>>

Helldivers 2 inspired game but AI is a Real Human! Wishlist on Steam to support me >>>

Marines vs God

3,553,766 Aufrufe • vor 1 Jahr

AWS WAF + World ID User hits rate limit: > Challenged to verify with World ID > Server verifies ZK proof > User issued a temporary session cookie Repo in thread, built by David MacDonald from AWS!

AWS WAF + World ID User hits rate limit: > Challenged to verify with World ID > Server verifies ZK proof > User issued a temporary session cookie Repo in thread, built by David MacDonald from AWS!

Andy

12,320 Aufrufe • vor 4 Monaten

your next marketing team is ONE CONVERSATION. Higgsfield MCP plugged into Claude Opus 4.8 just took me from zero to a launch-ready ads creative batch in an afternoon. > market research > image gen > animation > transitions REAL ESTATE MARKETING JUST CHANGED FOREVER

your next marketing team is ONE CONVERSATION. Higgsfield MCP plugged into Claude Opus 4.8 just took me from zero to a launch-ready ads creative batch in an afternoon. > market research > image gen > animation > transitions REAL ESTATE MARKETING JUST CHANGED FOREVER

arc.

55,013 Aufrufe • vor 1 Monat

People that actually think outside the box >>>>>> This is a breath of fresh air from the usual they want to use and finish us. The fact that it looks appetizing....I rate it a 💯 abeg Would you be willing to try this out?

People that actually think outside the box >>>>>> This is a breath of fresh air from the usual they want to use and finish us. The fact that it looks appetizing....I rate it a 💯 abeg Would you be willing to try this out?

NaijaFarmer

34,503 Aufrufe • vor 7 Monaten

This is not acceptable An Overseas Pakistani has paid a shepherd to take his animals for a walk on GT road for some fresh air GT ( Grazing Track)

This is not acceptable An Overseas Pakistani has paid a shepherd to take his animals for a walk on GT road for some fresh air GT ( Grazing Track)

Bilal AI

67,737 Aufrufe • vor 5 Monaten

CLI agents using.. CLI browsers?? Agents can use tmux to control carbonyl, a Chromium browser that runs in the terminal > Browser representation in ASCII art > Interacts directly with "pixels" i.e. text in the terminal Could this be the future of AI browser use?

CLI agents using.. CLI browsers?? Agents can use tmux to control carbonyl, a Chromium browser that runs in the terminal > Browser representation in ASCII art > Interacts directly with "pixels" i.e. text in the terminal Could this be the future of AI browser use?

shawn

113,970 Aufrufe • vor 3 Monaten

Road to Perdition! An RTC bus struggles to move past a pothole in #Hyderabad. This one is near MGBS, Chadarghat. City’s roads are riddled with potholes. Pathetic is an understatement. Free bus okay! But you know what will be better? Roads free of potholes 🙏🏽🙏🏽🙏🏽 #Pathetic #Roads

Road to Perdition! An RTC bus struggles to move past a pothole in #Hyderabad. This one is near MGBS, Chadarghat. City’s roads are riddled with potholes. Pathetic is an understatement. Free bus okay! But you know what will be better? Roads free of potholes 🙏🏽🙏🏽🙏🏽 #Pathetic #Roads

Revathi

170,854 Aufrufe • vor 9 Monaten

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,792 Aufrufe • vor 2 Jahren

looksmaxing is blowing up and this is the easiest format to promote an app 7.3M views on this video using: > fully ai-generated person > before/after transformation > "let's try this thing" hook they're pushing peptides but this format + a looksmaxing app = easy viral content

looksmaxing is blowing up and this is the easiest format to promote an app 7.3M views on this video using: > fully ai-generated person > before/after transformation > "let's try this thing" hook they're pushing peptides but this format + a looksmaxing app = easy viral content

Fekri

13,443,052 Aufrufe • vor 7 Monaten

The World Cup is on! ⚽️ Trade Mundial markets and earn your chance to secure a Mundial Box. The boxes stay sealed until reveal day. Get involved now -> -> use code: WORLDCUP

The World Cup is on! ⚽️ Trade Mundial markets and earn your chance to secure a Mundial Box. The boxes stay sealed until reveal day. Get involved now -> -> use code: WORLDCUP

Chance

16,535 Aufrufe • vor 1 Monat

Damn it worked! Genie 3 world --> inpaint UI --> 4x topaz AI upscale --> train 3d gaussian splat You can step inside a painting of Socrates from 1787. Better than any image-to-3d model I've seen. I think Google has stumbled upon the killer app for VR -- the literal holodeck.

Damn it worked! Genie 3 world --> inpaint UI --> 4x topaz AI upscale --> train 3d gaussian splat You can step inside a painting of Socrates from 1787. Better than any image-to-3d model I've seen. I think Google has stumbled upon the killer app for VR -- the literal holodeck.

Bilawal Sidhu

657,658 Aufrufe • vor 11 Monaten

LOOK. This is just a regular ol' website. No JavaScript whatsoever. Navigation pages with clicks <a> links to other HTML pages. The most basic website in the world. Yet, with a few lines of code to activate View Transitions, KAPOW.

LOOK. This is just a regular ol' website. No JavaScript whatsoever. Navigation pages with clicks <a> links to other HTML pages. The most basic website in the world. Yet, with a few lines of code to activate View Transitions, KAPOW.

Chris Coyier

830,480 Aufrufe • vor 3 Jahren

this is an untapped niche for mobile apps. 1.7M views. > add a catchy timer with strong visuals > track times + block apps use this exact format to promote the app. don’t sleep on this trend.

this is an untapped niche for mobile apps. 1.7M views. > add a catchy timer with strong visuals > track times + block apps use this exact format to promote the app. don’t sleep on this trend.

Simone Canc

361,511 Aufrufe • vor 7 Monaten

Figured out a cool workflow to automate product videos and virtual staging. I made this in a couple minutes and could've further optimized the clips - but it's a great first try! This is a real furniture set from Pottery Barn. It uses Ideogram -> nano-banana -> Veo 3 👇

Figured out a cool workflow to automate product videos and virtual staging. I made this in a couple minutes and could've further optimized the clips - but it's a great first try! This is a real furniture set from Pottery Barn. It uses Ideogram -> nano-banana -> Veo 3 👇

Justine Moore

48,535 Aufrufe • vor 10 Monaten

gamedev friends! please help! I am trying to export from blender (->fbx) A mesh that is PARENTED to an animated bone (not skinned!) I CAN'T find a combination of export settings that will. correctly position the object in Unity (the yellow container in the image)

gamedev friends! please help! I am trying to export from blender (->fbx) A mesh that is PARENTED to an animated bone (not skinned!) I CAN'T find a combination of export settings that will. correctly position the object in Unity (the yellow container in the image)

thomas "noio" vandenberg

86,683 Aufrufe • vor 6 Monaten

Ok in just a few hours, I have converted my Claude Skill into an entire Mac App that can be used by anyone.. > Sign in with Google (mail + cal) > Give it disk access > Voila! Right now it's using my own API keys, but will transition to BYOK. The future is truly wild💃

Ok in just a few hours, I have converted my Claude Skill into an entire Mac App that can be used by anyone.. > Sign in with Google (mail + cal) > Give it disk access > Voila! Right now it's using my own API keys, but will transition to BYOK. The future is truly wild💃

Nikunj Kothari

202,265 Aufrufe • vor 6 Monaten

3. Modify image Use this prompt to modify the image you have chosen: "Modify image [1] with seed [1470033597]: add a parrot on her shoulder" Dall-E 3 identifies the image and makes the changes for you! Tips and tricks: - You can generate as many variations as you like. - It's also possible to remove an element from the image using the same method. - Sometimes the image isn't 100% identical, but still looks very similar.

3. Modify image Use this prompt to modify the image you have chosen: "Modify image [1] with seed [1470033597]: add a parrot on her shoulder" Dall-E 3 identifies the image and makes the changes for you! Tips and tricks: - You can generate as many variations as you like. - It's also possible to remove an element from the image using the same method. - Sometimes the image isn't 100% identical, but still looks very similar.

Paul Couvert

44,073 Aufrufe • vor 2 Jahren

A preview of what's next, visualized with Rerun and PlayCanvas supersplat ✨ (Also, feel free to send me a DM 📩; I’ll be in San Francisco from July 21–29, and I'm looking to meet like-minded folks!) I'm convinced that Gaussian Splats will be an integral part of any data engine as an underlying representation. So I've started putting together a repo that: 1. Given a single image, perform image outpainting 🖼️🖌️ 2. Estimate a monocular depth map on the outpainted image 📏 3. Train a Gaussian Splat initialized from the monocular depth 🎓✨ 4. Warp to new views, perform inpainting on the missing masks -> Train new splat 🔄🎨 This is going to be integrated into exo-egoforge, but I wanted to start with the simple single-image version before moving to a multi-video implementation There's some weirdness in the final rerun visualization, but the trained splat looks great 🎉! This is all based on the very cool VistaDream paper ( .github.io/) More on this next week!

A preview of what's next, visualized with Rerun and PlayCanvas supersplat ✨ (Also, feel free to send me a DM 📩; I’ll be in San Francisco from July 21–29, and I'm looking to meet like-minded folks!) I'm convinced that Gaussian Splats will be an integral part of any data engine as an underlying representation. So I've started putting together a repo that: 1. Given a single image, perform image outpainting 🖼️🖌️ 2. Estimate a monocular depth map on the outpainted image 📏 3. Train a Gaussian Splat initialized from the monocular depth 🎓✨ 4. Warp to new views, perform inpainting on the missing masks -> Train new splat 🔄🎨 This is going to be integrated into exo-egoforge, but I wanted to start with the simple single-image version before moving to a multi-video implementation There's some weirdness in the final rerun visualization, but the trained splat looks great 🎉! This is all based on the very cool VistaDream paper ( .github.io/) More on this next week!

Pablo Vela

26,036 Aufrufe • vor 1 Jahr

Here's a closer look at the new GR GT and GT3 version. Both versions were developed alongside each other and together. But although it is an all-new sports car, the GT is also a rather traditional one, with a V-8 at the front driving the rear wheels and only what seems to be a modest level of hybrid assistance.

Here's a closer look at the new GR GT and GT3 version. Both versions were developed alongside each other and together. But although it is an all-new sports car, the GT is also a rather traditional one, with a V-8 at the front driving the rear wheels and only what seems to be a modest level of hybrid assistance.

Road & Track

21,030 Aufrufe • vor 7 Monaten