[HN Gopher] YOLO-World: Real-Time Open-Vocabulary Object Detection
___________________________________________________________________
YOLO-World: Real-Time Open-Vocabulary Object Detection
Author : greesil
Score : 52 points
Date : 2025-05-31 20:54 UTC (2 hours ago)
(HTM) web link (arxiv.org)
(TXT) w3m dump (arxiv.org)
| ed wrote:
| Neat. Wonder how this compares to Segment Anything (SAM), which
| also does zero-shot segmentation and performs pretty well in my
| experience.
| ipsum2 wrote:
| SAM doesn't do open vocabulary i.e. it segments things without
| knowing the name of the object, so you can't ask it to do
| "highlight the grapes", you have to give it an example of a
| grape first.
| stevepotter wrote:
| Try this: https://github.com/luca-medeiros/lang-segment-
| anything
| ipsum2 wrote:
| This uses GroundingDINO for open vocabulary, separate
| model. Useful nonetheless, but means you're running a lot
| of model inference for a single image.
| RugnirViking wrote:
| YOLO is way faster. We used to run both, with YOLO finding
| candidate bounding boxes and SAM segmenting just those.
|
| For what it's worth, YOLO has been a standard in image
| processing for ages at this point, with dozens of variations on
| the algorithm (yolov3, yolov5, yolov6, etc) and this is yet
| another new one. Looks great tho
|
| SAM wouldn't run under 1000ms per frame for most reasonable
| image sizes
| AndrewKemendo wrote:
| We've tested this in our production environment on mobile robots
| (think quadcopter and ground UGV) and it works really nicely
| TechDebtDevin wrote:
| If this is military related, im terrified of the future. Sci-fi
| movies with crazy drones from back when are no longer that
| cute.
| jiggawatts wrote:
| The truly scary part is that it's a straightforward evolution
| from this to 1000 fps hyperspectral sensors.
|
| There will be no hiding from these things and no possibility
| of evasion.
|
| They'll have agility exceeding champion drone pilots and be
| too small to even see or hear until it's far too late.
|
| Life in the Donbass trenches is already hell. We'll find a
| way to make it worse.
| bevenky wrote:
| Is this OSS?
| T-A wrote:
| https://github.com/AILab-CVC/YOLO-World
| fc417fc802 wrote:
| Unclear exactly what you're asking. The linked paper
| describes an algorithm (patent status unclear). That paper
| happens to link to a GPL licensed implementation whose
| authors explicitly solicit business licensing inquiries. The
| related model weights are available on Hugging Face (license
| unclear). Notably the HF readme file contains conflicting
| claims. The metadata specifies apache while the body
| specifies GPL.
|
| https://github.com/AILab-CVC/YOLO-World
|
| https://huggingface.co/spaces/stevengrove/YOLO-
| World/tree/ma...
| silentsea90 wrote:
| Q. Any of you know models that do well at deleting objects from
| an image i.e. inpainting with mask with intention to replace mask
| with background? Whatever I've tried so far leaves a smudge (eg.
| LaMa)
| GaggiX wrote:
| There are plenty of Stable Diffusion based models that are
| capable of inpainting, of course they are heavier to run than
| LaMa.
| pavl wrote:
| This looks so good! Will it be available on replicate?
___________________________________________________________________
(page generated 2025-05-31 23:00 UTC)