Very interesting, I work in a similar space with diverse cameras and we’ve been using DepthAnything for a while, but I hadn’t seen these new models yet so thanks!
The association model seems like the special sauce, anything more you can share about that? Architecture, inputs and outputs etc. I’m always really interested in unique CV models.
Yeah, DepthAnything (especially DA3) is also really good. The space is moving so quickly, and I always try to keep an eye on the trending HF depth estimation models :D
We frame the association model as an instance segmentation ranking problem. Given a set of freight item segmentations, the question becomes which freight item is most likely being scanned? Our model needs to analyze the pose of the workers, consider multiple frames and map the whole scene to 3D.
This is really cool. Congrats guys. Just because I'm curious, how does the market for this look? How much revenue are you saving your customers with this? Also, surely this is very applicable in many many industries, do you have expansion plans?
Nevertheless, this is awesome and I wish I'd built it :)
thanks!! Our wedge is underbilling in LTL trucking with ~10k relevant cross-docking warehouses across the US and Europe. Carriers lose revenue when shippers understate freight dimensions. We're seeing ~$50k/site/month in recoverable revenue from fixing that alone.
And yes, from there we expand to other industries such as fulfillment and manufacturing. Long term, we will be the CV layer for any warehouse running CCTV.
I fully get this and think its an excellent piece of work. Have you considered interfacing into Warehouse Management in order to provide dimensioned arbitrary pallet heights ? In other words to inform the put away process in warehousing ?
Thanks!! For now, we are focusing on LTL, but improving the put away process in warehousing with better dimensioning data would be a great next use case. thanks for your thoughts!
This is great. If of interest, please consider adding Hubble Networks's scanning gateway SDK to your devices in the future (https://hubble.com). Happy to chat privately about what incentives there may be available especially at logistics warehouses.
1 + 4) If the bbox fit is accurate, we are below 1.5 inch MAE today. Improving bbox fit accuracy is where most of our effort goes. We're confident this gets to <1 inch at full coverage. The tail is bounded by data and model scale, both of which we're actively closing.
2) Not necessarily. Models like MapAnything/MoGe predict calibration params directly and GeoCalib is good for distortion coefficients. We still calibrate manually on-site, but mainly to validate these models actually hold up in real warehouses and collect our own calibration training data. We are confident the future is calibration-free.
3) carriers lose money every day because shippers understate dimensions and LTL is priced by volume. Every understated shipment is lost revenue. Thats the wedge we sre going after.
Very interesting, I work in a similar space with diverse cameras and we’ve been using DepthAnything for a while, but I hadn’t seen these new models yet so thanks!
The association model seems like the special sauce, anything more you can share about that? Architecture, inputs and outputs etc. I’m always really interested in unique CV models.
Yeah, DepthAnything (especially DA3) is also really good. The space is moving so quickly, and I always try to keep an eye on the trending HF depth estimation models :D
We frame the association model as an instance segmentation ranking problem. Given a set of freight item segmentations, the question becomes which freight item is most likely being scanned? Our model needs to analyze the pose of the workers, consider multiple frames and map the whole scene to 3D.
This is really cool. Congrats guys. Just because I'm curious, how does the market for this look? How much revenue are you saving your customers with this? Also, surely this is very applicable in many many industries, do you have expansion plans?
Nevertheless, this is awesome and I wish I'd built it :)
thanks!! Our wedge is underbilling in LTL trucking with ~10k relevant cross-docking warehouses across the US and Europe. Carriers lose revenue when shippers understate freight dimensions. We're seeing ~$50k/site/month in recoverable revenue from fixing that alone.
And yes, from there we expand to other industries such as fulfillment and manufacturing. Long term, we will be the CV layer for any warehouse running CCTV.
I fully get this and think its an excellent piece of work. Have you considered interfacing into Warehouse Management in order to provide dimensioned arbitrary pallet heights ? In other words to inform the put away process in warehousing ?
Thanks!! For now, we are focusing on LTL, but improving the put away process in warehousing with better dimensioning data would be a great next use case. thanks for your thoughts!
This is great. If of interest, please consider adding Hubble Networks's scanning gateway SDK to your devices in the future (https://hubble.com). Happy to chat privately about what incentives there may be available especially at logistics warehouses.
Props for finding a problem that needed to be solved instead of just generating some hype
I appreciate it!
Interesting app of CV in OR.
Questions: - what is the measurement precision?
- do you need calibration? How do you do it in production?
- what it is the root problem you are trying to solve?
- what is your hypothesis about your solution- quantitatively?
1 + 4) If the bbox fit is accurate, we are below 1.5 inch MAE today. Improving bbox fit accuracy is where most of our effort goes. We're confident this gets to <1 inch at full coverage. The tail is bounded by data and model scale, both of which we're actively closing.
2) Not necessarily. Models like MapAnything/MoGe predict calibration params directly and GeoCalib is good for distortion coefficients. We still calibrate manually on-site, but mainly to validate these models actually hold up in real warehouses and collect our own calibration training data. We are confident the future is calibration-free.
3) carriers lose money every day because shippers understate dimensions and LTL is priced by volume. Every understated shipment is lost revenue. Thats the wedge we sre going after.
This is a nice niche problem to solve ! Rooting for you !
Interesting work. Is this something where SAM-3D or it background applies to?
Yes it is. 3D pose estimation and synthetic data generation are example use cases.
is this solution... legally certified for trade?
you may need to look into NTEP approval before this is being used for legal trade... dimensioning is a big deal.
Not yet. But we are working hard to make it happen!
Error Code: SSL_ERROR_RX_RECORD_TOO_LONG
Oh shoot - where did it happen? Can you try again?
Looks nice, I can see many nice things to use this kind of system, especially for an upcoming project of mine for a coffee shop.
[flagged]
[flagged]