Hacker News Reader

Comment by mitthrowaway2 | Hacker News Reader

> We compare our reconstruction with state-of-the-art models in single-view 3D reconstruction.

Here they list "GT Mesh", "Ours", "Point-E", and "MCC". Does anyone know what technique "GT mesh" refers to? Is it simply the original mesh that generated the source image?

View on HN

"Ground Truth", the actual mesh

Ground truth

Well honestly the "Ground truth" algorithm seems a lot superior to their method, it has higher fidelity in ALL the examples

“Ground truth” doesn’t refer to a particular algorithm; it refers to the ideal benchmark of what a perfect performance would look like, which they’re grading against.

Ground truth means that a human person created the model.

Not necessarily, could also be synthetic. Google did the same for hand poses in BlazePalm

Ground truth means the original model that the image was generated from.

Haha, I am sorry. I spit my coffee reading this. It is ofc totally OK to not know what ground truth means but the irony was to funny. Yes ground truth will always be superior compared to anything else :)!

Ground truth will always be superior on the "does this match the ground truth?" metric, but that's often just a proxy for output quality and the model will be judged differently once deployed (e.g. "do human users like this?")

That's something to be aware of, especially when you're using convenience data of unknown quality to evaluate your model – many research datasets scraped off the internet with little curation and labeled in a rush by low-paid workers contain a lot of SEO garbage and labeling errors.

I always wanted to meet the team behind Ground Truth. It’s truly remarkable what they have built. Every time AI models show up, these guys outperform them on every metric.

Anyone have any contacts? They seem to be extremely elusive

I read that with the sarcasm that I hope was intended and had a good laugh.

Reply on news.ycombinator.com