Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras · HackerPapers discussions

Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras — mentioned by fxtentacle

Wed, 19 Aug 2020 08:00:06 GMT

I strongly disagree! I have seen fantastic results with stereo cameras, colored lights, and self-calibration. For most use cases, it's no problem if your robot will stop for a few seconds, rotate the camera axis around a bit, and then continue. But that appears to be good enough to calibrate the features for tracking things like a reflective and transparent glass jar. As for the precision, I agree that 1cm at 10m distance doesn't work. But 1cm precision at 50cm distance is doable. And for a robot arm, you mainly need the precision when you're close to the object. And yes, I am talking about…

Paper and discussion history. A mention is not an endorsement.

Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras — mentioned by fxtentacle

Tue, 16 Jun 2020 07:54:21 GMT

Wow, that G-GLN paper is really new. Thanks for sharing it :) My first impression is that this will be very challenging to use for many of the people currently using AI in practice, because of the requirement to have a convex and gaussian-distributed result. For example, I currently work on optical flow and the loss functions are usually very jumpy and usually only convex within a few pixels around the correct result. I have seen plenty of modeling errors in optical flow SOTA papers, for example casting a boolean occlusion term so that it can be added to the loss (Won't work, no gradient). I…

Paper and discussion history. A mention is not an endorsement.

Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras — mentioned by m3at

Fri, 16 Aug 2019 03:36:59 GMT

It’s always better to have multiple sensor modalities available. This is the main takeaway. Unsurprising but interesting nonetheless. I'm working in the field and it confirms my experience. However they have a big bias that need to be pointed out: [...] we must be able to annotate this data at extremely high accuracy levels or the perception system’s performance will begin to regress. Since Scale has a suite of data labeling products built for AV developers, [...] Garbage in, garbage out; yes annotation quality matters. But they're neglecting very promising approaches that allow to leverage…

Paper and discussion history. A mention is not an endorsement.

Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras — mentioned by Isinlor

Wed, 24 Apr 2019 11:38:54 GMT

Independent researchers have already proven Musk to be 100% right about LIDAR. Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving https://arxiv.org/abs/1812.07179 3D object detection is an essential task in autonomous driving. Recent techniques excel with highly accurate detection rates, provided the 3D input data is obtained from precise but expensive LiDAR technology. Approaches based on cheaper monocular or stereo imagery data have, until now, resulted in drastically lower accuracies --- a gap that is commonly attributed to poor…

Paper and discussion history. A mention is not an endorsement.