Python starts when you choose Run.
From Camera Pixels to a Bird’s-Eye Grid
Depth hypotheses place a pixel along several points on a camera ray. Their weighted projection exposes the effects of calibration and grid resolution.
Pure coordinate geometry and weighted grid accumulation for one synthetic pixel; no camera, neural network, training, or perception benchmark.
The code uses Python 3 and the standard library. Saved output is from the checked CPU run.
width 1.0 pitch 0.0 cells [((1, 8), 0.2), ((2, 10), 0.6), ((2, 12), 0.2)] width 1.0 pitch 5.0 cells [((1, 8), 0.2), ((2, 10), 0.6), ((2, 12), 0.2)] width 1.0 pitch -5.0 cells [((1, 7), 0.2), ((2, 9), 0.6), ((2, 11), 0.2)] width 2.0 pitch 0.0 cells [((0, 4), 0.2), ((1, 5), 0.6), ((1, 6), 0.2)] width 2.0 pitch 5.0 cells [((0, 4), 0.2), ((1, 5), 0.6), ((1, 6), 0.2)] width 2.0 pitch -5.0 cells [((0, 3), 0.2), ((1, 4), 0.6), ((1, 5), 0.2)] depth10_forward_shift 0.0491
Sources
- Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D: https://arxiv.org/abs/2008.05711
Python runs locally in this page. Saved results and figures are visible before execution.