Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
aaronhertzmann.com
Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
1–10 of 17 posts
Re: Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
#2This was a surprisingly great read, especially Part 2.
Re: Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
#3This is nerd sniping at its best. I immediately fell into the exact trap described in the article. My first immediate reaction: can we represent it with 3D B-splines and solve analytically for tangent rays? My second reaction: humans are pretty good at contouring but we rely on shading and contrast change information a lot. Can we ray trace a bunch of images shaded from different points and apply convolutional nets to get contours? I am pretty sure the second approach is a bit of a chicken and egg problem and the first one has plenty of gotchas, but it was entertaining to think about it.
Re: Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
#4It seems like some of the difficulty comes from trying to calculate the the contour as a vector rather than a raster image.
I would think that a method that only calculates the contour up to a given resolution to be much easier. Rendering the model using location mapped to color and then a post processing step on the image seems like it should be able to do the job.
Re: Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
#5This is nerd sniping at its best. I immediately fell into the exact trap described in the article. My first immediate reaction: can we represent it with 3D B-splines and solve analytically for tangent rays? My second reaction: humans are pretty good at contouring but we rely on shading and contrast change information a lot. Can we ray trace a bunch of images shaded from different points and apply convolutional nets t…
My first thought, not being good with math, or spatial thinking, was just to postprocess the rendered depth map somehow, look for sharp dropoffs, and then do some kind of intersection between the lines from the map and the model
Re: Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
#6This is nerd sniping at its best. I immediately fell into the exact trap described in the article. My first immediate reaction: can we represent it with 3D B-splines and solve analytically for tangent rays? My second reaction: humans are pretty good at contouring but we rely on shading and contrast change information a lot. Can we ray trace a bunch of images shaded from different points and apply convolutional nets t…
Why not simply draw twice, once slightly enlarged with inverted normals, painted black? That's how it was done in the old days.
Re: Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
#7This is nerd sniping at its best. I immediately fell into the exact trap described in the article. My first immediate reaction: can we represent it with 3D B-splines and solve analytically for tangent rays? My second reaction: humans are pretty good at contouring but we rely on shading and contrast change information a lot. Can we ray trace a bunch of images shaded from different points and apply convolutional nets t…
Why not simply draw twice, once slightly enlarged with inverted normals, painted black? That's how it was done in the old days.
That gets you the outline, not the internal contours.
Re: Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
#8Earlier quoted context omitted.
Why not simply draw twice, once slightly enlarged with inverted normals, painted black? That's how it was done in the old days.
That gets you the outline, not the internal contours.
Can you describe what an internal contour is. As far as I can tell from reading the article and linked pages, it's just an edge with a sharp drop off in depth map?
Re: Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
#9Earlier quoted context omitted.
That gets you the outline, not the internal contours.
Can you describe what an internal contour is. As far as I can tell from reading the article and linked pages, it's just an edge with a sharp drop off in depth map?
Consider the pig picture in the article (the one under "The Occluding Contour Problem"). The method proposed by dvh would give the outline, but not the contour of the pig's left ear for example.
Re: Occluding Contour Breakthroughs, Part 1: A Surprisingly Hard Problem
#10Earlier quoted context omitted.
Can you describe what an internal contour is. As far as I can tell from reading the article and linked pages, it's just an edge with a sharp drop off in depth map?
Consider the pig picture in the article (the one under "The Occluding Contour Problem"). The method proposed by dvh would give the outline, but not the contour of the pig's left ear for example.
It would, if the enlargement is not by linear scaling but instead produces a shell around the object at some distance from the surface. The inverted-normal shell of the ear would then occlude the body behind it, while itself being occluded by the slightly smaller ear, producing a contour line.