• Content count

  • Joined

  • Last visited

Community Reputation

139 Neutral

About azer.darkblade

  • Rank
  1. It's me again, Actually i still have one more issue. As you can see in the image below. My hand is in front of my chest but as as viewed on the normal calculation result the hand seems connected with my chest. [img][/img]
  2. [quote name='Seabolt' timestamp='1346084441' post='4973815'] This may be fairly random, but I think you and I are working on the same project [img][/img] I've been doing the Kinect graphics for the 360 on a strikingly similar background ;) The approach I used to get fairly good results was to just do a simple downsample to a half size target, leveraging bi-linear filtering. If you need to maintain the size of your normal map as you have it now, this may not work, since it thins out the appendages, but to our 120x90 image it looks great. I also had some really great results by applying a gaussian blur on top of everything. [/quote] Hahaha I see [img][/img] , good luck with your 360 project. mine uses Unity i did a little bit tweak on my bilateral filter and it looks better right now. yes you are right by downsampling and applying gaussian filter, the result is more consistent and less noise, right now i choose not to lose the detail and keep on 320x240 resolution instead. I got depth map and normal map, hey i can add SSAO effect now [img][/img]
  3. Hi, Currently i'm doing some image processing on depth map (using OpenNI and XTion) My depth map size is 320x240 (cannot make it 640x480 due to performance issue since we're developing a game) The image processing should be real-time so it's fully written in fragment shader. I generate normal map using simple cross product of 8 neighbouring pixels [img][/img] Since the depth is noisy, i do a hack, so i calculate the 8 pixels like this [source lang="cpp"]float step = _range/512.0; // 512.0 is tex size float4 top = tex2D(_SubTex, float2(i.uv.x, i.uv.y - step)); float4 right = tex2D(_SubTex, float2(i.uv.x + step, i.uv.y)); //and so on....[/source] i can adjust the _range variable and looking for farther pixels Here's the result (raw depth map, now prepocessing at all) [img][/img] 2nd result (5x5 bilateral filter is applied first) [img][/img] My approach to estimate normal is kinda stupid and i need suggestions to do it in a better way [img][/img] And also i'm considering to apply 5x5 median filter (i've tried 3x3 media filter but it's too small to remove noise) but it will be difficult to use such a huge 5x5 window due to implementation and performance issue
  4. Hi, right now i am doing a post-processing of kinect's depth map. This is, of course, for gaming purpose so i need everything runs in realtime. The game itself will be in HD and as you can guess, the problem is kinect's depth map has row resolution and it wouldn't be good. So i decided to use [url=""]hq4x[/url] to smooth the kinect's depth map since this filtering is very good on binary image. Here's my steps:[list=1] [*]My depth map resolution is only 320x240 (it's a sufficient resolution for gesture tracking, higher resolution may cause performance problem) [*]Segment user's body only (this is very easy using user mask from OpenNI) [*]I am using texture buffer and for speed consideration, the buffer should be power-of-two which is 512x512 (i don't want to cut my depth map so 512 is decided as the higher-nearest power-of-two). [*]Then the 320x240 depth image is downsampled to 80x60 so when it's applied on hq4x the resolution is back to 320x240 and it's fit to 512x512 texture buffer [*]Apply hq2x upsampling on 80x60 image [/list] Here's my input: [img][/img] And this is my output: [img][/img] As you can see, hq4x does pretty well and the result is very good but there's an issue, the resulted image still has sharp curvatures on the edge. What i want look like this: [img][/img] Currently i am stuck with this problem and i'm still thinking how to improve the result. Actually, I have an idea to do morphological erosion (or dilation) first, anyway i need to do research again Perhaps anyone here has another idea Thanks !