![]() I'm an experienced edit assistant on #avidmediacomposer of three years working on BBC programmes. #ai #vfx #animation #film #television #tech Grupo Televisaĭesperately seeking employment. If you haven't already, I would recommend to listen to Allan McKay 's interview with Nikola Todorovic (Co-Founder and CEO at Wonder Dynamics). Despite all of this, I'm amazed to see what the team at Wonder Dynamics have achieved with A.I. Wonder Studio has already implemented a feature to add your own character, so more updates and tests for this app are in the works. For now, my workaround was to do a difference key in Nuke to obtain the alpha for the character to add compression, artifacts, etc, so it feels more integrated to the plate. I have no doubt that in future versions this will be implemented. The Alpha it generates is not for the 3D character but rather for the Clean Plate, so it is not easy to make any further tweaks to the CG in the renders unless you make those modifications using the Blender file. My first test using Wonder Studio (Beta) replacing El Chavo del Ocho with a Bot.Īt the moment, Wonder Studio tools are limited when it comes down to controls for the CG and Clean Plate when working within its platform. Recomiendo esta entrevista de Allan McKay con Nikola Todorovic (Co-Fundador y CEO de Wonder Dynamics). A pesar de esto, es increíble ver lo que Wonder Dynamics ha logrado usando A.I. Wonder Studio acaba de implementar una herramienta para añadir tu propio personaje 3D por lo que vendrán más updates y tests de este app. Por ahora, mi workaround fue hacer un difference key en Nuke y de esa manera obtuve a el alpha del personaje para añadirle compresión, artefactos, etc, para que se integrara mejor en el plate. Estoy seguro que en futuras versiones esto se irá implementando. Incluso el Alpha que te genera, no es del CG sino del Clean Plate por lo que es difícil hacer cualquier modificación en el render a menos que hagas las modificaciones en el archivo de Blender. ![]() Por el momento, Wonder Studio es limitado en los outputs que genera para obtener control del CG y del Clean Plate dentro de su plataforma. Mi primer test usando Wonder Studio (Beta) reemplazando a el Chavo del Ocho con un Bot. Then I would like to know how to fix it.CONVIRTIENDO A “EL CHAVO DEL OCHO” EN “EL CHABOT DEL OCHO” CON A.I. I have some idea why inpainting fails, but I would like to know for sure. With a radius of 50 it inpaints everything with nans. ![]() With a radius of 1 it inpaints almost anything, but the result is shoddy due to the small radius, and it overwrites good data. Inpainted2 = cv2.inpaint(inpainted, m_nans_small_remaining, 1, cv2.INPAINT_NS)Īt last I tried inpainting a dilated m_nans. m_nans_small_remaining = np.isnan(inpainted) & m_nans_small Even two-pixel regions completely surrounded by valid pixels fail to inpaint. This suggests that inpainting does not fail from a lack of paint. Interestingly, if I try to inpaint recursively - inpaint the image above masked with the nans from that image intersected with the original mask - there is no noticeable improvement, even with the smallest radius. A radius of 1 is also too small compared to the area of the regions I want to inpaint. Then I tried the smallest radius possible (1) with m_nans_small and while that inpaints more regions, it fails to fully inpaint the region of interest. The result was identical for the regions I was actually interested in inpainting, m_nans_small. Thinking higher radius caused only nans to be inpainted, I tried again with all nans masked ( m_nans). Then I tried dilating the mask, which led to nans being inpainted. Then I tried increasing the radius to 10 which resulted in nothing being inpainted. ![]() inpainted = cv2.inpaint(input, m_nans_small, 3, cv2.INPAINT_NS) ![]() Now I would like to inpaint the regions above, lets start with radius 3. M_nans_small = np.isin(nans_labelled, labels).astype(np.uint8) Here I select connected regions of nans with areas below an arbitrary threshold: n,nans_labelled,stats,centroids = cv2.connectedComponentsWithStats(m_nans) Here are the nans (white): m_nans = np.isnan(input).astype(np.uint8) I would like to inpaint the smaller connected regions of nan. I have a 100x100 numpy array which is about 47% nans. ![]()
0 Comments
Leave a Reply. |