You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
Hi team, thanks for the work on this repo it's quite fantastic. I have everything setup and working perfectly ( detectron2 inference), however I would now like to move to my next step which is animating a character in babylonjs using the joints data I get after running infer_video_d2. I have found a few articles but since the tech is still quite obscure not much info exists, I have found some info around using 3d pose baseline and tried applying that with the data output from this repo but that doesn't work correctly.
If possible could you provide some info/tips around how one would go about applying the output data to animate a character (through bone rotations since that makes the most sense) and additionally shed some light on structure of the output data (order of the joints, scaling factor required and other general info that would be helpful in translating the data to animation).
The text was updated successfully, but these errors were encountered:
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Hi team, thanks for the work on this repo it's quite fantastic. I have everything setup and working perfectly ( detectron2 inference), however I would now like to move to my next step which is animating a character in babylonjs using the joints data I get after running infer_video_d2. I have found a few articles but since the tech is still quite obscure not much info exists, I have found some info around using 3d pose baseline and tried applying that with the data output from this repo but that doesn't work correctly.
If possible could you provide some info/tips around how one would go about applying the output data to animate a character (through bone rotations since that makes the most sense) and additionally shed some light on structure of the output data (order of the joints, scaling factor required and other general info that would be helpful in translating the data to animation).
The text was updated successfully, but these errors were encountered: