Currently my pipeline is as follows- v4l2src → …YUY2… → videoconvert → nvvideoconvert ->…->nveglglesink(max-lateness is set to 1000000000000000000) I’m running DeepStream on a dGPU. There is a significant constant latency for some reason.

Can you try following pipeline: v4l2src → …MJPEG… ->nvv4l2decoder-> nvvideoconvert ->…->nveglglesink or v4l2src → …YUY2… ->videoconvert-> nvvideoconvert ->“video/x-raw(memory:NVMM)”…->nveglglesink