Konrad Reczko(@reczko_konrad):Depth-aware light injection in TypeGPU I got a 448x448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dispatches, which is fast enough to use in realtime :D Since the inference is written directly in TypeGPU, I can just feed the depth buffer straight into the lighting pass. It never has to leave the GPU or go through any extra synchronization/interop step Inference, lighting and draw all go through the same command encoder.

Konrad Reczko

@reczko_konrad

Software Engineer @ Software Mansion working on TypeGPU 💜

加入 September 2016

341 正在關注 7.6K 粉絲

Konrad Reczko@reczko_konrad

2026.08.18 11:09

Depth-aware light injection in TypeGPU I got a 448x448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dispatches, which is fast enough to use in realtime :D Since the inference is written directly in TypeGPU, I can just feed the depth buffer straight into the lighting pass. It never has to leave the GPU or go through any extra synchronization/interop step Inference, lighting and draw all go through the same command encoder.