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.
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.
nao sei se existe expressão mais bonita do que "radio peão": a fofoca no mundo corporativo é tão POTENTE que tem uma expressão só pra ela. isso é muito bonito. é o reconhecimento do trabalhador brasileiro
This is free advice from an expensive psychologist.
If you're an anxious person, do everything for fun. Go to a job interview for fun. Submit documents for fun. Start a blog for fun. Anxiety feeds on importance. Don't make everything a matter of life and death.
não consigo entrar nessa de "não seja amigo de pessoas do trabalho"
sei que tem pessoas que fingem, puxam tapete e teatralizam
mas to ok com isso, aceito o risco em troca do ônus de ser eu mesmo na medida do possível, de ser humano com os outros, ser legal e útil ao mesmo tempo