@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 dis…

X AI KOLs Timeline News

Summary

A developer achieved real-time monocular depth estimation by optimizing a 448x448 model to run at ~8 ms on an M4 Pro using TypeGPU, allowing seamless GPU integration for depth-aware lighting.

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.
Original Article
View Cached Full Text

Cached at: 08/18/26, 02:36 PM

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.

Similar Articles

@yoheinakajima: this stuff is so cool

X AI KOLs Following

Marc demonstrates depth-aware light injection in VisionCamera using DINOv2 and Apple Vision framework, enabling real-time rendering with react-native-webgpu.

chenxwh/depth-anything-v2

Replicate Explore

Depth Anything V2 is a monocular depth estimation model that significantly outperforms V1 in fine-grained details and robustness, offering faster inference and higher accuracy than SD-based models. It is available on Replicate under varying licenses.

@Snixtp: DeepSeek V4 Flash on a single RTX Pro 6000?

X AI KOLs Following

DeepSeek V4 Flash GGUF quantizations have been released by antirez, enabling the model to run on single GPUs like the RTX Pro 6000 and Macs with 128GB+ RAM. The quantized files are available on Hugging Face with instructions for the DS4 inference engine.