Loading video...

Video Failed to Load

Go Home

Depth-aware light injection in VisionCamera This runs Depth- (DINOv2) and Hand-detection (Apple VN) for 448x336 Frames in less than 25ms, then zero-copy renders lighting/shadows with react-native-webgpu - I felt like Tony Stark while moving the invisible light around 🦸🏻‍♂️

mrousavy's profile picture

Marc

21,512 subscribers

105,903 views • 2 months ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Announcing 𝚛𝚎𝚊𝚌𝚝-𝚗𝚊𝚝𝚒𝚟𝚎-𝚗𝚒𝚝𝚛𝚘-𝚣𝚡𝚒𝚗𝚐 - up to 10x faster Barcode detection for React Native and VisionCamera! 🍾
0:11

Announcing 𝚛𝚎𝚊𝚌𝚝-𝚗𝚊𝚝𝚒𝚟𝚎-𝚗𝚒𝚝𝚛𝚘-𝚣𝚡𝚒𝚗𝚐 - up to 10x faster Barcode detection for React Native and VisionCamera! 🍾

Margelo

100,132 views • 2 months ago

Sheer fabric with light transmission. Cloth physics that responds to wind. Depth-of-field compositing. Physically-based lighting - all rendered live in the browser.
0:14

Sheer fabric with light transmission. Cloth physics that responds to wind. Depth-of-field compositing. Physically-based lighting - all rendered live in the browser.

Kimi.ai

13,735 views • 6 months ago

.Laurids 🇪🇺🇺🇦🇵🇸 and I rebuilt Doodle Jump in React Native — the main game loop runs in a Reanimated useFrameCallback(), and everything renders using Skia. Runs pretty smooth! 🤩
0:16

.Laurids 🇪🇺🇺🇦🇵🇸 and I rebuilt Doodle Jump in React Native — the main game loop runs in a Reanimated useFrameCallback(), and everything renders using Skia. Runs pretty smooth! 🤩

Marc

131,232 views • 1 year ago

Seedance 2.0 in native 4K. Best-in-class particle physics, lighting fidelity, depth of scale, and shadow detail. The best model for cinematic storytelling.
0:15

Seedance 2.0 in native 4K. Best-in-class particle physics, lighting fidelity, depth of scale, and shadow detail. The best model for cinematic storytelling.

Higgsfield AI 🧩

47,620 views • 4 months ago

Realtime hand detection via a custom VisionCamera Frame Processor Plugin running MediaPipe in Swift/Kotlin, then rendering in JS via Skia:
0:10

Realtime hand detection via a custom VisionCamera Frame Processor Plugin running MediaPipe in Swift/Kotlin, then rendering in JS via Skia:

Marc

10,935 views • 6 months ago

Previewing one of the new features I'm building for Three Blocks: Making multi-angle object photography interactive: rotate and explore it in real time. Views and depth are streamed as compact video atlases, decoded with WebCodecs, then depth-warped and blended in WebGPU.
0:14

Previewing one of the new features I'm building for Three Blocks: Making multi-angle object photography interactive: rotate and explore it in real time. Views and depth are streamed as compact video atlases, decoded with WebCodecs, then depth-warped and blended in WebGPU.

Renaud

19,540 views • 3 months ago

This is an object detector model running in React Native VisionCamera. I am looping through all the output data and drawing red boxes using simple JavaScript - even the model can be hotswapped! All of this while still running at more than 60 FPS 🤯 - no more native code!!
0:15

This is an object detector model running in React Native VisionCamera. I am looping through all the output data and drawing red boxes using simple JavaScript - even the model can be hotswapped! All of this while still running at more than 60 FPS 🤯 - no more native code!!

Marc

93,961 views • 3 years ago

Depth Anything V2 is a total beast for real-time 3D. Built a website that hits 30fps+ depth reconstructions from a single camera feed, extruding 12k voxels via WebGPU. Pure ML running local Vision Transformers with Three.js and zero backend lag. Lmk in the comments if you want a copy! 🙌 Experience and music made with AI in Omma AI (tool by Spline).
0:15

Depth Anything V2 is a total beast for real-time 3D. Built a website that hits 30fps+ depth reconstructions from a single camera feed, extruding 12k voxels via WebGPU. Pure ML running local Vision Transformers with Three.js and zero backend lag. Lmk in the comments if you want a copy! 🙌 Experience and music made with AI in Omma AI (tool by Spline).

Gábor Pribék

142,791 views • 6 months ago

Featuring next-level performance, long battery life, and our first-ever variable aperture for better low-light photography and greater depth of field.
0:15

Featuring next-level performance, long battery life, and our first-ever variable aperture for better low-light photography and greater depth of field.

Apple

18,800,554 views • 1 month ago

Featuring next-level performance, long battery life and our first-ever variable aperture for better low-light photography and greater depth of field.
0:15

Featuring next-level performance, long battery life and our first-ever variable aperture for better low-light photography and greater depth of field.

Apple

4,221,470 views • 2 months ago

Featuring next-level performance, long battery life and our first-ever variable aperture for better low-light photography and greater depth of field.
0:15

Featuring next-level performance, long battery life and our first-ever variable aperture for better low-light photography and greater depth of field.

Apple

14,881,693 views • 2 months ago

What brings life and depth to a drawing? It’s all in the way you shape light and shadow Light direction,✨ occlusion, edge control master the essentials.
0:12

What brings life and depth to a drawing? It’s all in the way you shape light and shadow Light direction,✨ occlusion, edge control master the essentials.

Coloso Global

3,803,125 views • 7 months ago

Today, Roblox is introducing Unified Lighting in Studio, an overhaul to configuring lighting in experiences. This update brings improvements to how lighting scales, while also laying the foundation for many improvements, including increased light ranges + light attenuation.
0:16

Today, Roblox is introducing Unified Lighting in Studio, an overhaul to configuring lighting in experiences. This update brings improvements to how lighting scales, while also laying the foundation for many improvements, including increased light ranges + light attenuation.

Bloxy News

107,085 views • 1 year ago

Border beam effect is now available for Swift and React Native Dynamic colors, 5 types, playground, dark & light mode, zero dependencies
0:17

Border beam effect is now available for Swift and React Native Dynamic colors, 5 types, playground, dark & light mode, zero dependencies

Jakub Antalik

111,230 views • 3 months ago

Grok Imagine running hyper-detailed renders. Real depth and motion consistency. Feathers crisp. Eyes glossy. Jungle light behaving properly. Cute? Yes. Technically stacked? Also yes.
0:10

Grok Imagine running hyper-detailed renders. Real depth and motion consistency. Feathers crisp. Eyes glossy. Jungle light behaving properly. Cute? Yes. Technically stacked? Also yes.

Mario Nawfal

33,100 views • 6 months ago

Path Tracing off vs on in the upcoming 007 First Light. Improved overall lighting detail, reflection accuracy, improved shadows/ambient occlusion (around pillows, etc.) Really looking forward to this game! 😃
0:15

Path Tracing off vs on in the upcoming 007 First Light. Improved overall lighting detail, reflection accuracy, improved shadows/ambient occlusion (around pillows, etc.) Really looking forward to this game! 😃

Jacob Freeman

43,860 views • 6 months ago

Seriously though, React Native apps can be faster than native apps 🔥. I'm making a React Native macOS diffing app that git diffs a folder, and renders and syntax highlights it, in 200ms. And look at that scrolling perf 😍 "React Native is slow" is wrong.
0:10

Seriously though, React Native apps can be faster than native apps 🔥. I'm making a React Native macOS diffing app that git diffs a folder, and renders and syntax highlights it, in 200ms. And look at that scrolling perf 😍 "React Native is slow" is wrong.

Jay Meistrich

21,968 views • 4 months ago

Find the light in the shadows!
0:16

Find the light in the shadows!

˗ˏˋ Shavonne Wong ˎˊ˗ ✨(NFT Asia/Bloom)

15,726 views • 3 years ago

gm So if you ask Nano Banana to make an image into a Depth Map, you get a grayscale image where white=close & black=far Then ask Google AI Studio for an app that turns depth maps into point clouds & lets you control them with hand gestures from webcam blam you’re Tony Stark
0:10

gm So if you ask Nano Banana to make an image into a Depth Map, you get a grayscale image where white=close & black=far Then ask Google AI Studio for an app that turns depth maps into point clouds & lets you control them with hand gestures from webcam blam you’re Tony Stark

Claire Silver 🌸

160,121 views • 11 months ago

Sora 2 can make a depth map, heat map, edge map and segmentation view, simultaneously in a grid. > start with a close up view of a woman in a studio, then split into a 2x2 grid showing in each cell the depth map, heat map, edge detection and segmentation of the scene
0:10

Sora 2 can make a depth map, heat map, edge map and segmentation view, simultaneously in a grid. > start with a close up view of a woman in a studio, then split into a 2x2 grid showing in each cell the depth map, heat map, edge detection and segmentation of the scene

fofr

39,830 views • 1 year ago