Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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.

onirenaud's profile picture

Renaud

12,703 subscribers

19,272 Aufrufe • vor 1 Monat •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Grok 3 is now available on Alchemist AI. Explore the power of Grok in your workflow. As an Ideation Model: Grok 3 turns rough ideas into structured, detailed prompts. It breaks down your intent into clear building blocks, understands nuance and context, and opens up multiple creative directions to explore. As a Generation Model: Grok 3 is built for logic-heavy outputs and multi-step generation. From game mechanics to character systems and worldbuilding, it’s capable of producing full-fledged games and applications with depth and precision.
0:11

Grok 3 is now available on Alchemist AI. Explore the power of Grok in your workflow. As an Ideation Model: Grok 3 turns rough ideas into structured, detailed prompts. It breaks down your intent into clear building blocks, understands nuance and context, and opens up multiple creative directions to explore. As a Generation Model: Grok 3 is built for logic-heavy outputs and multi-step generation. From game mechanics to character systems and worldbuilding, it’s capable of producing full-fledged games and applications with depth and precision.

ALCHEMIST AI 🔮

16,075 Aufrufe • vor 1 Jahr

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 🦸🏻‍♂️
0:19

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 🦸🏻‍♂️

Marc

105,194 Aufrufe • vor 22 Tagen

Introducing A library of interactive UI blocks you can explore, tune, bench, and take into your own projects. Started as a spare-time experiment to see what happens when my design thinking and style meet Claude, pushing further into interactions, components, and the details that make interfaces feel good. Then it became something worth building properly. New blocks every week. More to come. Excited for this 🐐🔥
0:19

Introducing A library of interactive UI blocks you can explore, tune, bench, and take into your own projects. Started as a spare-time experiment to see what happens when my design thinking and style meet Claude, pushing further into interactions, components, and the details that make interfaces feel good. Then it became something worth building properly. New blocks every week. More to come. Excited for this 🐐🔥

Lorenzo Cabra

161,806 Aufrufe • vor 1 Tag

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

142,512 Aufrufe • vor 4 Monaten

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.
0:13

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.

MrNeRF

27,428 Aufrufe • vor 1 Jahr

🤯 Found another great use case for Depth today! I tried recreating this fashion transformation video with my own character, but the original character kept showing up. 🌟 So I switched the reference video to Depth, and it worked way better! Same motion and timing, but now I can use my own character and completely new outfits! Quick workflow in the comments Full Depth workflow in the quoted post 👇
0:11

🤯 Found another great use case for Depth today! I tried recreating this fashion transformation video with my own character, but the original character kept showing up. 🌟 So I switched the reference video to Depth, and it worked way better! Same motion and timing, but now I can use my own character and completely new outfits! Quick workflow in the comments Full Depth workflow in the quoted post 👇

Larus Canus

128,456 Aufrufe • vor 1 Monat

Hi! I'm on the lookout for new collaborations. Happy to offer generative coding workshops (one-on-one are the most fun), help out with building proof-of-concept prototypes, and open to other ideas. And as always, looking for new venues, public spaces, and everything in between🤍
0:15

Hi! I'm on the lookout for new collaborations. Happy to offer generative coding workshops (one-on-one are the most fun), help out with building proof-of-concept prototypes, and open to other ideas. And as always, looking for new venues, public spaces, and everything in between🤍

Marpi Studio

12,856 Aufrufe • vor 2 Jahren

This was all streamed from Bitcoin using Ordinals. The 3D world supports real-time multiplayer interactions, and decentralized land ownership. All this is on-chain on Bitcoin, and as immutable and secure as Bitcoin itself. The weather in the world reacts to Bitcoin fees, clouds are linked to transaction volume, and time in the world is determined by block height. Makes sense for a Bitcoin world. Real-time multiplayer interactions is one of the newest features. This is particularly difficult to do because Bitcoin block times are ~10 minutes. Bitcoin has been around for 17 years, and we're now seeing fascinating new things being built on top of it.
0:11

This was all streamed from Bitcoin using Ordinals. The 3D world supports real-time multiplayer interactions, and decentralized land ownership. All this is on-chain on Bitcoin, and as immutable and secure as Bitcoin itself. The weather in the world reacts to Bitcoin fees, clouds are linked to transaction volume, and time in the world is determined by block height. Makes sense for a Bitcoin world. Real-time multiplayer interactions is one of the newest features. This is particularly difficult to do because Bitcoin block times are ~10 minutes. Bitcoin has been around for 17 years, and we're now seeing fascinating new things being built on top of it.

danny huuep

103,145 Aufrufe • vor 4 Monaten

Interactive web visualisation for a compact multi-layer perceptron trained on the MNIST handwritten digit dataset. Draw a digit, watch activations propagate through the network in 3D, and inspect real-time prediction probabilities. github/DFin/Neural-Network-Visualisation
0:16

Interactive web visualisation for a compact multi-layer perceptron trained on the MNIST handwritten digit dataset. Draw a digit, watch activations propagate through the network in 3D, and inspect real-time prediction probabilities. github/DFin/Neural-Network-Visualisation

tetsuo

23,509 Aufrufe • vor 2 Monaten

We are sharing a major update to our General World Models efforts. GWM Worlds 2 can generate full, interactive, real-time video simulations in one continuous 720p stream at 24 fps and audio at 48000 Hz, responding to your inputs as you explore. It is the first world model that generalizes to arbitrary actions rather than a fixed set of actions or just navigation. Dynamic actions are what actually matter for building gaming and interactive experiences, and for training agents in these simulations. We also introduced WorldPrompt, a way to tell GWM-2 that a world can be split into two kinds of state: what persists and what changes over time. For example: persistent gravity, physics, and light, alongside actions that describe movement, gestures, object interactions, speech, and sound.
0:15

We are sharing a major update to our General World Models efforts. GWM Worlds 2 can generate full, interactive, real-time video simulations in one continuous 720p stream at 24 fps and audio at 48000 Hz, responding to your inputs as you explore. It is the first world model that generalizes to arbitrary actions rather than a fixed set of actions or just navigation. Dynamic actions are what actually matter for building gaming and interactive experiences, and for training agents in these simulations. We also introduced WorldPrompt, a way to tell GWM-2 that a world can be split into two kinds of state: what persists and what changes over time. For example: persistent gravity, physics, and light, alongside actions that describe movement, gestures, object interactions, speech, and sound.

Cristóbal Valenzuela

248,098 Aufrufe • vor 8 Tagen

Timelapse in Google Earth is a zoomable time-lapse video of the planet, showing how it's changed over the years — and it now features new imagery of nearly 40 years of global change. Learn more and explore →
0:10

Timelapse in Google Earth is a zoomable time-lapse video of the planet, showing how it's changed over the years — and it now features new imagery of nearly 40 years of global change. Learn more and explore →

Google

331,505 Aufrufe • vor 3 Jahren

Here's a first look at the NBA's new interactive LED glass court for this year's all-star weekend. The court will display replays and stats directly on the floor and it can also rotate through sponsors in real-time. The future is going to be wild.
0:17

Here's a first look at the NBA's new interactive LED glass court for this year's all-star weekend. The court will display replays and stats directly on the floor and it can also rotate through sponsors in real-time. The future is going to be wild.

Joe Pompliano

1,542,190 Aufrufe • vor 2 Jahren

🤯 Depth can now recreate complex climbing and parkour motion this cleanly! Turned a fast climbing clip into a Depth motion reference, then swapped in a 20-year-old twin-tail student with a backpack while keeping the same concrete structure. Wall contact, weight shifts, jumps, climbing paths, and full-body movement all stay surprisingly clean and consistent! 🌟 Workflow: 1. Pick a reference clip under 15 seconds 2. Convert it to Depth with Depth Anything V2 3. Generate a new character + scene 4. Feed everything into Seedance with the prompt below 🌟 Depth video conversion: You can build a local Depth converter with Codex — prompt in the comments. Dance, martial arts, climbing, parkour, and other complex movements can all be transferred cleanly with Depth! Workflow + Prompt below 👇
0:15

🤯 Depth can now recreate complex climbing and parkour motion this cleanly! Turned a fast climbing clip into a Depth motion reference, then swapped in a 20-year-old twin-tail student with a backpack while keeping the same concrete structure. Wall contact, weight shifts, jumps, climbing paths, and full-body movement all stay surprisingly clean and consistent! 🌟 Workflow: 1. Pick a reference clip under 15 seconds 2. Convert it to Depth with Depth Anything V2 3. Generate a new character + scene 4. Feed everything into Seedance with the prompt below 🌟 Depth video conversion: You can build a local Depth converter with Codex — prompt in the comments. Dance, martial arts, climbing, parkour, and other complex movements can all be transferred cleanly with Depth! Workflow + Prompt below 👇

Larus Canus

116,939 Aufrufe • vor 1 Monat

You can actually interact with the world simulator directly in the browser. 🤖 Here is a quick screen recording (8x speed) of me playing with it: real-time action-conditioned video prediction across rigid objects, deformable objects, rope, and object piles. Try it yourself (no install required): Huge kudos to my student Yixuan Wang for making the interactive demo happen!
0:18

You can actually interact with the world simulator directly in the browser. 🤖 Here is a quick screen recording (8x speed) of me playing with it: real-time action-conditioned video prediction across rigid objects, deformable objects, rope, and object piles. Try it yourself (no install required): Huge kudos to my student Yixuan Wang for making the interactive demo happen!

Yunzhu Li

41,513 Aufrufe • vor 6 Monaten

🔥 AI video creation is finally evolving beyond basic motion prompts. Try out Depth Map Control right here: Historically, the hardest part of the process has been maintaining scene consistency: • camera movement • object placement • spatial relationships Thanks to PixVerse Depth Map Control, you can now grab depth data from a reference video and merge it with a fresh image to explore highly directed video generation. The final outcome? Much smoother camera tracking. Highly cohesive visual scenes. It is a powerful workflow that hands creators actual authority over how their AI visuals shift and flow over time. 🎬
0:10

🔥 AI video creation is finally evolving beyond basic motion prompts. Try out Depth Map Control right here: Historically, the hardest part of the process has been maintaining scene consistency: • camera movement • object placement • spatial relationships Thanks to PixVerse Depth Map Control, you can now grab depth data from a reference video and merge it with a fresh image to explore highly directed video generation. The final outcome? Much smoother camera tracking. Highly cohesive visual scenes. It is a powerful workflow that hands creators actual authority over how their AI visuals shift and flow over time. 🎬

Elara Quinn

12,202 Aufrufe • vor 1 Monat

AI is empowering everything! The new version of DaVinci Resolve added many AI-powered features that are more efficient and precise than ever. One standout is the updated Depth Map, which lets you easily isolate subjects and apply stunning effects with incredible accuracy.
0:13

AI is empowering everything! The new version of DaVinci Resolve added many AI-powered features that are more efficient and precise than ever. One standout is the updated Depth Map, which lets you easily isolate subjects and apply stunning effects with incredible accuracy.

el.cine

62,227 Aufrufe • vor 1 Jahr

Issue 4 of Interfaces just released! This issue is about building an animated sign-in dialog. It covers everything that goes into building it, from the animations to the small but important details. It's one of the most in-depth issues yet, full of code snippets and demos.
0:15

Issue 4 of Interfaces just released! This issue is about building an animated sign-in dialog. It covers everything that goes into building it, from the animations to the small but important details. It's one of the most in-depth issues yet, full of code snippets and demos.

Jakub Krehel

37,748 Aufrufe • vor 3 Monaten