Загрузка видео...

Не удалось загрузить видео

На главную

🥉 3rd Place: Custom Universe Jake Stevens & Mauricio Pereira built a real-time engine that turns a single phone photo into a fully editable, photorealistic 3D scene.

ClaudeDevs's profile picture

ClaudeDevs

527,522 subscribers

51,743 просмотров • 1 месяц назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

ByteDance and Carnegie Mellon researchers just announced PartCrafter This AI turns a single photo into fully editable 3D parts in seconds 10 wild examples:
0:28

ByteDance and Carnegie Mellon researchers just announced PartCrafter This AI turns a single photo into fully editable 3D parts in seconds 10 wild examples:

Min Choi

962,860 просмотров • 1 год назад

3D scene reconstructions by NVIDIA. ArtiFixer - repairs artifacts and extends sparse views via Wan 2.1. - high-fidelity inpainting in occluded regions - gens hundreds of consistent frames in a single pass - 3D Gaussian Splatting for navigable scene reconstruction Makes the 3D environment look photorealistic and fully navigable for VR/AR. It basically turns a broken 3D model into a polished, professional scene.
0:43

3D scene reconstructions by NVIDIA. ArtiFixer - repairs artifacts and extends sparse views via Wan 2.1. - high-fidelity inpainting in occluded regions - gens hundreds of consistent frames in a single pass - 3D Gaussian Splatting for navigable scene reconstruction Makes the 3D environment look photorealistic and fully navigable for VR/AR. It basically turns a broken 3D model into a polished, professional scene.

Wildminder

15,711 просмотров • 1 месяц назад

Built a pipeline that turns any video into 3D + detects human poses in 3D space. opencv + rerun.io 🧵 Running fully local on Apple Silicon.
0:48

Built a pipeline that turns any video into 3D + detects human poses in 3D space. opencv + rerun.io 🧵 Running fully local on Apple Silicon.

Jaskirat Singh

18,447 просмотров • 3 месяцев назад

A 3D samurai incense holder that turns smoke into a scene.
0:29

A 3D samurai incense holder that turns smoke into a scene.

Tansu Yegen

40,377 просмотров • 20 дней назад

The first AI that makes cinema! Not “just a video” Higgsfield WAN Higgsfield AI 🧩 Camera Control turns a single photo into a fully acted, scored, and shot sequence. Think real camera language, real motion, real sound. Cinema assembled from one still:
3:25

The first AI that makes cinema! Not “just a video” Higgsfield WAN Higgsfield AI 🧩 Camera Control turns a single photo into a fully acted, scored, and shot sequence. Think real camera language, real motion, real sound. Cinema assembled from one still:

Alex Patrascu

34,970 просмотров • 10 месяцев назад

Nuwa is live on Virtuals Protocol. A Human Search Engine that turns a single photo or name into instant discovery, profiles, social media, news, and real-world connections. A new layer of human identity in the agent economy.
2:21

Nuwa is live on Virtuals Protocol. A Human Search Engine that turns a single photo or name into instant discovery, profiles, social media, news, and real-world connections. A new layer of human identity in the agent economy.

Virtuals Protocol

205,633 просмотров • 11 месяцев назад

SOMEONE CREATED A TOOL THAT TURNS A SINGLE CHARACTER IMAGE INTO FULLY ANIMATED SPRITE SHEETS IN SECONDS.
0:39

SOMEONE CREATED A TOOL THAT TURNS A SINGLE CHARACTER IMAGE INTO FULLY ANIMATED SPRITE SHEETS IN SECONDS.

0xMarioNawfal

172,706 просмотров • 4 месяцев назад

Higgsfield Plugin for Photoshop is live. 1. Real Time turns your sketch into a finished image as you draw, in any style. 2. Decompose any image into editable layers. 3. Restyle any photo with a preset or prompt. Your whole creative pipeline, inside Photoshop.
0:45

Higgsfield Plugin for Photoshop is live. 1. Real Time turns your sketch into a finished image as you draw, in any style. 2. Decompose any image into editable layers. 3. Restyle any photo with a preset or prompt. Your whole creative pipeline, inside Photoshop.

Higgsfield AI 🧩

277,926 просмотров • 1 месяц назад

Wow. This is insane MetaHumans just got robotic limbs. "A creator Dmitriy Balakhonov built a fully rigged robotic arms that plug directly into MetaHuman Creator." "They support unnatural joint rotation, even beyond human anatomy, while staying fully customizable 👽👀" "It will be delivered as an mhpkg, they drop straight into Unreal Engine pipelines." This turns digital humans into modular systems that can be editable. we’re moving from animating humans to designing them.
0:25

Wow. This is insane MetaHumans just got robotic limbs. "A creator Dmitriy Balakhonov built a fully rigged robotic arms that plug directly into MetaHuman Creator." "They support unnatural joint rotation, even beyond human anatomy, while staying fully customizable 👽👀" "It will be delivered as an mhpkg, they drop straight into Unreal Engine pipelines." This turns digital humans into modular systems that can be editable. we’re moving from animating humans to designing them.

SciTech Era

11,396 просмотров • 3 месяцев назад

Man fits Ferrari F355 V8 engine into custom built motorcycle that holds the proportions of a proper sports bike
0:58

Man fits Ferrari F355 V8 engine into custom built motorcycle that holds the proportions of a proper sports bike

Massimo

51,126 просмотров • 10 месяцев назад

Built a custom tool using Three.js 3RF by Poimandres to convert SVGs to 3D Models in real time ⚡️
0:24

Built a custom tool using Three.js 3RF by Poimandres to convert SVGs to 3D Models in real time ⚡️

Malay Vasa

221,839 просмотров • 2 лет назад

Unreal Engine asset packs are about to be worthless. Tencent just shipped HY-World 2.0. You type one sentence. It outputs a real 3D scene with meshes, point clouds, and 3DGS that drags straight into your game engine. Renders in real time on a consumer GPU. Phone video in, digital twin out, one forward pass. The marketplace economy of selling 3D assets just had its Napster moment.
1:04

Unreal Engine asset packs are about to be worthless. Tencent just shipped HY-World 2.0. You type one sentence. It outputs a real 3D scene with meshes, point clouds, and 3DGS that drags straight into your game engine. Renders in real time on a consumer GPU. Phone video in, digital twin out, one forward pass. The marketplace economy of selling 3D assets just had its Napster moment.

Ihtesham Ali

45,956 просмотров • 2 месяцев назад

Introducing Gizmo, a simulation-authoring agent that turns text and reference images into structured, editable 3D scenes for robotics workflows. We're opening the public beta today.
1:14

Introducing Gizmo, a simulation-authoring agent that turns text and reference images into structured, editable 3D scenes for robotics workflows. We're opening the public beta today.

Shrey Kothari

45,086 просмотров • 10 дней назад

Genie3 generates videos. We generate 𝟯𝗗 𝘄𝗼𝗿𝗹𝗱𝘀 you can actually use. Launching tomorrow — Tencent #HYWorld 2.0, an engine-ready World Model🚀 This isn't a video. It's a real 3D scene, all generated & editable. One image in. A whole 3D world out. 🔥Open-source tomorrow
0:27

Genie3 generates videos. We generate 𝟯𝗗 𝘄𝗼𝗿𝗹𝗱𝘀 you can actually use. Launching tomorrow — Tencent #HYWorld 2.0, an engine-ready World Model🚀 This isn't a video. It's a real 3D scene, all generated & editable. One image in. A whole 3D world out. 🔥Open-source tomorrow

Tengfei Wang

549,646 просмотров • 3 месяцев назад

Introducing Speech Engine. Developers can now turn their existing chat agent into a full voice agent with one prompt. Speech Engine combines our leading speech, transcription, and voice orchestration models into a single pipeline - all custom built to work best together.
0:54

Introducing Speech Engine. Developers can now turn their existing chat agent into a full voice agent with one prompt. Speech Engine combines our leading speech, transcription, and voice orchestration models into a single pipeline - all custom built to work best together.

ElevenLabs

134,449 просмотров • 2 месяцев назад

someone open-sourced a tool that turns any phone video into a full 3D world in real time. you record a walk around your house, drop the mp4 in, and the entire scene comes back as a walkable 996k-point world at 60fps on your local GPU. no cloud. no subscription. runs 100% locally. 100% open source.
0:33

someone open-sourced a tool that turns any phone video into a full 3D world in real time. you record a walk around your house, drop the mp4 in, and the entire scene comes back as a walkable 996k-point world at 60fps on your local GPU. no cloud. no subscription. runs 100% locally. 100% open source.

Superman

813,575 просмотров • 15 дней назад

i built an app that turns any space into a digital clone just by looking at it ray-ban meta glasses → fully navigable 3d world 📍 my friend’s studio in tokyo
0:37

i built an app that turns any space into a digital clone just by looking at it ray-ban meta glasses → fully navigable 3d world 📍 my friend’s studio in tokyo

Martin Maly

75,827 просмотров • 3 месяцев назад

I modded Twitch chat into Elden Ring as a custom summon. Fully voiced in real-time. Miyazaki forgive me.
1:31

I modded Twitch chat into Elden Ring as a custom summon. Fully voiced in real-time. Miyazaki forgive me.

Blurbs

979,093 просмотров • 1 год назад

Digital Artist 3Dystopia unveiled a new photorealistic real-time 3D environment created with RealityCapture, Blender, and Unreal Engine 5. Full video and more info: #unrealengine #UE5 #realitycapture #photogrammetry #3dart #3dmodeling #gamedev #indiedev
0:54

Digital Artist 3Dystopia unveiled a new photorealistic real-time 3D environment created with RealityCapture, Blender, and Unreal Engine 5. Full video and more info: #unrealengine #UE5 #realitycapture #photogrammetry #3dart #3dmodeling #gamedev #indiedev

80 LEVEL

26,839 просмотров • 3 лет назад

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:
1:04

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:

Ziwei Liu

26,953 просмотров • 1 год назад