Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing FLARE #CVPR2026 2025 FLARE is a feed-forward model that simultaneously estimates high-quality camera poses, 3D geometry, and appearance from sparse uncalibrated images. 1/4

GordonWetzstein's profile picture

Gordon Wetzstein

5,072 subscribers

29,518 Aufrufe • vor 1 Jahr •via X (Twitter)

Nachrichten & PolitikWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

6 Kommentare

Profilbild von Gordon Wetzstein
Gordon Wetzsteinvor 1 Jahr

Our cascaded learning framework comprises three core components: 1. Camera pose estimation without bundle adjustment 2. Geometry reconstruction 3. Appearance modeling using 3D Gaussians 2/4

Profilbild von Gordon Wetzstein
Gordon Wetzsteinvor 1 Jahr

Transform your room into a 3D model with just a few photos! 📸✨Try it out and see your space come to life! GitHub: 3/4

Profilbild von Gordon Wetzstein
Gordon Wetzsteinvor 1 Jahr

FLARE can also perform photorealistic novel-view synthesis. Lots of results on the project site: 4/4

Profilbild von Gordon Wetzstein
Gordon Wetzsteinvor 1 Jahr

with Shangzhan Zhang, Jianyuan Wang, @YinghaoXu1, @NanXue7, Christian Rupprecht, @XiaoweiZhou5, Yujun Shen

Profilbild von Oliver Wang
Oliver Wangvor 1 Jahr

@CVPR No bundle adjustment ?! Nice nice

Profilbild von Rainmaker
Rainmakervor 2 Jahren

Join me as I put several Machine Learning models head-to-head to see which one can beat the market and deliver strong returns. In this free Substack post I share several models that deliver better returns with much lower drawdown compared to Buy-and-Hold approach.

Ähnliche Videos

"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.
0:38

"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.

Alexandre Morgand

14,839 Aufrufe • vor 4 Monaten

SpatialTrackerV2: unified, end-to-end 3D point tracking model which simultaneously estimates Camera Motion, Consistent Geometry and Pixel-wise 3D Trajectories.
0:35

SpatialTrackerV2: unified, end-to-end 3D point tracking model which simultaneously estimates Camera Motion, Consistent Geometry and Pixel-wise 3D Trajectories.

Bilawal Sidhu

20,346 Aufrufe • vor 11 Monaten

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4
0:37

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4

Gordon Wetzstein

19,210 Aufrufe • vor 2 Jahren

🚀 Speed3R (#CVPR2026): sparse feed-forward 3D reconstruction. 12.4× faster on 1000-view sequences with minimal accuracy loss. Plug-and-play on VGGT, π³, etc. 🔗 📄 💻
0:35

🚀 Speed3R (#CVPR2026): sparse feed-forward 3D reconstruction. 12.4× faster on 1000-view sequences with minimal accuracy loss. Plug-and-play on VGGT, π³, etc. 🔗 📄 💻

Kai Han

11,420 Aufrufe • vor 1 Monat

Feed-forward 3D Gaussians from Visual Geometry Group (VGG) strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page: Code: Arxiv: A 🧵👇
0:27

Feed-forward 3D Gaussians from Visual Geometry Group (VGG) strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page: Code: Arxiv: A 🧵👇

Stan Szymanowicz

26,970 Aufrufe • vor 1 Jahr

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy) 🌐 Project: (1/4)
0:27

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy) 🌐 Project: (1/4)

Hanwen Jiang

69,607 Aufrufe • vor 1 Jahr

🚀 Introducing DiffusionRenderer, a neural rendering engine powered by video diffusion models. 🎥 Estimates high-quality geometry and materials from videos, synthesizes photorealistic light transport, enables relighting and material editing with realistic shadows and reflections
2:14

🚀 Introducing DiffusionRenderer, a neural rendering engine powered by video diffusion models. 🎥 Estimates high-quality geometry and materials from videos, synthesizes photorealistic light transport, enables relighting and material editing with realistic shadows and reflections

Zian Wang

125,404 Aufrufe • vor 1 Jahr

Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images TL;DR: Given partially visible objects within images, Amodal3R reconstructs semantically meaningful 3D assets with reasonable geometry and plausible appearance.
1:16

Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images TL;DR: Given partially visible objects within images, Amodal3R reconstructs semantically meaningful 3D assets with reasonable geometry and plausible appearance.

Alexandre Morgand

23,300 Aufrufe • vor 1 Jahr

Exciting news for Flare ☀️ developers 🚀 Introducing the Flare Devs MCP Server for Flare documentation. Another powerful tool alongside our Flare AI skills. Give it a try and let me know what you’re building.
2:40

Exciting news for Flare ☀️ developers 🚀 Introducing the Flare Devs MCP Server for Flare documentation. Another powerful tool alongside our Flare AI skills. Give it a try and let me know what you’re building.

Kristaps Grinbergs

16,973 Aufrufe • vor 3 Monaten

Extremely high detail views of the X class solar flare that just erupted. Still waiting for updated coronagraph images...
0:23

Extremely high detail views of the X class solar flare that just erupted. Still waiting for updated coronagraph images...

SpaceWeatherNews

88,412 Aufrufe • vor 8 Monaten

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:
1:20

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Tencent Hy

168,397 Aufrufe • vor 8 Monaten

Microsoft released Trellis! Trellis is a new 3D model that generates high-quality 3D assets in formats like Radiance Fields, 3D Gaussians, and meshes.
0:36

Microsoft released Trellis! Trellis is a new 3D model that generates high-quality 3D assets in formats like Radiance Fields, 3D Gaussians, and meshes.

Dreaming Tulpa 🥓👑

85,115 Aufrufe • vor 1 Jahr

#SIGGRAPH2024 🏆Best Paper Honorable Mentioned Introducing the magic behind #Rodin ( CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets (1/n) CLAY is 3D #stablediffusion + #ControlNet + #LoRA.
4:18

#SIGGRAPH2024 🏆Best Paper Honorable Mentioned Introducing the magic behind #Rodin ( CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets (1/n) CLAY is 3D #stablediffusion + #ControlNet + #LoRA.

Deemos

30,855 Aufrufe • vor 2 Jahren

Introducing Dream Machine - a next generation video model for creating high quality, realistic shots from text instructions and images using AI. It’s available to everyone today! Try for free here #LumaDreamMachine
0:33

Introducing Dream Machine - a next generation video model for creating high quality, realistic shots from text instructions and images using AI. It’s available to everyone today! Try for free here #LumaDreamMachine

Luma

2,477,223 Aufrufe • vor 2 Jahren

Introducing the Mint 3D asset pack generator. Generate 20 high quality 3D assets from one prompt!
0:56

Introducing the Mint 3D asset pack generator. Generate 20 high quality 3D assets from one prompt!

tamrat

376,221 Aufrufe • vor 28 Tagen

An AVATAR program developed with UE5 that supports connecting to AI motion capture for real-time, high-quality UE animation output. It features a highly flexible character customization system and rich clothing and accessory assets. You can upload images to generate 3D models and quickly obtain high-quality 3D model assets.
1:52

An AVATAR program developed with UE5 that supports connecting to AI motion capture for real-time, high-quality UE animation output. It features a highly flexible character customization system and rich clothing and accessory assets. You can upload images to generate 3D models and quickly obtain high-quality 3D model assets.

CYANPUPPETS

11,542 Aufrufe • vor 5 Monaten

Top Sets for Flare’s in College This Season - Spain Flare - Horns Rip Flare - Iverson Curl Flare - Horns Wedge Flare - Wedge Double Flare Riffle - Horns Touch Flare - Horns Twist Flare - Iverson Misdirection Flare - Ram Ghost Flare - Stack Touch Flare - Stack Ghost Flare - Away Ghost Flare
1:48

Top Sets for Flare’s in College This Season - Spain Flare - Horns Rip Flare - Iverson Curl Flare - Horns Wedge Flare - Wedge Double Flare Riffle - Horns Touch Flare - Horns Twist Flare - Iverson Misdirection Flare - Ram Ghost Flare - Stack Touch Flare - Stack Ghost Flare - Away Ghost Flare

Isaiah Taveras

27,321 Aufrufe • vor 5 Monaten

Novel view synthesis has long been a core challenge in 3D vision. But how much 3D inductive bias is truly needed? —Surprisingly, very little! Introducing "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"—a fully transformer-based approach that enables scalable, generalizable, and fully data-driven novel view synthesis, from sparse posed inputs. 🧵(1/6) Project Page:
0:36

Novel view synthesis has long been a core challenge in 3D vision. But how much 3D inductive bias is truly needed? —Surprisingly, very little! Introducing "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"—a fully transformer-based approach that enables scalable, generalizable, and fully data-driven novel view synthesis, from sparse posed inputs. 🧵(1/6) Project Page:

Haian Jin

114,757 Aufrufe • vor 1 Jahr

Did you know that lens flare in Ocarina of Time is a bunch of transparent circles placed in 3d space between you and the sun?
0:44

Did you know that lens flare in Ocarina of Time is a bunch of transparent circles placed in 3d space between you and the sun?

Daniel Baamonde

754,589 Aufrufe • vor 16 Tagen

Introducing Flare Time Series Oracle v2 More data, delivered faster. Free to query any crypto feeds that are as secure as the network. Now on Flare ☀️ mainnet ☀️
0:28

Introducing Flare Time Series Oracle v2 More data, delivered faster. Free to query any crypto feeds that are as secure as the network. Now on Flare ☀️ mainnet ☀️

Flare ☀️

8,332,132 Aufrufe • vor 1 Jahr