Загрузка видео...

Не удалось загрузить видео

На главную

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 просмотров • 1 год назад •via X (Twitter)

Новости и политикаНаука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 6

Фото профиля Gordon Wetzstein
Gordon Wetzstein1 год назад

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

Фото профиля Gordon Wetzstein
Gordon Wetzstein1 год назад

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

Фото профиля Gordon Wetzstein
Gordon Wetzstein1 год назад

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

Фото профиля Gordon Wetzstein
Gordon Wetzstein1 год назад

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

Фото профиля Oliver Wang
Oliver Wang1 год назад

@CVPR No bundle adjustment ?! Nice nice

Фото профиля Rainmaker
Rainmaker2 лет назад

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.

Похожие видео

"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 просмотров • 4 месяцев назад

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 просмотров • 2 лет назад

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 просмотров • 1 год назад

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 просмотров • 1 год назад

🚀 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

125,452 просмотров • 1 год назад

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

168,451 просмотров • 8 месяцев назад

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 просмотров • 1 год назад

#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 просмотров • 2 лет назад

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

2,477,330 просмотров • 2 лет назад

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 просмотров • 5 месяцев назад

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 просмотров • 1 год назад

It’s #SunDay! This week’s (Nov. 28 - Dec. 4) space weather report includes: · 1 X-class flare · 9 M-class flares · 44 coronal mass ejections · 1 geomagnetic storm This video from NASA’s Solar Dynamics Observatory (SDO) shows the week’s activity. This week’s X-class flare, at about 1:23 in the video below, is particularly photogenic because of its location on the Sun’s limb, or edge. This positioning gave SDO a clear view of a suspended strand of solar plasma, known as a prominence, against the blackness of space as it erupted with the flare. More imagery and information about that flare:
3:06

It’s #SunDay! This week’s (Nov. 28 - Dec. 4) space weather report includes: · 1 X-class flare · 9 M-class flares · 44 coronal mass ejections · 1 geomagnetic storm This video from NASA’s Solar Dynamics Observatory (SDO) shows the week’s activity. This week’s X-class flare, at about 1:23 in the video below, is particularly photogenic because of its location on the Sun’s limb, or edge. This positioning gave SDO a clear view of a suspended strand of solar plasma, known as a prominence, against the blackness of space as it erupted with the flare. More imagery and information about that flare:

NASA Space Alerts

27,009 просмотров • 7 месяцев назад

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:
0:50

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,563 просмотров • 9 месяцев назад

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito
0:38

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito

Matthias Niessner

74,698 просмотров • 1 год назад

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)
0:20

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

Stan Szymanowicz

125,888 просмотров • 1 год назад

Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive results on several downstreams (video depth, camera pose) and believe this is a promising step toward feed-forward 4D reconstruction
1:03

Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive results on several downstreams (video depth, camera pose) and believe this is a promising step toward feed-forward 4D reconstruction

Junyi Zhang

131,562 просмотров • 1 год назад

VGGT: Visual Geometry Grounded Transformer TL;DR: Is DUSt3R facing a formidable new rival? Contributions: (1) We introduce VGGT, a large feed-forward transformer that can, given one, a few, or even hundreds of images of a scene, predict all its key 3D attributes - including camera intrinsics and extrinsics, point maps, depth maps, and 3D point tracks - in seconds. (2) We demonstrate that VGGT’s predictions are directly usable, being highly competitive and usually better than those of state-of-the-art methods that use slow post-processing optimization techniques. (3) We also show that when further combined with BA post-processing, VGGT achieves state-of-the-art results across the board, even when compared to methods that specialize in a subset of 3D tasks, often improving quality substantially.
0:28

VGGT: Visual Geometry Grounded Transformer TL;DR: Is DUSt3R facing a formidable new rival? Contributions: (1) We introduce VGGT, a large feed-forward transformer that can, given one, a few, or even hundreds of images of a scene, predict all its key 3D attributes - including camera intrinsics and extrinsics, point maps, depth maps, and 3D point tracks - in seconds. (2) We demonstrate that VGGT’s predictions are directly usable, being highly competitive and usually better than those of state-of-the-art methods that use slow post-processing optimization techniques. (3) We also show that when further combined with BA post-processing, VGGT achieves state-of-the-art results across the board, even when compared to methods that specialize in a subset of 3D tasks, often improving quality substantially.

MrNeRF

29,461 просмотров • 1 год назад

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀 One universal model enables SoTA for: 🔥 Mono Depth Estimation 🔥 Multi-View SfM 🔥 Multi-View Stereo 🔥 Depth Completion 🔥 Registration … and many more possibilities! – plus everything is metric 🎯 We release code for data processing, training, benchmarking & ablations – everything Apache 2.0! Details & Links 👇
1:30

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀 One universal model enables SoTA for: 🔥 Mono Depth Estimation 🔥 Multi-View SfM 🔥 Multi-View Stereo 🔥 Depth Completion 🔥 Registration … and many more possibilities! – plus everything is metric 🎯 We release code for data processing, training, benchmarking & ablations – everything Apache 2.0! Details & Links 👇

Nikhil Keetha

122,791 просмотров • 10 месяцев назад

Today, Generative AI takes its next big step forward. Introducing Gen-1: a new AI model that uses language and images to generate new videos out of existing ones. Sign up for early research access:
1:53

Today, Generative AI takes its next big step forward. Introducing Gen-1: a new AI model that uses language and images to generate new videos out of existing ones. Sign up for early research access:

Runway

2,480,471 просмотров • 3 лет назад

💫It's fascinating that a single feed-forward pass through an LLM can replace a complex rendering pipeline, like Blender! Just feed it 3D shapes, xyz positions, and poses as tokens, and it spits out the image token-by-token. The dual, aka scene reconstruction, is also possible! 👇
0:26

💫It's fascinating that a single feed-forward pass through an LLM can replace a complex rendering pipeline, like Blender! Just feed it 3D shapes, xyz positions, and poses as tokens, and it spits out the image token-by-token. The dual, aka scene reconstruction, is also possible! 👇

Georgia Gkioxari

44,610 просмотров • 1 год назад