Home > Technology peripherals > AI > 3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

WBOY
Release: 2024-03-07 08:40:02
forward
801 people have browsed it

Only 2 pictures, no need to measure any additional data——

Dangdang, a complete 3D bear is there:

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

This new tool called DUSt3R is so popular that it ranked second on the GitHub Hot List not long after it was launched. ##.

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

Netizen actually tested, took two photos, and really reconstructed his kitchen, the whole processIt takes less than 2 seconds!

(In addition to 3D images, it can also provide depth maps, confidence maps and point cloud images)

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

Amazing This friend has to say:

Everyone

Forget about sora first, this is what we can really see and touch.

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

# Experiments show that DUSt3R achieves SOTA in the three tasks of monocular/multi-view depth estimation and relative pose estimation.

The author team

(from the European branch of NAVER LABS Institute of Artificial Intelligence, Aalto University, Finland) ’s “manifesto” is also full of momentum:

We It is to make the world have no difficult 3D visual tasks.

So, how is it done?

“all-in-one”

For the multi-view stereo reconstruction

(MVS) task, the first step is to estimate the camera parameters, including internal and external parameters.

This operation is boring and troublesome, but it is indispensable for subsequent triangulation of pixels in three-dimensional space, and this is an inseparable part of almost all MVS algorithms with better performance.

In the study of this article, the DUSt3R introduced by the author's team adopted a completely different approach.

It

does not require any prior information about camera calibration or viewpoint pose, and can complete dense or unconstrained 3D reconstruction of arbitrary images.

Here, the team formulates the pairwise reconstruction problem as point-plot regression, unifying the monocular and binocular reconstruction situations.

When more than two input images are provided, all pairs of point images are represented into a common reference frame through a simple and effective global alignment strategy.

As shown in the figure below, given a set of photos with unknown camera poses and intrinsic features, DUSt3R outputs a corresponding set of point maps, from which we can directly recover various geometric quantities that are usually difficult to estimate simultaneously. Such as camera parameters, pixel correspondence, depth map, and completely consistent 3D reconstruction effect.

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

(The author reminds that DUSt3R is also applicable to a single input image)

In terms of specific network architecture, DUSt3R is based on

Standard Transformer encoder and decoder, inspired by CroCo (a study on self-supervised pre-training of 3D vision tasks across views), and adopted Simple regression loss training is completed.

As shown in the figure below, the two views of the scene

(I1, I2) are first encoded in Siamese (Siamese) mode using the shared ViT encoder.

The resulting token representation

(F1 and F2) is then passed to two Transformer decoders, which pass the cross attention Information is constantly exchanged.

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

#Finally, the two regression heads output two corresponding point maps and associated confidence maps.

The key point is that both point maps must be represented in the same coordinate system of the first image.

Многозадачность SOTA

В ходе эксперимента сначала оценивается DUST3R на 7 сценах (7 сцен в помещении) и Cambridge Landmarks (8 сцен на открытом воздухе) Наборы данных Производительность на Задача абсолютной оценки позы, индикаторами являются ошибка перевода и ошибка вращения (чем меньше значение, тем лучше) .

Автор заявил, что по сравнению с другими существующими методами сопоставления функций и сквозными методами производительность DUSt3R замечательна.

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

Потому что он никогда не проходил никакого обучения визуальному позиционированию, и, во-вторых, он не сталкивался с изображениями запросов и изображениями базы данных в процессе обучения.

Во-вторых, это задача регрессии позы с несколькими изображениями, выполняемая на 10 случайных кадрах. Результаты. DUST3R добился лучших результатов на обоих наборах данных.

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

В задаче монокулярной оценки глубины DUSt3R также может хорошо обрабатывать сцены в помещении и на открытом воздухе, с производительностью лучше, чем у базовых линий с самоконтролем, и отличается от самых продвинутых базовых линий с контролируемым контролем. . Вверх и вниз.

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

С точки зрения оценки глубины в нескольких ракурсах производительность DUSt3R также выдающаяся.

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

Ниже приведены эффекты 3D-реконструкции, предоставленные двумя группами чиновников. Чтобы вы почувствовали, они ввели только два изображения:

(1 )

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

(2)

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

Реальные измерения пользователей сети: ничего страшного, если два изображения не перекрываются

Да Пользователь сети предоставил DUST3R два изображения без перекрывающегося содержимого, а также за несколько секунд выдал точное 3D-изображение:

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora

# на фото его офис, так что я, должно быть, никогда не видел его на тренировке)

##В ответ некоторые пользователи сети сказали, что это означает, что метода нет. Делайте «объективные измерения» и вместо этого ведите себя как ИИ.

3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about SoraКроме того, некоторым людям интересно

Действителен ли этот метод, когда входные изображения сняты двумя разными камерами

? Некоторые пользователи сети действительно попробовали это, и ответ
да
!
## Портал:

[1]Бумага https://arxiv.org/abs/2312.14132 ############[2]Код https ://github.com/naver/dust3r##################

The above is the detailed content of 3D reconstruction of two pictures in 2 seconds! This AI tool is popular on GitHub, netizens: Forget about Sora. For more information, please follow other related articles on the PHP Chinese website!

Related labels:
source:51cto.com
Statement of this Website
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
Popular Tutorials
More>
Latest Downloads
More>
Web Effects
Website Source Code
Website Materials
Front End Template