Loading video...

Video Failed to Load

Go Home

SharedNeRF: Leveraging Photorealistic and View-dependent Rendering for Real-time and Remote Collaboration Abstract (excerpt): When collaborators are remote, coordinating the sharing of views of their physical environment becomes challenging. Video-conferencing tools often do not provide the desired viewpoints for a remote viewer. While RGB-D cameras offer 3D views, they lack...

janusch_patas's profile picture

MrNeRF

16,709 subscribers

10,615 views • 1 year ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

3 Comments

MrNeRF's profile picture
MrNeRF1 year ago

Paper (pdf): Youtube:

Mose Sakashita's profile picture
Mose Sakashita1 year ago

Thank you for sharing the work!:)

N Y 🇵🇸's profile picture
N Y 🇵🇸1 year ago

this is so cool

Related Videos

VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams paper page: Neural Radiance Fields (NeRFs) excel in photorealistically rendering static scenes. However, rendering dynamic, long-duration radiance fields on ubiquitous devices remains challenging, due to data storage and computational constraints. In this paper, we introduce VideoRF, the first approach to enable real-time streaming and rendering of dynamic radiance fields on mobile platforms. At the core is a serialized 2D feature image stream representing the 4D radiance field all in one. We introduce a tailored training scheme directly applied to this 2D domain to impose the temporal and spatial redundancy of the feature image stream. By leveraging the redundancy, we show that the feature image stream can be efficiently compressed by 2D video codecs, which allows us to exploit video hardware accelerators to achieve real-time decoding. On the other hand, based on the feature image stream, we propose a novel rendering pipeline for VideoRF, which has specialized space mappings to query radiance properties efficiently. Paired with a deferred shading model, VideoRF has the capability of real-time rendering on mobile devices thanks to its efficiency. We have developed a real-time interactive player that enables online streaming and rendering of dynamic scenes, offering a seamless and immersive free-viewpoint experience across a range of devices, from desktops to mobile phones.
4:56

VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams paper page: Neural Radiance Fields (NeRFs) excel in photorealistically rendering static scenes. However, rendering dynamic, long-duration radiance fields on ubiquitous devices remains challenging, due to data storage and computational constraints. In this paper, we introduce VideoRF, the first approach to enable real-time streaming and rendering of dynamic radiance fields on mobile platforms. At the core is a serialized 2D feature image stream representing the 4D radiance field all in one. We introduce a tailored training scheme directly applied to this 2D domain to impose the temporal and spatial redundancy of the feature image stream. By leveraging the redundancy, we show that the feature image stream can be efficiently compressed by 2D video codecs, which allows us to exploit video hardware accelerators to achieve real-time decoding. On the other hand, based on the feature image stream, we propose a novel rendering pipeline for VideoRF, which has specialized space mappings to query radiance properties efficiently. Paired with a deferred shading model, VideoRF has the capability of real-time rendering on mobile devices thanks to its efficiency. We have developed a real-time interactive player that enables online streaming and rendering of dynamic scenes, offering a seamless and immersive free-viewpoint experience across a range of devices, from desktops to mobile phones.

AK

38,686 views • 2 years ago

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.
0:42

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

AK

62,768 views • 3 years ago

[SIGGRAPH Asia '24 (TOG)] Representing Long Volumetric Video with Temporal Gaussian Hierarchy Contributions: • We introduce a novel, efficient, and expressive Temporal Gaussian Hierarchy representation for long volumetric video. To our knowledge, our method is the first approach capable of handling minutes of volumetric video data. • We propose a Compact Appearance Model and a new rasterization implementation to facilitate real-time, high-quality dynamic view synthesis while maintaining a compact size. • We propose a system to efficiently model long volumetric videos for the first time and demonstrate state-of-the-art dynamic view synthesis quality on the Neural3DV [Li et al. 2022], ENeRF-Outdoor [Lin et al. 2022], and MobileStage [Xu et al. 2024b] datasets, while also achieving the best rendering speed with reduced training cost and memory usage.
0:53

[SIGGRAPH Asia '24 (TOG)] Representing Long Volumetric Video with Temporal Gaussian Hierarchy Contributions: • We introduce a novel, efficient, and expressive Temporal Gaussian Hierarchy representation for long volumetric video. To our knowledge, our method is the first approach capable of handling minutes of volumetric video data. • We propose a Compact Appearance Model and a new rasterization implementation to facilitate real-time, high-quality dynamic view synthesis while maintaining a compact size. • We propose a system to efficiently model long volumetric videos for the first time and demonstrate state-of-the-art dynamic view synthesis quality on the Neural3DV [Li et al. 2022], ENeRF-Outdoor [Lin et al. 2022], and MobileStage [Xu et al. 2024b] datasets, while also achieving the best rendering speed with reduced training cost and memory usage.

MrNeRF

79,379 views • 1 year ago

FAU Erlangen-Nürnberg presents TRIPS Trilinear Point Splatting for Real-Time Radiance Field Rendering paper page: Point-based radiance field rendering has demonstrated impressive results for novel view synthesis, offering a compelling blend of rendering quality and computational efficiency. However, also latest approaches in this domain are not without their shortcomings. 3D Gaussian Splatting [Kerbl and Kopanas et al. 2023] struggles when tasked with rendering highly detailed scenes, due to blurring and cloudy artifacts. On the other hand, ADOP [R\"uckert et al. 2022] can accommodate crisper images, but the neural reconstruction network decreases performance, it grapples with temporal instability and it is unable to effectively address large gaps in the point cloud. In this paper, we present TRIPS (Trilinear Point Splatting), an approach that combines ideas from both Gaussian Splatting and ADOP. The fundamental concept behind our novel technique involves rasterizing points into a screen-space image pyramid, with the selection of the pyramid layer determined by the projected point size. This approach allows rendering arbitrarily large points using a single trilinear write. A lightweight neural network is then used to reconstruct a hole-free image including detail beyond splat resolution. Importantly, our render pipeline is entirely differentiable, allowing for automatic optimization of both point sizes and positions. Our evaluation demonstrate that TRIPS surpasses existing state-of-the-art methods in terms of rendering quality while maintaining a real-time frame rate of 60 frames per second on readily available hardware. This performance extends to challenging scenarios, such as scenes featuring intricate geometry, expansive landscapes, and auto-exposed footage.
0:21

FAU Erlangen-Nürnberg presents TRIPS Trilinear Point Splatting for Real-Time Radiance Field Rendering paper page: Point-based radiance field rendering has demonstrated impressive results for novel view synthesis, offering a compelling blend of rendering quality and computational efficiency. However, also latest approaches in this domain are not without their shortcomings. 3D Gaussian Splatting [Kerbl and Kopanas et al. 2023] struggles when tasked with rendering highly detailed scenes, due to blurring and cloudy artifacts. On the other hand, ADOP [R\"uckert et al. 2022] can accommodate crisper images, but the neural reconstruction network decreases performance, it grapples with temporal instability and it is unable to effectively address large gaps in the point cloud. In this paper, we present TRIPS (Trilinear Point Splatting), an approach that combines ideas from both Gaussian Splatting and ADOP. The fundamental concept behind our novel technique involves rasterizing points into a screen-space image pyramid, with the selection of the pyramid layer determined by the projected point size. This approach allows rendering arbitrarily large points using a single trilinear write. A lightweight neural network is then used to reconstruct a hole-free image including detail beyond splat resolution. Importantly, our render pipeline is entirely differentiable, allowing for automatic optimization of both point sizes and positions. Our evaluation demonstrate that TRIPS surpasses existing state-of-the-art methods in terms of rendering quality while maintaining a real-time frame rate of 60 frames per second on readily available hardware. This performance extends to challenging scenarios, such as scenes featuring intricate geometry, expansive landscapes, and auto-exposed footage.

AK

45,459 views • 2 years ago

📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢 We use octahedra or tetrahedra as explicit as volumetric building blocks for gradient-based novel view synthesis - as an alternative to 3D Gaussians with discrete, bounded geometry. We show how it can be used to reconstruct photorealistic scenes, and introduce a corresponding differentiable CUDA rasterizer that enables real-time rendering. On real-world scenes, LinPrim achieves comparable image quality with fewer primitives, adding a practical polyhedral option to the 3D scene representation toolbox and expanding the known design space. 🌍 🎥 Amazing work by Nicolas von Lützow!
0:35

📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢 We use octahedra or tetrahedra as explicit as volumetric building blocks for gradient-based novel view synthesis - as an alternative to 3D Gaussians with discrete, bounded geometry. We show how it can be used to reconstruct photorealistic scenes, and introduce a corresponding differentiable CUDA rasterizer that enables real-time rendering. On real-world scenes, LinPrim achieves comparable image quality with fewer primitives, adding a practical polyhedral option to the 3D scene representation toolbox and expanding the known design space. 🌍 🎥 Amazing work by Nicolas von Lützow!

Matthias Niessner

11,413 views • 1 year ago

Chaos and the double pendulum: the configuration space of the double pendulum is a torus (a circle for each angle coordinate) so we can plot the evolution of such a pendulum in two ways: either as a "real pendulum" in physical space, or as a point in configuration space :)
0:37

Chaos and the double pendulum: the configuration space of the double pendulum is a torus (a circle for each angle coordinate) so we can plot the evolution of such a pendulum in two ways: either as a "real pendulum" in physical space, or as a point in configuration space :)

Steve Trettel

149,864 views • 2 years ago

Check out our CVPR 2023 Award Candidate paper, DynIBaR! DynIBaR takes monocular videos of dynamic scenes and renders novel views in space and time. It addresses limitations of prior dynamic NeRF methods, rendering much higher quality views.
1:01

Check out our CVPR 2023 Award Candidate paper, DynIBaR! DynIBaR takes monocular videos of dynamic scenes and renders novel views in space and time. It addresses limitations of prior dynamic NeRF methods, rendering much higher quality views.

Zhengqi Li

86,193 views • 3 years ago

✨ Today we are ready to take AI Graphics to the next level: full volumetric photorealistic NeRF rendering on the web. All in realtime! What you see is what you get for photorealistic 3D is finally here! Starting with the the Fields Editor soon you’ll be able to reshoot in NeRF, not a proxy. Following that, we will bring Luma's NeRF-RT renderer to other tools 🚀
0:26

✨ Today we are ready to take AI Graphics to the next level: full volumetric photorealistic NeRF rendering on the web. All in realtime! What you see is what you get for photorealistic 3D is finally here! Starting with the the Fields Editor soon you’ll be able to reshoot in NeRF, not a proxy. Following that, we will bring Luma's NeRF-RT renderer to other tools 🚀

Luma

841,981 views • 3 years ago

SpecNeRF: Gaussian Directional Encoding for Specular Reflections paper page: Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.
3:41

SpecNeRF: Gaussian Directional Encoding for Specular Reflections paper page: Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.

AK

33,933 views • 2 years ago

THIRD EYE SPIES: PROJECT STARGATE Full Documentary Project Stargate was a CIA program involving the use of remote viewing, pyschic abilities, occult sorcery, and witchcraft similar to those of the ancient mystery schools such as the Rosicrucians etc. using astral projection and various other methods. "Two physicists discover psychic abilities are real only to have their experiments at Stanford co-opted by the CIA and their research silenced by the demands of secrecy. Yet, as both these 'remote viewers' and our audience learn, the 'more you hide something, the more it shines like a beacon in psychic space and this ancient truth can no longer be suppressed." "Project Star gate is the collective name for advanced psychic functioning or Remote viewing experiments and programs that were undertaken for over twenty years to create a trainable, repeatable, operational and if at all possible, accurate method of psychic spying or information gathering for the U.S. Military and intelligence agencies (CIA, NSA, DIA)." Here are some notable remote viewing examples but trust me its much more than this. 1. Ingo Swann’s Experiments: Ingo Swann, a key figure in Operation Stargate, is often cited as one of the most successful remote viewers. In controlled experiments, Swann provided detailed and accurate information about remote locations and objects he had never seen. These experiments played a significant role in gaining initial credibility for remote viewing. 2. Pat Price’s Predictions: Pat Price, another remote viewer involved in Operation Stargate, made several predictions about secret underground installations. Some of these predictions were eerily accurate, such as describing an underground facility at the White Sands Missile Range, which was later confirmed. 3. The SRI Experiments: The Stanford Research Institute conducted numerous experiments to investigate remote viewing. Some of the experiments involved remote viewing of distant or hidden targets, and some of the results were reportedly impressive, though they remain controversial. 4. Lyn Buchanan’s Claims: Lyn Buchanan, a former military remote viewer, has claimed several successful remote viewing missions. One notable claim is his involvement in the search for an SR-71 Blackbird spy plane that had crashed in hostile territory. Further research and documents Inside The CIA’s Project Stargate To Create Remote Viewing Spies
1:55:10

THIRD EYE SPIES: PROJECT STARGATE Full Documentary Project Stargate was a CIA program involving the use of remote viewing, pyschic abilities, occult sorcery, and witchcraft similar to those of the ancient mystery schools such as the Rosicrucians etc. using astral projection and various other methods. "Two physicists discover psychic abilities are real only to have their experiments at Stanford co-opted by the CIA and their research silenced by the demands of secrecy. Yet, as both these 'remote viewers' and our audience learn, the 'more you hide something, the more it shines like a beacon in psychic space and this ancient truth can no longer be suppressed." "Project Star gate is the collective name for advanced psychic functioning or Remote viewing experiments and programs that were undertaken for over twenty years to create a trainable, repeatable, operational and if at all possible, accurate method of psychic spying or information gathering for the U.S. Military and intelligence agencies (CIA, NSA, DIA)." Here are some notable remote viewing examples but trust me its much more than this. 1. Ingo Swann’s Experiments: Ingo Swann, a key figure in Operation Stargate, is often cited as one of the most successful remote viewers. In controlled experiments, Swann provided detailed and accurate information about remote locations and objects he had never seen. These experiments played a significant role in gaining initial credibility for remote viewing. 2. Pat Price’s Predictions: Pat Price, another remote viewer involved in Operation Stargate, made several predictions about secret underground installations. Some of these predictions were eerily accurate, such as describing an underground facility at the White Sands Missile Range, which was later confirmed. 3. The SRI Experiments: The Stanford Research Institute conducted numerous experiments to investigate remote viewing. Some of the experiments involved remote viewing of distant or hidden targets, and some of the results were reportedly impressive, though they remain controversial. 4. Lyn Buchanan’s Claims: Lyn Buchanan, a former military remote viewer, has claimed several successful remote viewing missions. One notable claim is his involvement in the search for an SR-71 Blackbird spy plane that had crashed in hostile territory. Further research and documents Inside The CIA’s Project Stargate To Create Remote Viewing Spies

Redpill Drifter

430,225 views • 1 year ago

Somewhere in the remote corners of the country. A harmony with nature and legacy of generations. #InternationalDayOfYoga
0:41

Somewhere in the remote corners of the country. A harmony with nature and legacy of generations. #InternationalDayOfYoga

Parveen Kaswan, IFS

57,010 views • 22 days ago

.IWC Watches and @Vast have entered into a strategic engineering collaboration to advance the durability and performance of mechanical watches on Earth, and explore their capacity for the environment of space. #IWCwatches
1:51

.IWC Watches and @Vast have entered into a strategic engineering collaboration to advance the durability and performance of mechanical watches on Earth, and explore their capacity for the environment of space. #IWCwatches

Vast

20,702 views • 9 months ago

A physical system, its phase-space state, and the energy function that governs the flow, all linked together. The point of the animation is that these are not three different objects. They are three views of the same dynamics. The pendulum on the left is the physical motion. The curve on the floor is the evolution of its state. The translucent surface shows the energy landscape that organizes that motion.
0:30

A physical system, its phase-space state, and the energy function that governs the flow, all linked together. The point of the animation is that these are not three different objects. They are three views of the same dynamics. The pendulum on the left is the physical motion. The curve on the floor is the evolution of its state. The translucent surface shows the energy landscape that organizes that motion.

Mathelirium

19,655 views • 2 months ago

Phase Space Is the Real Stage of Dynamics. So, Stop Watching the Object and Watch the State. Ordinary Space tells you where something is. Phase Space tells you what state it is in. Position alone is not enough because you also need the variable that tells you where the system is trying to go. In the animation, the left panel shows the particle moving in Ordinary Space, while the right panel shows the same system as a moving point in Phase Space. For one degree of freedom, the state is (x, p) and as time evolves, that state traces a trajectory t ↦ (x(t), p(t)) Instead of thinking of a differential equation as just a formula, Phase Space lets you see it as a flow on the space of states. For this lecture we use ẋ = p ṗ = x − x³ with Hamiltonian H(x,p) = 0.5 p² + 0.25 x⁴ − 0.5 x² #PhaseSpace #DynamicalSystems #NonlinearDynamics #HamiltonianMechanics #Mathematics
0:30

Phase Space Is the Real Stage of Dynamics. So, Stop Watching the Object and Watch the State. Ordinary Space tells you where something is. Phase Space tells you what state it is in. Position alone is not enough because you also need the variable that tells you where the system is trying to go. In the animation, the left panel shows the particle moving in Ordinary Space, while the right panel shows the same system as a moving point in Phase Space. For one degree of freedom, the state is (x, p) and as time evolves, that state traces a trajectory t ↦ (x(t), p(t)) Instead of thinking of a differential equation as just a formula, Phase Space lets you see it as a flow on the space of states. For this lecture we use ẋ = p ṗ = x − x³ with Hamiltonian H(x,p) = 0.5 p² + 0.25 x⁴ − 0.5 x² #PhaseSpace #DynamicalSystems #NonlinearDynamics #HamiltonianMechanics #Mathematics

Mathelirium

30,340 views • 3 months ago

Earth and the Moon appear together in the vastness of space, forming one of the most iconic views in our solar system. Earth shines with its vibrant blue oceans and swirling clouds, while the Moon reflects sunlight as a quiet and distant companion. Despite the distance between them, their connection is powerful, with gravity keeping them bound in a constant relationship. The Moon plays a key role in stabilizing Earth and influencing tides. This view reminds us of the beauty of our cosmic neighborhood and the delicate balance that exists between these two worlds. A simple yet powerful perspective of our place in space. #nasa #space #spacex
0:21

Earth and the Moon appear together in the vastness of space, forming one of the most iconic views in our solar system. Earth shines with its vibrant blue oceans and swirling clouds, while the Moon reflects sunlight as a quiet and distant companion. Despite the distance between them, their connection is powerful, with gravity keeping them bound in a constant relationship. The Moon plays a key role in stabilizing Earth and influencing tides. This view reminds us of the beauty of our cosmic neighborhood and the delicate balance that exists between these two worlds. A simple yet powerful perspective of our place in space. #nasa #space #spacex

Physics & Astronomy Zone

12,822 views • 2 months ago

Behind the scenes of remote camera setup for tomorrow's Falcon Heavy launch of the ViaSat-3 F3 mission. It's been awhile and there will be a lot of lenses ready to catch the moment. for live views of Cape happenings
0:58

Behind the scenes of remote camera setup for tomorrow's Falcon Heavy launch of the ViaSat-3 F3 mission. It's been awhile and there will be a lot of lenses ready to catch the moment. for live views of Cape happenings

Julia Bergeron

51,837 views • 2 months ago

“99% of people can remote view…” That’s the claim. A Remote Viewer explains whether it can actually be learned.
2:55

“99% of people can remote view…” That’s the claim. A Remote Viewer explains whether it can actually be learned.

Julian Dorey

23,873 views • 2 months ago

🇮🇱 𝐍𝐄𝐖: Israel has selected SMARTSHOOTER’s SMASH Hopper Remote Weapon Station. The AI assisted system is designed to detect, track, and engage drones and ground targets from a remote position, and can be deployed on vehicles, fixed sites, and robotic platforms. The move highlights the growing importance of counter drone technology as armed forces worldwide adapt to the increasing role of UAVs on the modern battlefield.
0:34

🇮🇱 𝐍𝐄𝐖: Israel has selected SMARTSHOOTER’s SMASH Hopper Remote Weapon Station. The AI assisted system is designed to detect, track, and engage drones and ground targets from a remote position, and can be deployed on vehicles, fixed sites, and robotic platforms. The move highlights the growing importance of counter drone technology as armed forces worldwide adapt to the increasing role of UAVs on the modern battlefield.

Defence Index

18,079 views • 22 days ago

Tracking Starship Flight 8. A multi view of my remote video cameras and the three cameras I tracked with robotically. 📸 - NSF - NASASpaceflight.com
7:30

Tracking Starship Flight 8. A multi view of my remote video cameras and the three cameras I tracked with robotically. 📸 - NSF - NASASpaceflight.com

D Wise

49,505 views • 1 year ago