Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🤩 Look at that radiance field and mesh! 🤩 My initial thoughts on 2DGS for Geometrically Accurate Radiance Fields. I am still learning that not ALL scenes work well, but it LOVES drone flights. Tutorial is coming, I promise. #3d #Computervision

jonstephens85's profile picture

Jonathan Stephens

13,274 subscribers

25,949 Aufrufe • vor 2 Jahren •via X (Twitter)

#3d#Computervision
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.
4:28

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

AK

140,624 Aufrufe • vor 3 Jahren

I am still stunned that my Tesla can back itself out of my garage and driveway! 🤩 I love watching it work.
0:29

I am still stunned that my Tesla can back itself out of my garage and driveway! 🤩 I love watching it work.

Martha 🌑🚀

51,003 Aufrufe • vor 3 Monaten

We are excited to share our work “Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones” published in IEEE Transactions on Robotics IEEE Transactions on Robotics (T-RO), which tackles sharp radiance field reconstruction under agile drone motion, where RGB frames are heavily motion-blurred and pose priors become unreliable! 4 years in the making! Code & dataset released! PDF: Code & Dataset: Full Narrated Video: High-speed flight is essential for time- and battery-constrained missions (e.g., inspection, exploration, search & rescue). However, fast motion corrupts visual data with severe motion blur and introduces drift/noise in visual-inertial odometry, making NeRF-based 3D reconstruction particularly brittle. We propose a unified framework that leverages asynchronous #EventCamera streams together with motion-blurred frames to reconstruct high-fidelity radiance fields from agile drone flights. Our key idea is to embed event-image fusion directly into radiance field optimization while jointly refining a shared, continuous-time camera trajectory initialized from event-based VIO. This enables us to recover sharp radiance fields and accurate trajectories without ground-truth supervision during training. We validate our method on synthetic data and on real sequences captured by a drone flying up to 2 m/s. Despite severe blur and noisy pose priors, our method preserves fine scene details and achieves a performance gain of over 50% on real-world data compared to state-of-the-art methods. Kudos to Rong Zou and Marco Cannici! Marco Cannici Reference: Rong Zou*, Marco Cannici*, Davide Scaramuzza Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones IEEE Transactions on Robotics (T-RO), 2026 NCCR Robotics European Research Council (ERC) AUTOASSESS UZH IfI University of Zurich UZH Science Prophesee SynSense UZH Space Hub
1:02

We are excited to share our work “Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones” published in IEEE Transactions on Robotics IEEE Transactions on Robotics (T-RO), which tackles sharp radiance field reconstruction under agile drone motion, where RGB frames are heavily motion-blurred and pose priors become unreliable! 4 years in the making! Code & dataset released! PDF: Code & Dataset: Full Narrated Video: High-speed flight is essential for time- and battery-constrained missions (e.g., inspection, exploration, search & rescue). However, fast motion corrupts visual data with severe motion blur and introduces drift/noise in visual-inertial odometry, making NeRF-based 3D reconstruction particularly brittle. We propose a unified framework that leverages asynchronous #EventCamera streams together with motion-blurred frames to reconstruct high-fidelity radiance fields from agile drone flights. Our key idea is to embed event-image fusion directly into radiance field optimization while jointly refining a shared, continuous-time camera trajectory initialized from event-based VIO. This enables us to recover sharp radiance fields and accurate trajectories without ground-truth supervision during training. We validate our method on synthetic data and on real sequences captured by a drone flying up to 2 m/s. Despite severe blur and noisy pose priors, our method preserves fine scene details and achieves a performance gain of over 50% on real-world data compared to state-of-the-art methods. Kudos to Rong Zou and Marco Cannici! Marco Cannici Reference: Rong Zou*, Marco Cannici*, Davide Scaramuzza Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones IEEE Transactions on Robotics (T-RO), 2026 NCCR Robotics European Research Council (ERC) AUTOASSESS UZH IfI University of Zurich UZH Science Prophesee SynSense UZH Space Hub

Davide Scaramuzza

12,028 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 2 Jahren

Trump on Gavin Newsom: "Gavin Newscum has admitted that he is a—that he has learning disabilities. Honestly, I'm all for people with learning disabilities, but not for my president. I think a president should not have learning disabilities."
0:50

Trump on Gavin Newsom: "Gavin Newscum has admitted that he is a—that he has learning disabilities. Honestly, I'm all for people with learning disabilities, but not for my president. I think a president should not have learning disabilities."

Breaking911

167,567 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 2 Jahren

Asmongold shares his thoughts on the effectiveness of medicine regarding mental health "I am a big believer in the bro science that medicine and that kind of stuff is all fake and the real problems that u have are ur actual life and u can't medicate the material conditions of ur life away..and doing so is bad for u" "I am not a doctor..made all of that up but I'm completely confident that it's accurate"
0:53

Asmongold shares his thoughts on the effectiveness of medicine regarding mental health "I am a big believer in the bro science that medicine and that kind of stuff is all fake and the real problems that u have are ur actual life and u can't medicate the material conditions of ur life away..and doing so is bad for u" "I am not a doctor..made all of that up but I'm completely confident that it's accurate"

yeet

49,320 Aufrufe • vor 2 Monaten

The fact that someone like me ended up where I am is proof that this country can still be great. But that promise doesn’t survive on its own. We have to fight for it.
1:23

The fact that someone like me ended up where I am is proof that this country can still be great. But that promise doesn’t survive on its own. We have to fight for it.

Ruben Gallego

44,633 Aufrufe • vor 9 Monaten

OMGG 🔥 Jimin on Seoul Economic TV for his records on Spotify and Billboard year-end charts 😭🤩 🗣️ : when you look at these records, you can feel that Jimin's music is not just a song that I listen to as a fan, but it is a music that is really loved through region and language.
3:24

OMGG 🔥 Jimin on Seoul Economic TV for his records on Spotify and Billboard year-end charts 😭🤩 🗣️ : when you look at these records, you can feel that Jimin's music is not just a song that I listen to as a fan, but it is a music that is really loved through region and language.

cocojm⁷

41,177 Aufrufe • vor 8 Monaten

Rosé hinting at ‘rosie’ performances 👀 “Well, primarily now when the album comes out, I would say that my next dream is to create performances and stages that I am fully satisfied with. There’s some things I worry about and I have rather high expectations for myself and my work, so whenever I get inspiration for something I immediately want to implement it that way. The dream after that, not sure, but for now it’s good performances of my new songs… Soon, we’ll be able to meet soon. Yeah.. I’ll try and work very hard on that.“
0:47

Rosé hinting at ‘rosie’ performances 👀 “Well, primarily now when the album comes out, I would say that my next dream is to create performances and stages that I am fully satisfied with. There’s some things I worry about and I have rather high expectations for myself and my work, so whenever I get inspiration for something I immediately want to implement it that way. The dream after that, not sure, but for now it’s good performances of my new songs… Soon, we’ll be able to meet soon. Yeah.. I’ll try and work very hard on that.“

젠바 🙈💕

142,214 Aufrufe • vor 1 Jahr

"I respect the racist cinnabon lady." "Not for being racist, but for standing ten toes down on that sh*t!" "You gonna cancel me? I work at cinnabon, I am already canceled." Hard to argue with that. At least she was real and owned it! Although if you look deeper, you will notice that those Somalians were starting ALL of it and let's be honest, deserved what they got!
0:43

"I respect the racist cinnabon lady." "Not for being racist, but for standing ten toes down on that sh*t!" "You gonna cancel me? I work at cinnabon, I am already canceled." Hard to argue with that. At least she was real and owned it! Although if you look deeper, you will notice that those Somalians were starting ALL of it and let's be honest, deserved what they got!

AmericanPapaBear™

179,952 Aufrufe • vor 8 Monaten

“I am for Nigeria and I am for Africa that’s my root and I’ll promote it with every opportunity I gat. What you see on tv about Nigeria/Africa is not all there is, it is far better than that. -Wizkid
1:43

“I am for Nigeria and I am for Africa that’s my root and I’ll promote it with every opportunity I gat. What you see on tv about Nigeria/Africa is not all there is, it is far better than that. -Wizkid

Arthur🇳🇬🇬🇧🇸🇳

138,187 Aufrufe • vor 1 Jahr

I don’t think this is accurate but it puts into perspective how long Kinger was alone for and how after all that he’s still standing which is insane
0:53

I don’t think this is accurate but it puts into perspective how long Kinger was alone for and how after all that he’s still standing which is insane

🌸Ember🌸

677,387 Aufrufe • vor 1 Monat

A friend asked me recently what I'm proudest of in my career. Well, I try not to be prideful, but I sure am grateful. I still can't believe that one record I made in college could start it all… and that for four and a half years, I had songs on the charts. Week after week, never a break. Nobody's ever come close to that streak, and I just thank God it was me. Now at 91, I've recorded over 2,700 songs! And by His grace, I'm still making music. And yes, still landing on the charts. #PatBoone #GratefulHeart #72YearsOfMusic #StillSinging #FaithAndMusic
1:02

A friend asked me recently what I'm proudest of in my career. Well, I try not to be prideful, but I sure am grateful. I still can't believe that one record I made in college could start it all… and that for four and a half years, I had songs on the charts. Week after week, never a break. Nobody's ever come close to that streak, and I just thank God it was me. Now at 91, I've recorded over 2,700 songs! And by His grace, I'm still making music. And yes, still landing on the charts. #PatBoone #GratefulHeart #72YearsOfMusic #StillSinging #FaithAndMusic

ThePatBoone

20,211 Aufrufe • vor 5 Monaten

" I decided to help my mother sell on Sunday some people videoed me and posted it on TikTok, does it mean because I am grown up i should not help my mother again but if I decided to stand at junction now, is that what you all want?"
1:30

" I decided to help my mother sell on Sunday some people videoed me and posted it on TikTok, does it mean because I am grown up i should not help my mother again but if I decided to stand at junction now, is that what you all want?"

ÓMÒÉLÉRÍNJÁRÉ

98,244 Aufrufe • vor 6 Monaten

I am so sorry for missing yesterday letting everyone down. I am completely ashamed of myself & deserve zero sympathy. It is an honor to work here & my actions did not reflect that. I am gutted but nobody’s fault but mine.
3:34

I am so sorry for missing yesterday letting everyone down. I am completely ashamed of myself & deserve zero sympathy. It is an honor to work here & my actions did not reflect that. I am gutted but nobody’s fault but mine.

Mintzy

4,265,191 Aufrufe • vor 1 Jahr