Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

At #CVPR2024: Tactile-augmented Radiance Fields! We probe a scene with a touch sensor and localize each sample within a NeRF. We use diffusion to estimate the tactile signals for the points we didn't touch. w/ Yiming Dou, Antonio Loquercio, Fengyu Yang, Yi Liu

andrewhowens's profile picture

Andrew Owens

2,391 subscribers

38,616 Aufrufe • vor 2 Jahren •via X (Twitter)

Gesundheit & WellnessWissenschaft & TechnologieBildung#CVPR2024
LIVE

Anya Rossi• Live Now

Private livecam show

8 Kommentare

Profilbild von Andrew Owens
Andrew Owensvor 2 Jahren

One fun technical detail: we mount the touch sensor to an RGB-D camera using a selfie stick. Since "vision-based" touch sensors (like DIGIT, GelSight) are based on ordinary cameras, you can use multi-view geometry to estimate the relative pose between both sensors!

Profilbild von Andrew Owens
Andrew Owensvor 2 Jahren

Here's what the capturing procedure looks like.

Profilbild von Andrew Owens
Andrew Owensvor 2 Jahren

Project page: Paper:

Profilbild von Andrew Owens
Andrew Owensvor 2 Jahren

The idea of filling in a touch signal using a generative model is similar to recent work by @ShaohongZhong et al.: which uses robotic proprioception and GANs for object-scale reconstructions.

Profilbild von Yiming Dou
Yiming Douvor 2 Jahren

@antoniloq Thanks Andrew! This project wouldn’t be possible without you advising on every single detail!😀

Profilbild von Igor Gilitschenski
Igor Gilitschenskivor 2 Jahren

@_YimingDou @antoniloq That is amazing work! Congrats everyone!

Profilbild von Andrew Owens
Andrew Owensvor 2 Jahren

@_YimingDou @antoniloq Thanks so much, Igor!

Profilbild von Mustafa
Mustafavor 2 Jahren

@_YimingDou @antoniloq Let's chat. Unfortunately can't dm you

Ähnliche Videos

We visited Paxini in Shenzhen, a company focused on the sense of touch for robots. We got hands-on with their dual-modal Dexter Hands (cameras + tactile sensors) and their Tora Double One humanoid. Humanoid robots will need this touch layer to get truly dexterous. Lena RoboHub🤖
6:50

We visited Paxini in Shenzhen, a company focused on the sense of touch for robots. We got hands-on with their dual-modal Dexter Hands (cameras + tactile sensors) and their Tora Double One humanoid. Humanoid robots will need this touch layer to get truly dexterous. Lena RoboHub🤖

The Humanoid Hub

26,704 Aufrufe • vor 15 Tagen

Today at Meta FAIR we’re announcing three new cutting-edge developments in robotics and touch perception — and releasing a collection of artifacts to empower the community to build on this work. Details on all of this new work ➡️ 1️⃣ Meta Sparsh is the first general-purpose encoder for vision-based tactile sensing that works across many tactile sensors and many tasks. Trained on 460K+ tactile images using self-supervised learning. 2️⃣ Meta Digit 360 is a breakthrough artificial fingertip-based tactile sensor, equipped with 18+ sensing features to deliver detailed touch data with human-level precision and touch-sensing capabilities. 3️⃣ Meta Digit Plexus is a standardized platform for robotic sensor connections and interactions. It provides a hardware-software solution to integrate tactile sensors on a single robot hand and enables seamless data collection, control and analysis over a single cable. The potential impact of expanding capabilities and components like these for the open source community ranges from medical research to supply chain, manufacturing and much more. We’re excited to continue this work with the broader community.
2:35

Today at Meta FAIR we’re announcing three new cutting-edge developments in robotics and touch perception — and releasing a collection of artifacts to empower the community to build on this work. Details on all of this new work ➡️ 1️⃣ Meta Sparsh is the first general-purpose encoder for vision-based tactile sensing that works across many tactile sensors and many tasks. Trained on 460K+ tactile images using self-supervised learning. 2️⃣ Meta Digit 360 is a breakthrough artificial fingertip-based tactile sensor, equipped with 18+ sensing features to deliver detailed touch data with human-level precision and touch-sensing capabilities. 3️⃣ Meta Digit Plexus is a standardized platform for robotic sensor connections and interactions. It provides a hardware-software solution to integrate tactile sensors on a single robot hand and enables seamless data collection, control and analysis over a single cable. The potential impact of expanding capabilities and components like these for the open source community ranges from medical research to supply chain, manufacturing and much more. We’re excited to continue this work with the broader community.

AI at Meta

453,218 Aufrufe • vor 1 Jahr

We just released TAVI -- a robotics framework that combines touch and vision to solve challenging dexterous tasks in under 1 hour. The key? Use human demonstrations to initialize a policy, followed by tactile-based online learning with vision-based rewards. Details in🧵(1/7)
0:35

We just released TAVI -- a robotics framework that combines touch and vision to solve challenging dexterous tasks in under 1 hour. The key? Use human demonstrations to initialize a policy, followed by tactile-based online learning with vision-based rewards. Details in🧵(1/7)

Lerrel Pinto

138,920 Aufrufe • vor 2 Jahren

More beautiful robot hands. This one from Sharpa The hand uses what they call a Dynamic Tactile Array, meaning vision and touch work together and their SaTA (Spatially-anchored Tactile Awareness) algorithm. Each fingertip includes a mini camera and 1,000+ tactile pixels, hitting 0.005N pressure sensitivity. With 22 DOF and 6D force sensing, it can do everything from eggs to tools.
0:59

More beautiful robot hands. This one from Sharpa The hand uses what they call a Dynamic Tactile Array, meaning vision and touch work together and their SaTA (Spatially-anchored Tactile Awareness) algorithm. Each fingertip includes a mini camera and 1,000+ tactile pixels, hitting 0.005N pressure sensitivity. With 22 DOF and 6D force sensing, it can do everything from eggs to tools.

Rohan Paul

41,775 Aufrufe • vor 6 Monaten

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

Touch alone isn’t enough. 🖐️ For robotics, tactile intelligence truly levels up when touch gains spatial meaning. At #ICRA2026, we dove into the core concept behind SaTA: Spatially-anchored Tactile Awareness for robust, dexterous manipulation. Read it here: The challenge is fundamental: a robot shouldn’t just register a touch, it needs to understand exactly where that contact occurs relative to its fingers, joints, and overall hand structure. This is the missing link that turns raw data into precise, real-time adjustments during manipulation. Why does this matter? Because the most complex part of any manipulation task happens when vision is at its least reliable, that final millimeter before insertion, sliding, gripping, or fine-tuning. At Sharpa, this is exactly why we’re building tactile hands and tactile AI in tandem. 🚀 #Sharpa #Robotics #EmbodiedAI #TactileIntelligence #ICRA2026 #DexterousManipulation 📷
0:54

Touch alone isn’t enough. 🖐️ For robotics, tactile intelligence truly levels up when touch gains spatial meaning. At #ICRA2026, we dove into the core concept behind SaTA: Spatially-anchored Tactile Awareness for robust, dexterous manipulation. Read it here: The challenge is fundamental: a robot shouldn’t just register a touch, it needs to understand exactly where that contact occurs relative to its fingers, joints, and overall hand structure. This is the missing link that turns raw data into precise, real-time adjustments during manipulation. Why does this matter? Because the most complex part of any manipulation task happens when vision is at its least reliable, that final millimeter before insertion, sliding, gripping, or fine-tuning. At Sharpa, this is exactly why we’re building tactile hands and tactile AI in tandem. 🚀 #Sharpa #Robotics #EmbodiedAI #TactileIntelligence #ICRA2026 #DexterousManipulation 📷

Sharpa

14,772 Aufrufe • vor 1 Monat

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 Aufrufe • vor 3 Jahren

📢Panoptic Lifting for 3D Scene Understanding with Neural Fields #CVPR23 highlight! Given only posed RGB images of a scene, we optimize a panoptic radiance field representing color, depth, semantics, and instances at any point in space. Vid: Yawar Siddiqui
0:44

📢Panoptic Lifting for 3D Scene Understanding with Neural Fields #CVPR23 highlight! Given only posed RGB images of a scene, we optimize a panoptic radiance field representing color, depth, semantics, and instances at any point in space. Vid: Yawar Siddiqui

Matthias Niessner

29,830 Aufrufe • vor 3 Jahren

🤖🤖🤖 Following RoboVerse, we introduce another work focused on Robotic Tactile Simulation - Taccel Simulator. Taccel is a high-performance simulation platform for vision-based tactile sensors and robots. 🚀🚀🚀 Boosted by Nvidia Warp, we optimize Taccel with highly parallelized simulations and support 900fps simulation with 4k+ parallel training envs. 🤝🤝🤝 Taccel is designed with user-friendly APIs and is easy to use. We open-sourced all the code and documentation. Feel free to try! Project: Preprint: Code:
2:27

🤖🤖🤖 Following RoboVerse, we introduce another work focused on Robotic Tactile Simulation - Taccel Simulator. Taccel is a high-performance simulation platform for vision-based tactile sensors and robots. 🚀🚀🚀 Boosted by Nvidia Warp, we optimize Taccel with highly parallelized simulations and support 900fps simulation with 4k+ parallel training envs. 🤝🤝🤝 Taccel is designed with user-friendly APIs and is easy to use. We open-sourced all the code and documentation. Feel free to try! Project: Preprint: Code:

Siyuan Huang

10,660 Aufrufe • vor 1 Jahr

Teaching robots to learn only from RGB human videos is hard! In Feel The Force (FTF), we teach robots to mimic the tactile feedback humans experience when handling objects. This allows for delicate, touch-sensitive tasks—like picking up a raw egg without breaking it. 🧵👇
1:13

Teaching robots to learn only from RGB human videos is hard! In Feel The Force (FTF), we teach robots to mimic the tactile feedback humans experience when handling objects. This allows for delicate, touch-sensitive tasks—like picking up a raw egg without breaking it. 🧵👇

Lerrel Pinto

70,323 Aufrufe • vor 1 Jahr

I was really impressed by the UMI gripper (Cheng Chi et al.), but a key limitation is that **force-related data wasn’t captured**: humans feel haptic feedback through the mechanical springs, but the robot couldn’t leverage that info, limiting the data’s value for fine-grained manipulation tasks. Led by my amazing students Yolanda Zhu and Binghao Huang, we designed a **portable visuo-tactile gripper** by integrating our dense, flexible tactile arrays with the UMI gripper to enable large-scale in-the-wild data collection. 🔗 We demonstrate **cross-modal representation learning** and **downstream policy learning** on tasks requiring in-hand state estimation (e.g., test tube reorientation) and fine-grained force sensing (e.g., pipette fluid transfer). Key takeaways: - Our flexible tactile arrays store the rich haptic information humans perceive as dense tactile signals. - Portability and robustness are key for in-the-wild data collection; our portable gripper is compact, lightweight, and durable. - Touch provides precise, robust measurements of in-hand object pose, invariant to lighting and viewpoint. - Cross-modal pretraining on large-scale in-the-wild data significantly improves policy robustness and sample efficiency (as shown many times before — and verified again here!). Also check out our previous investigations of dense, flexible tactile grids for understanding human-robot-environment interactions: - Dense tactile glove (Nature ’19): - 3D-ViTac (CoRL ’24):
5:35

I was really impressed by the UMI gripper (Cheng Chi et al.), but a key limitation is that **force-related data wasn’t captured**: humans feel haptic feedback through the mechanical springs, but the robot couldn’t leverage that info, limiting the data’s value for fine-grained manipulation tasks. Led by my amazing students Yolanda Zhu and Binghao Huang, we designed a **portable visuo-tactile gripper** by integrating our dense, flexible tactile arrays with the UMI gripper to enable large-scale in-the-wild data collection. 🔗 We demonstrate **cross-modal representation learning** and **downstream policy learning** on tasks requiring in-hand state estimation (e.g., test tube reorientation) and fine-grained force sensing (e.g., pipette fluid transfer). Key takeaways: - Our flexible tactile arrays store the rich haptic information humans perceive as dense tactile signals. - Portability and robustness are key for in-the-wild data collection; our portable gripper is compact, lightweight, and durable. - Touch provides precise, robust measurements of in-hand object pose, invariant to lighting and viewpoint. - Cross-modal pretraining on large-scale in-the-wild data significantly improves policy robustness and sample efficiency (as shown many times before — and verified again here!). Also check out our previous investigations of dense, flexible tactile grids for understanding human-robot-environment interactions: - Dense tactile glove (Nature ’19): - 3D-ViTac (CoRL ’24):

Yunzhu Li

13,188 Aufrufe • vor 1 Jahr

We have created a list of Cursor rules you can copy and paste into your codebase! Each rule comes with a sample description and glob pattern so that your rule is only applied to the appropriate use case. What other sample rules should we create on top of what we have now?
0:23

We have created a list of Cursor rules you can copy and paste into your codebase! Each rule comes with a sample description and glob pattern so that your rule is only applied to the appropriate use case. What other sample rules should we create on top of what we have now?

Tyler Shukert

129,056 Aufrufe • vor 1 Jahr

My team is hiring in multimodal representation learning. We are working on tactile representations to equip robots with a physical understanding of the world. Bored of scraping disembodied internet data and looking for a new challenge? Apply here:
0:30

My team is hiring in multimodal representation learning. We are working on tactile representations to equip robots with a physical understanding of the world. Bored of scraping disembodied internet data and looking for a new challenge? Apply here:

Mustafa Mukadam

56,704 Aufrufe • vor 2 Jahren

Lovely touch at the end for a brilliant coach and a true gentleman. Shook hands with our whole squad. Thank you Adi Viveash. Without you we wouldn’t be anywhere near where we are right now
0:31

Lovely touch at the end for a brilliant coach and a true gentleman. Shook hands with our whole squad. Thank you Adi Viveash. Without you we wouldn’t be anywhere near where we are right now

Cj Joiner

51,051 Aufrufe • vor 7 Monaten

1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause force — tactile sensing without ever touching a tactile sensor. 4/🔥Want a fully open-source framework — hardware + software — to train your own force-aware learn-from-human-data robot policy? 🚀We introduce ForceBand: Learning Forceful Manipulation with sEMG -- bring force into human videos with sEMG, for force-aware manipulation ⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Force Beyond Vision ✦ Free-Hand Force Sensing ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Low-Cost & Easy-to-Implement Let's squeeze every bit of signal out of human data, and let robots feel the force! 🌐 Website: 📄 Paper: 💻 Code: 🎥 Video: 🧵 1/n
1:48

1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause force — tactile sensing without ever touching a tactile sensor. 4/🔥Want a fully open-source framework — hardware + software — to train your own force-aware learn-from-human-data robot policy? 🚀We introduce ForceBand: Learning Forceful Manipulation with sEMG -- bring force into human videos with sEMG, for force-aware manipulation ⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Force Beyond Vision ✦ Free-Hand Force Sensing ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Low-Cost & Easy-to-Implement Let's squeeze every bit of signal out of human data, and let robots feel the force! 🌐 Website: 📄 Paper: 💻 Code: 🎥 Video: 🧵 1/n

Zhi (Leo) Wang

49,681 Aufrufe • vor 20 Tagen

✈️ As the airline that connects the most countries in the world, we see the world as a whole with all its elements. Just like in 2023, we wish for many years ahead where we create value for everyone we touch and every destination we fly to. #TurkishAirlines #Sustainability
2:09

✈️ As the airline that connects the most countries in the world, we see the world as a whole with all its elements. Just like in 2023, we wish for many years ahead where we create value for everyone we touch and every destination we fly to. #TurkishAirlines #Sustainability

Turkish Airlines

23,426 Aufrufe • vor 2 Jahren

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.
2:32

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.

AK

161,530 Aufrufe • vor 2 Jahren

Today, we honor a WCU tradition with deep significance. Before each home game, Golden Ram football players touch the statue of Michael Horrocks — a beloved WCU alum, Marine, and hero. As we reflect, we remember him and all the lives lost on 9/11. 💜 #NeverForget #September11
0:28

Sensitive content

Today, we honor a WCU tradition with deep significance. Before each home game, Golden Ram football players touch the statue of Michael Horrocks — a beloved WCU alum, Marine, and hero. As we reflect, we remember him and all the lives lost on 9/11. 💜 #NeverForget #September11

West Chester University

33,565 Aufrufe • vor 1 Jahr

First responders are on the scene of a collapse of a construction crane next to a residential high-rise building in Hell’s Kitchen at Tenth Avenue btwn 41st & 40th Streets. We are in touch with the FDNY on and will share any updates as we have them. Video by Jimmy 💃🏻
0:33

First responders are on the scene of a collapse of a construction crane next to a residential high-rise building in Hell’s Kitchen at Tenth Avenue btwn 41st & 40th Streets. We are in touch with the FDNY on and will share any updates as we have them. Video by Jimmy 💃🏻

Erik Bottcher

384,431 Aufrufe • vor 3 Jahren

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