正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Come to our #SIGGRAPH2026 talk today: Our method turns existing 3D objects into multi-touch sensors, without modifying the interior. From a scan, we sample surface-intrinsic curves that conform to mutual-cap layouts, and optimize their intersections for coverage & fabrication.

Christian Holz

2,586 subscribers

53,043 次观看 • 3 个月前 •via X (Twitter)

科学技术教育 #SIGGRAPH2026

Anya Rossi• Live Now

Private livecam show

19 条评论

Christian Holz 的头像

Christian Holz3 个月前

Our method formulates sensor design as constrained curve routing on a 3D mesh. We generate two layers of surface-intrinsic Tx/Rx curves. Through integer optimization, we select a fabrication-ready subset with uniform coverage under sensing, hardware, and geometry constraints.

Christian Holz 的头像

Christian Holz3 个月前

For fabrication, we unfold the 3D curves into 2D traces, vinyl-cut them from thin Kapton-copper laminate, and use projection guidance for attachment. Our fabricated bunny, mouse, bowl, and spoon achieve mean touch errors of just 0.65-1.6 mm and strong SNR.

Christian Holz 的头像

Christian Holz3 个月前

Andela Ilic, J. Gao, Z. Li, Y. Jiang, R. Schuchert, M. Meier, P. Herholz, C. Holz. Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing. ACM SIGGRAPH 2026. project: arXiv:

LF0 的头像

LF03 个月前

Fun! 1000 great ideas possible with that

Pathetic Brook 的头像

Pathetic Brook3 个月前

This is cool as hell.

Furkan+ 的头像

Furkan+3 个月前

Wow so cool

EsotericHustler 的头像

EsotericHustler3 个月前

this is so cyberpunk (endearing) i can't even.

amy 的头像

amy3 个月前

So cool

sanjay prasad hs 的头像

sanjay prasad hs3 个月前

Oh wow! Can this also detect pressure and other things, not just touch? , But it also probably senses temperature and pressure as well. Then you could probably put this on a lot of stuff for VR and AR tech, right?

Christian Holz 的头像

Christian Holz3 个月前

It also detects pressure right now in the form of increased coupling, but more as an artifact due to our fabrication not by design. It's a clear direction for future work though, exactly for input control in AR/MR.

MrManderly 的头像

MrManderly3 个月前

Very cool. The bunny deserves to have ear rubs too though.

Christian Holz 的头像

Christian Holz3 个月前

challenging for surface routing due to bottleneck in geometry but working on this for v2

Mohamed Sami Zeghdar 的头像

Mohamed Sami Zeghdar3 个月前

Amazing concept, it can add new dimensions to input devices. Have you thought about bringing space mouse capabilities to standard ones via touch?

Frankenbyte 的头像

Frankenbyte3 个月前

Using the projection for sensor print placement is pretty innovative. Nice.

Christian Holz 的头像

Christian Holz3 个月前

Only way we found to make sure the physical sensor precisely works the way the optimized design generated, though there's got to be easier ways to get that part done in the future...

Makr3D 的头像

Makr3D3 个月前

Sampling conductive layouts along the existing surface is a clever way to keep the object geometry intact. The fabrication question is especially interesting: how tolerant is the method of rougher FDM surfaces and layer texture compared with a smooth scanned part?

Jake↑↑↑ 的头像

Jake↑↑↑3 个月前

@lushptr we need the inverse of this for robotic sensing

Christian Holz 的头像

Christian Holz3 个月前

@lushptr Yes! That's the reason we've developed this... as a labeling technique for hand-object contact and force.

Jake↑↑↑ 的头像

Jake↑↑↑3 个月前

@lushptr oh wow, youre going to do very well

相关视频

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

AK

179,061 次观看 • 3 年前

Introducing HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction. We built a multi-camera system and a semi-automatic method for annotating the shape and pose of hands and objects Project page:

Introducing HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction. We built a multi-camera system and a semi-automatic method for annotating the shape and pose of hands and objects Project page:

Yu Xiang

57,588 次观看 • 1 年前

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.

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 次观看 • 3 年前

📢 Intrinsic Image Fusion for Multi-View 3D Material Reconstruction 📢 We combine generative material priors with inverse path tracing: 1) define a parametric texture space 2) fuse monocular predictions across views into consistent textures 3) optimize low-dimensional parameters for physically-grounded reconstructions. The results are relightable PBR textures for 3D scenes: check out the result on a real-world 3D scan from the ScanNet++ dataset! 🌍 🎥 Great work by Peter Kocsis Lukas Höllein!

📢 Intrinsic Image Fusion for Multi-View 3D Material Reconstruction 📢 We combine generative material priors with inverse path tracing: 1) define a parametric texture space 2) fuse monocular predictions across views into consistent textures 3) optimize low-dimensional parameters for physically-grounded reconstructions. The results are relightable PBR textures for 3D scenes: check out the result on a real-world 3D scan from the ScanNet++ dataset! 🌍 🎥 Great work by Peter Kocsis Lukas Höllein!

Matthias Niessner

23,285 次观看 • 10 个月前

Moving Atoms (YC S26) introduces Scan to 3D Model. One click turns any LiDAR or SLAM scan into a segmented, fully editable BIM model, ready to export to Revit, IFC, STEP, USD or Isaac Sim. How it works: 1. Upload your scan. It opens instantly in our 3D viewer, which handles sites up to 5,000,000 sq ft. 2. The engine builds the model. It splits the scan into individual objects, measures each one and generates a native BIM element for every object. 3. Every point is checked. A heatmap shows where the model differs from the scan, and the engine refines each discrepancy until the model matches to within 5 mm.

Moving Atoms (YC S26) introduces Scan to 3D Model. One click turns any LiDAR or SLAM scan into a segmented, fully editable BIM model, ready to export to Revit, IFC, STEP, USD or Isaac Sim. How it works: 1. Upload your scan. It opens instantly in our 3D viewer, which handles sites up to 5,000,000 sq ft. 2. The engine builds the model. It splits the scan into individual objects, measures each one and generates a native BIM element for every object. 3. Every point is checked. A heatmap shows where the model differs from the scan, and the engine refines each discrepancy until the model matches to within 5 mm.

Moving Atoms (YC S26)

16,932 次观看 • 4 天前

We’re introducing intrinsic discovery, a new learning method that allows models to explore and learn from open-ended environments without human supervision. Using intrinsic discovery, we trained a world model that surpasses GPT-5.6 Sol at simulating terminal environments.

We’re introducing intrinsic discovery, a new learning method that allows models to explore and learn from open-ended environments without human supervision. Using intrinsic discovery, we trained a world model that surpasses GPT-5.6 Sol at simulating terminal environments.

Induction Labs

69,224 次观看 • 2 个月前

Our document parsing is really good You can see for yourself with our new feature💫: convert complex PDFs with tables, charts, multi-column layouts to clean markdown/JSON representations through our new clickable templates! 1. We convert complex tables with gaps into clean markdown structures 2. We parse chart + line graphs into interpretable 2d tables Check out LlamaCloud: Come talk to us:

Our document parsing is really good You can see for yourself with our new feature💫: convert complex PDFs with tables, charts, multi-column layouts to clean markdown/JSON representations through our new clickable templates! 1. We convert complex tables with gaps into clean markdown structures 2. We parse chart + line graphs into interpretable 2d tables Check out LlamaCloud: Come talk to us:

Jerry Liu

18,029 次观看 • 8 个月前

EgoLifter Open-world 3D Segmentation for Egocentric Perception In this paper we present EgoLifter, a novel system that can automatically segment scenes captured from egocentric sensors into a complete decomposition of individual 3D objects. The system is specifically

EgoLifter Open-world 3D Segmentation for Egocentric Perception In this paper we present EgoLifter, a novel system that can automatically segment scenes captured from egocentric sensors into a complete decomposition of individual 3D objects. The system is specifically

AK

41,117 次观看 • 2 年前

Our TEDxLondon talk is live for #IWD2023 and we want to talk about feminist liberation & care! Collective care is our strongest tool to build a world without violence. Here’s a short 🧵 on why & you can watch the full talk here:

Our TEDxLondon talk is live for #IWD2023 and we want to talk about feminist liberation & care! Collective care is our strongest tool to build a world without violence. Here’s a short 🧵 on why & you can watch the full talk here:

Level Up

32,263 次观看 • 3 年前

Multi-Agent workflows are the future of AI. OpenAI released new Agent APIs today, and Box built an Agent that combines documents from Box and web search tools to generate answers. Enterprise devs can grab sample code from our GitHub repo to customize with their data.

Multi-Agent workflows are the future of AI. OpenAI released new Agent APIs today, and Box built an Agent that combines documents from Box and web search tools to generate answers. Enterprise devs can grab sample code from our GitHub repo to customize with their data.

Aaron Levie

102,062 次观看 • 1 年前

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Dreaming Tulpa 🥓👑

270,942 次观看 • 3 年前

Imagine if you have an object in hand, you can rotate the object by feeling without even looking. This is what we enable the robot to do now: Rotating without Seeing. Our multi-finger robot hand learns to rotate diverse objects using only touch sensing.

Imagine if you have an object in hand, you can rotate the object by feeling without even looking. This is what we enable the robot to do now: Rotating without Seeing. Our multi-finger robot hand learns to rotate diverse objects using only touch sensing.

Xiaolong Wang

65,293 次观看 • 3 年前

Europe is where we come from. And it’s where we are headed. Because we are Europeans. Today, I addressed the European Parliament on our commitment to a European path. Without Belarus and Ukraine, the EU remains incomplete. This is the future we passionately work towards for our people.

Europe is where we come from. And it’s where we are headed. Because we are Europeans. Today, I addressed the European Parliament on our commitment to a European path. Without Belarus and Ukraine, the EU remains incomplete. This is the future we passionately work towards for our people.

Sviatlana Tsikhanouskaya

54,701 次观看 • 3 年前

"More Doggo than Doggo" Motion scanned @ 60fps. Playing back @ 20fps. Meet our inhouse tech Doggo "Rolo". Since July we've been redesigning our scanning pipeline to work with the new 3D Gaussian Splatting for Real-Time Radiance Field Rendering method from Inria. GS has reignited our passion for 3D/4D scanning. Thank you to the team at Inria IR's AeonX capture system has been designed to capture "Spatial" memories for the future. We've built on a custom version of Inria's Sibr viewer to handle the playback of our multiple processed 4D frames. Our next goal is to optimize the player to be multi-threaded to improve performance over 60fps. GS has reignited our passion for 3D/4D scanning. Thank you to the team at Inria More content to come. #guassiansplatting #ir #aeonx #4d #motionscanning #inria #ximea #idatronic #spatial #youth83

"More Doggo than Doggo" Motion scanned @ 60fps. Playing back @ 20fps. Meet our inhouse tech Doggo "Rolo". Since July we've been redesigning our scanning pipeline to work with the new 3D Gaussian Splatting for Real-Time Radiance Field Rendering method from Inria. GS has reignited our passion for 3D/4D scanning. Thank you to the team at Inria IR's AeonX capture system has been designed to capture "Spatial" memories for the future. We've built on a custom version of Inria's Sibr viewer to handle the playback of our multiple processed 4D frames. Our next goal is to optimize the player to be multi-threaded to improve performance over 60fps. GS has reignited our passion for 3D/4D scanning. Thank you to the team at Inria More content to come. #guassiansplatting #ir #aeonx #4d #motionscanning #inria #ximea #idatronic #spatial #youth83

Infinite-Realities

48,330 次观看 • 3 年前

💙 We are pleased to announce that our Official Formalwear Partner, Suited & Booted, have signed a new and enhanced extension to their existing partnership. 📲 Read More |

💙 We are pleased to announce that our Official Formalwear Partner, Suited & Booted, have signed a new and enhanced extension to their existing partnership. 📲 Read More |

Rangers Football Club

57,268 次观看 • 1 年前

3D arrived to Krea. this new feature lets you turn images into 3D objects and use them in our Real-time tool. free for everyone.

3D arrived to Krea. this new feature lets you turn images into 3D objects and use them in our Real-time tool. free for everyone.

Krea

666,325 次观看 • 1 年前