We just released AnySense, an iPhone app for effortless data acquisition and streaming for robotics. We leverage Apple’s development frameworks to record and stream:
1. RGBD + Pose data
2. Audio from the mic or custom contact microphones
3. Seamless Bluetooth integration for external sensors
1. RGBD + Pose data
2. Audio from the mic or custom contact microphones
3. Seamless Bluetooth integration for external sensors
February 26, 2025 at 3:14 PM
We just released AnySense, an iPhone app for effortless data acquisition and streaming for robotics. We leverage Apple’s development frameworks to record and stream:
1. RGBD + Pose data
2. Audio from the mic or custom contact microphones
3. Seamless Bluetooth integration for external sensors
1. RGBD + Pose data
2. Audio from the mic or custom contact microphones
3. Seamless Bluetooth integration for external sensors
pySLAM: An Open-Source, Modular, and Extensible Framework for SLAM
Luigi Freda
tl;dr: python implementation of a Visual SLAM pipeline, support monocular, stereo and RGBD cameras
github.com/luigifreda/p...
arxiv.org/abs/2502.11955
Luigi Freda
tl;dr: python implementation of a Visual SLAM pipeline, support monocular, stereo and RGBD cameras
github.com/luigifreda/p...
arxiv.org/abs/2502.11955
February 20, 2025 at 9:03 AM
pySLAM: An Open-Source, Modular, and Extensible Framework for SLAM
Luigi Freda
tl;dr: python implementation of a Visual SLAM pipeline, support monocular, stereo and RGBD cameras
github.com/luigifreda/p...
arxiv.org/abs/2502.11955
Luigi Freda
tl;dr: python implementation of a Visual SLAM pipeline, support monocular, stereo and RGBD cameras
github.com/luigifreda/p...
arxiv.org/abs/2502.11955
Keyframe-based Dense Mapping with the Graph of View-Dependent Local Maps
Krzysztof Zielinski, Dominik Belter
tl;dr: RGBD-SLAM from #ICRA2020.
arXiving your old papers is good way to preserve them, please do it.
arxiv.org/abs/2601.08520
Krzysztof Zielinski, Dominik Belter
tl;dr: RGBD-SLAM from #ICRA2020.
arXiving your old papers is good way to preserve them, please do it.
arxiv.org/abs/2601.08520
January 14, 2026 at 8:45 AM
Keyframe-based Dense Mapping with the Graph of View-Dependent Local Maps
Krzysztof Zielinski, Dominik Belter
tl;dr: RGBD-SLAM from #ICRA2020.
arXiving your old papers is good way to preserve them, please do it.
arxiv.org/abs/2601.08520
Krzysztof Zielinski, Dominik Belter
tl;dr: RGBD-SLAM from #ICRA2020.
arXiving your old papers is good way to preserve them, please do it.
arxiv.org/abs/2601.08520
FrontierNet: Learning Visual Cues to Explore
Boyang Sun, Hanzhi Chen, Stefan Leutenegger, Cesar Cadena, @marcpollefeys.bsky.social , Hermann Blum
tl;dr: predict frontier (where we weren't yet) using RGBD and then make a map, and not otherwise.
arxiv.org/abs/2501.04597
Boyang Sun, Hanzhi Chen, Stefan Leutenegger, Cesar Cadena, @marcpollefeys.bsky.social , Hermann Blum
tl;dr: predict frontier (where we weren't yet) using RGBD and then make a map, and not otherwise.
arxiv.org/abs/2501.04597
February 5, 2025 at 3:17 PM
FrontierNet: Learning Visual Cues to Explore
Boyang Sun, Hanzhi Chen, Stefan Leutenegger, Cesar Cadena, @marcpollefeys.bsky.social , Hermann Blum
tl;dr: predict frontier (where we weren't yet) using RGBD and then make a map, and not otherwise.
arxiv.org/abs/2501.04597
Boyang Sun, Hanzhi Chen, Stefan Leutenegger, Cesar Cadena, @marcpollefeys.bsky.social , Hermann Blum
tl;dr: predict frontier (where we weren't yet) using RGBD and then make a map, and not otherwise.
arxiv.org/abs/2501.04597
THEY SHIPPED BACK MY EXTERNAL MONITOR YAYYY also i have anew laptop cooler and rgbd again. my bad
January 31, 2025 at 4:08 PM
THEY SHIPPED BACK MY EXTERNAL MONITOR YAYYY also i have anew laptop cooler and rgbd again. my bad
Putting it all together:
- Create rgbd bodyparts from mesh.
- Link those parts together with stiff pos constraints.
- Playback anim on a duplicated skeleton.
- Link to the duplicates using soft-ish ang/pos constraints.
- Double-spring for smooth root motion following. #gamephysics #indiegamedev
- Create rgbd bodyparts from mesh.
- Link those parts together with stiff pos constraints.
- Playback anim on a duplicated skeleton.
- Link to the duplicates using soft-ish ang/pos constraints.
- Double-spring for smooth root motion following. #gamephysics #indiegamedev
April 11, 2026 at 7:35 AM
Putting it all together:
- Create rgbd bodyparts from mesh.
- Link those parts together with stiff pos constraints.
- Playback anim on a duplicated skeleton.
- Link to the duplicates using soft-ish ang/pos constraints.
- Double-spring for smooth root motion following. #gamephysics #indiegamedev
- Create rgbd bodyparts from mesh.
- Link those parts together with stiff pos constraints.
- Playback anim on a duplicated skeleton.
- Link to the duplicates using soft-ish ang/pos constraints.
- Double-spring for smooth root motion following. #gamephysics #indiegamedev
Scene Coordinate Reconstruction Priors
@wenjingbian.bsky.social @axelbarroso.bsky.social Tommaso Cavallari, Victor Adrian Prisacariu, @ericbrachmann.bsky.social
tl;dr: in title. Depth priors is Laplace around RGBD, and diffusion is point cloud denoising.
arxiv.org/abs/2510.12387
@wenjingbian.bsky.social @axelbarroso.bsky.social Tommaso Cavallari, Victor Adrian Prisacariu, @ericbrachmann.bsky.social
tl;dr: in title. Depth priors is Laplace around RGBD, and diffusion is point cloud denoising.
arxiv.org/abs/2510.12387
October 15, 2025 at 12:38 PM
Scene Coordinate Reconstruction Priors
@wenjingbian.bsky.social @axelbarroso.bsky.social Tommaso Cavallari, Victor Adrian Prisacariu, @ericbrachmann.bsky.social
tl;dr: in title. Depth priors is Laplace around RGBD, and diffusion is point cloud denoising.
arxiv.org/abs/2510.12387
@wenjingbian.bsky.social @axelbarroso.bsky.social Tommaso Cavallari, Victor Adrian Prisacariu, @ericbrachmann.bsky.social
tl;dr: in title. Depth priors is Laplace around RGBD, and diffusion is point cloud denoising.
arxiv.org/abs/2510.12387
Introducing “Gaussian Mapping of Evolving Scenes”! We present an RGBD mapping system with novel view synthesis capabilities that accurately reconstruct scenes that change over time
vladimiryugay.github.io/game/
vladimiryugay.github.io/game/
June 10, 2025 at 12:06 PM
Introducing “Gaussian Mapping of Evolving Scenes”! We present an RGBD mapping system with novel view synthesis capabilities that accurately reconstruct scenes that change over time
vladimiryugay.github.io/game/
vladimiryugay.github.io/game/
I feel we finally reached a point where uncalibrated RGB-only SLAM is getting as viable as the more traditional RGBD, excited to see what will come next :)
December 16, 2024 at 7:36 PM
I feel we finally reached a point where uncalibrated RGB-only SLAM is getting as viable as the more traditional RGBD, excited to see what will come next :)
GaME: Gaussian Mapping for Evolving Scenes
RGBD 数据流（含深度信息的视频）转 3D高斯溅射场景重建模型
- 能适应一定程度的场景变换，如：重建了厨房后，对卧室进行了扫描，随后又回到厨房。这期间，有人移动了椅子并在厨房里加了一张桌子。
项目： vladimiryugay.github.io/game/
GitHub: github.com/VladimirYuga...
RGBD 数据流（含深度信息的视频）转 3D高斯溅射场景重建模型
- 能适应一定程度的场景变换，如：重建了厨房后，对卧室进行了扫描，随后又回到厨房。这期间，有人移动了椅子并在厨房里加了一张桌子。
项目： vladimiryugay.github.io/game/
GitHub: github.com/VladimirYuga...
September 25, 2026 at 12:14 PM
GaME: Gaussian Mapping for Evolving Scenes
RGBD 数据流（含深度信息的视频）转 3D高斯溅射场景重建模型
- 能适应一定程度的场景变换，如：重建了厨房后，对卧室进行了扫描，随后又回到厨房。这期间，有人移动了椅子并在厨房里加了一张桌子。
项目： vladimiryugay.github.io/game/
GitHub: github.com/VladimirYuga...
RGBD 数据流（含深度信息的视频）转 3D高斯溅射场景重建模型
- 能适应一定程度的场景变换，如：重建了厨房后，对卧室进行了扫描，随后又回到厨房。这期间，有人移动了椅子并在厨房里加了一张桌子。
项目： vladimiryugay.github.io/game/
GitHub: github.com/VladimirYuga...
📢 📢 📢 We've released the ScanNet++ Novel View Synthesis Benchmark for iPhone data!
Test your models on RGBD video featuring real-world challenges like exposure changes & motion blur!
Download the newest iPhone NVS test split and submit your results! ⬇️
scannetpp.mlsg.cit.tum.de/scannetpp/be...
Test your models on RGBD video featuring real-world challenges like exposure changes & motion blur!
Download the newest iPhone NVS test split and submit your results! ⬇️
scannetpp.mlsg.cit.tum.de/scannetpp/be...
October 13, 2025 at 4:19 PM
📢 📢 📢 We've released the ScanNet++ Novel View Synthesis Benchmark for iPhone data!
Test your models on RGBD video featuring real-world challenges like exposure changes & motion blur!
Download the newest iPhone NVS test split and submit your results! ⬇️
scannetpp.mlsg.cit.tum.de/scannetpp/be...
Test your models on RGBD video featuring real-world challenges like exposure changes & motion blur!
Download the newest iPhone NVS test split and submit your results! ⬇️
scannetpp.mlsg.cit.tum.de/scannetpp/be...
Surprise REPO stream w/ @mythicalredfox.bsky.social
April 27, 2025 at 11:56 PM
Surprise REPO stream w/ @mythicalredfox.bsky.social
VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians
Pengchong Hu, Zhizhong Han
tl;dr: tie a 3D Gaussian to each pixel on the depth; simplify an ellipsoid 3D Gaussian as a sphere
arxiv.org/abs/2506.02741
Pengchong Hu, Zhizhong Han
tl;dr: tie a 3D Gaussian to each pixel on the depth; simplify an ellipsoid 3D Gaussian as a sphere
arxiv.org/abs/2506.02741
June 4, 2025 at 1:51 PM
VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians
Pengchong Hu, Zhizhong Han
tl;dr: tie a 3D Gaussian to each pixel on the depth; simplify an ellipsoid 3D Gaussian as a sphere
arxiv.org/abs/2506.02741
Pengchong Hu, Zhizhong Han
tl;dr: tie a 3D Gaussian to each pixel on the depth; simplify an ellipsoid 3D Gaussian as a sphere
arxiv.org/abs/2506.02741
📊 We're releasing a massive dataset and generation tools to help the community solve these tasks
• 466GB of RGBD + state data
• 44K episodes
• 8.8M transitions
• Detailed event labeling + trajectory filtering
Download: arth-shukla.github.io/mshab/#dataset-section
(4/5)
• 466GB of RGBD + state data
• 44K episodes
• 8.8M transitions
• Detailed event labeling + trajectory filtering
Download: arth-shukla.github.io/mshab/#dataset-section
(4/5)
December 19, 2024 at 10:47 PM
📊 We're releasing a massive dataset and generation tools to help the community solve these tasks
• 466GB of RGBD + state data
• 44K episodes
• 8.8M transitions
• Detailed event labeling + trajectory filtering
Download: arth-shukla.github.io/mshab/#dataset-section
(4/5)
• 466GB of RGBD + state data
• 44K episodes
• 8.8M transitions
• Detailed event labeling + trajectory filtering
Download: arth-shukla.github.io/mshab/#dataset-section
(4/5)
Vision to Motion, mapless navigation: navigating robot, using yolov8 for navigation, full chain transformation(optimal camera frame to baseline frame, odom), then extended sensor fusion with kalman filter(fusing rgbd and lidar) then navigation to the chair 🪑 in Gazebo Depo World!
December 21, 2024 at 2:14 AM
Vision to Motion, mapless navigation: navigating robot, using yolov8 for navigation, full chain transformation(optimal camera frame to baseline frame, odom), then extended sensor fusion with kalman filter(fusing rgbd and lidar) then navigation to the chair 🪑 in Gazebo Depo World!
i really want an rgbd camera
May 5, 2023 at 12:09 AM
i really want an rgbd camera
[2025-04-08] 📚 Updates in #3DPC
(1) Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learning
(2) <a href="https://researchtrend.ai/papers/2504.04701" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
(3) DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
🔍 More at researchtrend.ai/communities/3DPC
(1) Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learning
(2) <a href="https://researchtrend.ai/papers/2504.04701" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
(3) DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
🔍 More at researchtrend.ai/communities/3DPC
April 8, 2025 at 5:18 AM
[2025-04-08] 📚 Updates in #3DPC
(1) Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learning
(2) <a href="https://researchtrend.ai/papers/2504.04701" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
(3) DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
🔍 More at researchtrend.ai/communities/3DPC
(1) Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learning
(2) <a href="https://researchtrend.ai/papers/2504.04701" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
(3) DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
🔍 More at researchtrend.ai/communities/3DPC
That doesn’t seem to make sense, you don’t need a RGBD camera, phone works fine. Happy to address it more if details can be shared on github if needed
July 5, 2025 at 3:04 AM
That doesn’t seem to make sense, you don’t need a RGBD camera, phone works fine. Happy to address it more if details can be shared on github if needed
Namal Jayasuriya, Yi Guo, Wen Hu, Oula Ghannoum
Deep Learning-Based Direct Leaf Area Estimation using Two RGBD Datasets for Model Development
https://arxiv.org/abs/2503.10129
Deep Learning-Based Direct Leaf Area Estimation using Two RGBD Datasets for Model Development
https://arxiv.org/abs/2503.10129
March 14, 2025 at 8:44 AM
Namal Jayasuriya, Yi Guo, Wen Hu, Oula Ghannoum
Deep Learning-Based Direct Leaf Area Estimation using Two RGBD Datasets for Model Development
https://arxiv.org/abs/2503.10129
Deep Learning-Based Direct Leaf Area Estimation using Two RGBD Datasets for Model Development
https://arxiv.org/abs/2503.10129
A key technical point is how it achieves real-time performance. It uses RGBD data and neural networks to bypass the heavy optimization steps typical in standard Gaussian Splatting. #NeuralRendering 2/6
May 16, 2025 at 5:00 PM
A key technical point is how it achieves real-time performance. It uses RGBD data and neural networks to bypass the heavy optimization steps typical in standard Gaussian Splatting. #NeuralRendering 2/6
Hu and Han, "SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance
Fields in RGBD SLAM"
Generalized ICP + Depth-wise adjusted pixel-aligned Gaussians. You don't need all the fancy bells and whistles, just a "tight" implementation.
Fields in RGBD SLAM"
Generalized ICP + Depth-wise adjusted pixel-aligned Gaussians. You don't need all the fancy bells and whistles, just a "tight" implementation.
March 25, 2026 at 12:44 AM
Hu and Han, "SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance
Fields in RGBD SLAM"
Generalized ICP + Depth-wise adjusted pixel-aligned Gaussians. You don't need all the fancy bells and whistles, just a "tight" implementation.
Fields in RGBD SLAM"
Generalized ICP + Depth-wise adjusted pixel-aligned Gaussians. You don't need all the fancy bells and whistles, just a "tight" implementation.
SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM
Pengchong Hu, Zhizhong Han
tl;dr: pixel-aligned Gaussians, but allow Gaussians to move along their rays
arxiv.org/abs/2603.21055
Pengchong Hu, Zhizhong Han
tl;dr: pixel-aligned Gaussians, but allow Gaussians to move along their rays
arxiv.org/abs/2603.21055
March 24, 2026 at 5:09 PM
SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM
Pengchong Hu, Zhizhong Han
tl;dr: pixel-aligned Gaussians, but allow Gaussians to move along their rays
arxiv.org/abs/2603.21055
Pengchong Hu, Zhizhong Han
tl;dr: pixel-aligned Gaussians, but allow Gaussians to move along their rays
arxiv.org/abs/2603.21055
Twenty-five years old now, but I still think about this beautiful, painted animation of "The Old Man and the Sea."
#Art
www.youtube.com/watch?v=RGbD...
#Art
www.youtube.com/watch?v=RGbD...
The Old Man and the Sea (1999), paint on glass animation
YouTube video by echologia time channel
www.youtube.com
July 23, 2026 at 11:02 AM
Twenty-five years old now, but I still think about this beautiful, painted animation of "The Old Man and the Sea."
#Art
www.youtube.com/watch?v=RGbD...
#Art
www.youtube.com/watch?v=RGbD...