November 1, 2026 at 2:49 PM
Building the 3D Boundary Environment via Backprojection
To convert the raw pulsed radio waves from the moving drone into a physical 3D map within the SoundThinking environment, Motorola's AI pipelines typically utilize a Time-Domain Backprojection (TDBP) algorithm.
To convert the raw pulsed radio waves from the moving drone into a physical 3D map within the SoundThinking environment, Motorola's AI pipelines typically utilize a Time-Domain Backprojection (TDBP) algorithm.
October 6, 2026 at 9:14 AM
Building the 3D Boundary Environment via Backprojection
To convert the raw pulsed radio waves from the moving drone into a physical 3D map within the SoundThinking environment, Motorola's AI pipelines typically utilize a Time-Domain Backprojection (TDBP) algorithm.
To convert the raw pulsed radio waves from the moving drone into a physical 3D map within the SoundThinking environment, Motorola's AI pipelines typically utilize a Time-Domain Backprojection (TDBP) algorithm.
Airborne SAR Drone (Skydio/BRINC)
Raw Pulsed RF Phase Data
Motorola AI Compute (Edge/Cloud)
Range-Doppler & Backprojection
Orchestration & Sensor Fusion
Computer Vision & Object Detection
Raw Pulsed RF Phase Data
Motorola AI Compute (Edge/Cloud)
Range-Doppler & Backprojection
Orchestration & Sensor Fusion
Computer Vision & Object Detection
October 6, 2026 at 9:12 AM
Airborne SAR Drone (Skydio/BRINC)
Raw Pulsed RF Phase Data
Motorola AI Compute (Edge/Cloud)
Range-Doppler & Backprojection
Orchestration & Sensor Fusion
Computer Vision & Object Detection
Raw Pulsed RF Phase Data
Motorola AI Compute (Edge/Cloud)
Range-Doppler & Backprojection
Orchestration & Sensor Fusion
Computer Vision & Object Detection
🌟 OPEN ACCESS 🌟 How does a rupture propagate in a geometrically complex multifault system? A new #BSSA paper considers this question by looking at the 2023 Kahramanmaraş, Türkiye earthquake doublet. ⚒️
buff.ly/VvrYIbv
buff.ly/VvrYIbv
August 18, 2026 at 3:00 AM
🌟 OPEN ACCESS 🌟 How does a rupture propagate in a geometrically complex multifault system? A new #BSSA paper considers this question by looking at the 2023 Kahramanmaraş, Türkiye earthquake doublet. ⚒️
buff.ly/VvrYIbv
buff.ly/VvrYIbv
🌟 OPEN ACCESS 🌟 In a new #BSSA paper, a team of scientists investigates the rupture kinematics of the two earthquakes that struck the Kahramanmaraş, Türkiye region in 2023. Among their findings, they report multiple transitions from subshear to supershear in the first event. ⚒️
buff.ly/VvrYIbv
buff.ly/VvrYIbv
August 12, 2026 at 9:01 PM
🌟 OPEN ACCESS 🌟 In a new #BSSA paper, a team of scientists investigates the rupture kinematics of the two earthquakes that struck the Kahramanmaraş, Türkiye region in 2023. Among their findings, they report multiple transitions from subshear to supershear in the first event. ⚒️
buff.ly/VvrYIbv
buff.ly/VvrYIbv
And related to that, #CryoLithe is a pre-trained neural network replacing the backprojection operator to reconstruct high-quality denoised tomograms blazing fast – also a great collab with Vinith Kishore and Valentin Debarnot from the @ivandokmanic.bsky.social 🤓
Efficient reconstruction and denoising of cryo-ET data with end-to-end localized deep learning
Cryo-electron tomography (cryo-ET) enables 3D visualization of cellular structures. Accurate reconstruction of high-resolution volumes is complicated by the very low signal-to-noise ratio and a restri...
arxiv.org
January 9, 2026 at 7:15 PM
And related to that, #CryoLithe is a pre-trained neural network replacing the backprojection operator to reconstruct high-quality denoised tomograms blazing fast – also a great collab with Vinith Kishore and Valentin Debarnot from the @ivandokmanic.bsky.social 🤓
lightly-train LightlyTrain is the first PyTorch framework to pretrain computer vision models on u...
https://www.libhunt.com/r/lightly-train
Event Attributes
https://www.libhunt.com/r/lightly-train
Event Attributes
Lightly-train Alternatives and Reviews
Which is the best alternative to lightly-train? Based on common mentions it is: Pytorch-metric-learning, Lightly, Quaterion or Calibrated-backprojection-network
www.libhunt.com
April 16, 2025 at 7:39 PM
lightly-train LightlyTrain is the first PyTorch framework to pretrain computer vision models on u...
https://www.libhunt.com/r/lightly-train
Event Attributes
https://www.libhunt.com/r/lightly-train
Event Attributes
filtered backprojection using a parameter-dependent Butterworth filter. For the optimization of filter's parameters, we adopt a kernel-based Bayesian optimization framework grounded in reproducing kernel Hilbert space theory, highlighting the [4/6 of https://arxiv.org/abs/2505.06692v1]
May 13, 2025 at 6:05 AM
filtered backprojection using a parameter-dependent Butterworth filter. For the optimization of filter's parameters, we adopt a kernel-based Bayesian optimization framework grounded in reproducing kernel Hilbert space theory, highlighting the [4/6 of https://arxiv.org/abs/2505.06692v1]
Radon transform and the pixel-driven backprojection under suitable choice of discretization parameters. Notably, said suitable parameter choices include the combination of the ray-driven Radon transform with the pixel-driven backprojection [6/7 of https://arxiv.org/abs/2503.03069v1]
March 6, 2025 at 6:09 AM
Radon transform and the pixel-driven backprojection under suitable choice of discretization parameters. Notably, said suitable parameter choices include the combination of the ray-driven Radon transform with the pixel-driven backprojection [6/7 of https://arxiv.org/abs/2503.03069v1]
approach combines the ray-driven Radon transform with the pixel-driven backprojection, as anecdotal reports describe these as showing the best approximation performance. However, there is little rigorous understanding of induced approximation [3/7 of https://arxiv.org/abs/2503.03069v1]
March 6, 2025 at 6:09 AM
approach combines the ray-driven Radon transform with the pixel-driven backprojection, as anecdotal reports describe these as showing the best approximation performance. However, there is little rigorous understanding of induced approximation [3/7 of https://arxiv.org/abs/2503.03069v1]
process. Since in any practical application one can only obtain and process finitely many measurements, suitable discretization of the Radon transform and its adjoint (called the backprojection) is crucial. The most commonly used discretization [2/7 of https://arxiv.org/abs/2503.03069v1]
March 6, 2025 at 6:08 AM
process. Since in any practical application one can only obtain and process finitely many measurements, suitable discretization of the Radon transform and its adjoint (called the backprojection) is crucial. The most commonly used discretization [2/7 of https://arxiv.org/abs/2503.03069v1]
ray-driven Radon transform and the pixel-driven backprojection under balanced resolutions. Our considerations are supported by numerical experiments highlighting aspects of the discussed methods. [6/6 of https://arxiv.org/abs/2501.11451v1]
January 22, 2025 at 1:08 PM
ray-driven Radon transform and the pixel-driven backprojection under balanced resolutions. Our considerations are supported by numerical experiments highlighting aspects of the discussed methods. [6/6 of https://arxiv.org/abs/2501.11451v1]
parameters: spatial-, detector-, and angular resolutions. The most widespread approach uses the ray-driven Radon transform and the pixel-driven backprojection in a balanced resolution setting, i.e., the spatial resolution roughly equals the [3/6 of https://arxiv.org/abs/2501.11451v1]
January 22, 2025 at 1:08 PM
parameters: spatial-, detector-, and angular resolutions. The most widespread approach uses the ray-driven Radon transform and the pixel-driven backprojection in a balanced resolution setting, i.e., the spatial resolution roughly equals the [3/6 of https://arxiv.org/abs/2501.11451v1]
transform. In practice, the solution of the tomographic problem requires discretization of the Radon transform and its adjoint (called the backprojection). There are various discretization schemes; often structured around three discretization [2/6 of https://arxiv.org/abs/2501.11451v1]
January 22, 2025 at 1:08 PM
transform. In practice, the solution of the tomographic problem requires discretization of the Radon transform and its adjoint (called the backprojection). There are various discretization schemes; often structured around three discretization [2/6 of https://arxiv.org/abs/2501.11451v1]
🌟 OPEN ACCESS 🌟 Mixed Subshear and Supershear Rupture Kinematics of the 2023 Kahramanmaraş, Türkiye Earthquake Doublet Modulated by Complex Fault Geometry #BSSA ⚒️
How does a rupture propagate in a geometrically complex multifault system?
buff.ly/dS3uPvD
How does a rupture propagate in a geometrically complex multifault system?
buff.ly/dS3uPvD
August 5, 2026 at 3:02 PM
🌟 OPEN ACCESS 🌟 Mixed Subshear and Supershear Rupture Kinematics of the 2023 Kahramanmaraş, Türkiye Earthquake Doublet Modulated by Complex Fault Geometry #BSSA ⚒️
How does a rupture propagate in a geometrically complex multifault system?
buff.ly/dS3uPvD
How does a rupture propagate in a geometrically complex multifault system?
buff.ly/dS3uPvD
🌟 OPEN ACCESS 🌟 Source Process of the 2025 Mw 8.8 Kamchatka Peninsula, Russia, Earthquake Revealed by Backprojection and Waveform Inversion #TSR ⚒️
Scientists found that this earthquake lasted about 180 seconds, with an average rupture propagation velocity of 2.2 km/sec.
buff.ly/i3zRXN1
Scientists found that this earthquake lasted about 180 seconds, with an average rupture propagation velocity of 2.2 km/sec.
buff.ly/i3zRXN1
July 21, 2026 at 3:01 PM
🌟 OPEN ACCESS 🌟 Source Process of the 2025 Mw 8.8 Kamchatka Peninsula, Russia, Earthquake Revealed by Backprojection and Waveform Inversion #TSR ⚒️
Scientists found that this earthquake lasted about 180 seconds, with an average rupture propagation velocity of 2.2 km/sec.
buff.ly/i3zRXN1
Scientists found that this earthquake lasted about 180 seconds, with an average rupture propagation velocity of 2.2 km/sec.
buff.ly/i3zRXN1
🌟 OPEN ACCESS 📣 PRESS RELEASE 🌟 The 2025 Mw 8.8 Kamchatka Megathrust Earthquake: Evidence for an Extended Rupture from Teleseismic Backprojection and Hydroacoustic Observations #TSR ⚒️
Press release: buff.ly/HiO4vtu
Paper: buff.ly/jdouQZw
Press release: buff.ly/HiO4vtu
Paper: buff.ly/jdouQZw
Massive Kamchatka Earthquake Has Extended Rupture That Overlaps 1952 Event | Seismological Society of America
10 June 2026—Researchers combining two methods to reconstruct the rupture evolution of the July 2025 magnitude 8.8. Kamchatka earthquake found the rupture from the megathrust event extended about 500…
buff.ly
June 12, 2026 at 4:01 PM
🌟 OPEN ACCESS 📣 PRESS RELEASE 🌟 The 2025 Mw 8.8 Kamchatka Megathrust Earthquake: Evidence for an Extended Rupture from Teleseismic Backprojection and Hydroacoustic Observations #TSR ⚒️
Press release: buff.ly/HiO4vtu
Paper: buff.ly/jdouQZw
Press release: buff.ly/HiO4vtu
Paper: buff.ly/jdouQZw
Backprojection, a method used to obtain the distribution of energy radiation of large earthquakes in space and time, can be affected by waveform complexities. A new #SRL presents a method to eliminate this issue. ⚒️
buff.ly/V7Heih6
buff.ly/V7Heih6
April 27, 2026 at 3:00 AM
Backprojection, a method used to obtain the distribution of energy radiation of large earthquakes in space and time, can be affected by waveform complexities. A new #SRL presents a method to eliminate this issue. ⚒️
buff.ly/V7Heih6
buff.ly/V7Heih6
In a new #SRL paper, scientists propose a new backprojection method—compressive sensing backprojection. They apply the method to the 2024 magnitude 7.2 Hualien earthquake in Taiwan. ⚒️
buff.ly/V7Heih6
buff.ly/V7Heih6
April 21, 2026 at 9:01 PM
In a new #SRL paper, scientists propose a new backprojection method—compressive sensing backprojection. They apply the method to the 2024 magnitude 7.2 Hualien earthquake in Taiwan. ⚒️
buff.ly/V7Heih6
buff.ly/V7Heih6
A New Compressive Sensing Backprojection Method Based on Deconvolution with Green’s Functions #SRL ⚒️
Scientists present a way to improve our understanding of energy radiation distribution from big earthquakes.
buff.ly/lmlJiZd
Scientists present a way to improve our understanding of energy radiation distribution from big earthquakes.
buff.ly/lmlJiZd
April 16, 2026 at 3:03 PM
A New Compressive Sensing Backprojection Method Based on Deconvolution with Green’s Functions #SRL ⚒️
Scientists present a way to improve our understanding of energy radiation distribution from big earthquakes.
buff.ly/lmlJiZd
Scientists present a way to improve our understanding of energy radiation distribution from big earthquakes.
buff.ly/lmlJiZd
What does a combination of integrated differential InSAR analysis, finite-fault inversion, backprojection, and aftershock relocation tell scientists about the 2024 Wushi earthquake that struck northwest China? Find out in #SRL ⚒️
pubs.geoscienceworld.org/ssa/srl/arti...
pubs.geoscienceworld.org/ssa/srl/arti...
December 4, 2025 at 3:00 AM
What does a combination of integrated differential InSAR analysis, finite-fault inversion, backprojection, and aftershock relocation tell scientists about the 2024 Wushi earthquake that struck northwest China? Find out in #SRL ⚒️
pubs.geoscienceworld.org/ssa/srl/arti...
pubs.geoscienceworld.org/ssa/srl/arti...
In a new #SRL paper, scientists integrate differential InSAR analysis, finite-fault inversion, backprojection, and aftershock relocation to explore the complexity of the 2024 Wushi earthquake in northwest China. ⚒️
pubs.geoscienceworld.org/ssa/srl/arti...
pubs.geoscienceworld.org/ssa/srl/arti...
November 28, 2025 at 8:00 PM
In a new #SRL paper, scientists integrate differential InSAR analysis, finite-fault inversion, backprojection, and aftershock relocation to explore the complexity of the 2024 Wushi earthquake in northwest China. ⚒️
pubs.geoscienceworld.org/ssa/srl/arti...
pubs.geoscienceworld.org/ssa/srl/arti...
donut-shaped focal spot can be used to reconstruct images with super-resolution and super-sensitivity through the deconvoution of the STED focal spot and filtered backprojection algorithm. [6/6 of https://arxiv.org/abs/2505.06490v1]
May 13, 2025 at 6:14 AM
donut-shaped focal spot can be used to reconstruct images with super-resolution and super-sensitivity through the deconvoution of the STED focal spot and filtered backprojection algorithm. [6/6 of https://arxiv.org/abs/2505.06490v1]
backprojection-convolution formula for recovering the transformed volume, provided the data is amenable to this method. The cone-beam method is usable for X-ray source point loci that are multidimensional and that adequately surround the [3/4 of https://arxiv.org/abs/2505.05372v1]
May 9, 2025 at 6:14 AM
backprojection-convolution formula for recovering the transformed volume, provided the data is amenable to this method. The cone-beam method is usable for X-ray source point loci that are multidimensional and that adequately surround the [3/4 of https://arxiv.org/abs/2505.05372v1]
a convolution-backprojection formula and a backprojection-convolution formula for recovering the transformed volume, provided the data is sufficient. The second theorem concerns X-ray data collected with a cone-beam; it contains a [2/4 of https://arxiv.org/abs/2505.05372v1]
May 9, 2025 at 6:13 AM
a convolution-backprojection formula and a backprojection-convolution formula for recovering the transformed volume, provided the data is sufficient. The second theorem concerns X-ray data collected with a cone-beam; it contains a [2/4 of https://arxiv.org/abs/2505.05372v1]