More Like this

1. Motion Adaptive Deblurring With Single-Photon Cameras

   Seets, Trevor; Ingle, Atul; Laurenzis, Martin; Velten, Andreas (January 2021, Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV))

   null (Ed.)

   Single-photon avalanche diodes (SPADs) are a rapidly developing image sensing technology with extreme low-light sensitivity and picosecond timing resolution. These unique capabilities have enabled SPADs to be used in applications like LiDAR, non-line-of-sight imaging and fluorescence microscopy that require imaging in photon-starved scenarios. In this work we harness these capabilities for dealing with motion blur in a passive imaging setting in low illumination conditions. Our key insight is that the data captured by a SPAD array camera can be represented as a 3D spatio-temporal tensor of photon detection events which can be integrated along arbitrary spatio-temporal trajectories with dynamically varying integration windows, depending on scene motion. We propose an algorithm that estimates pixel motion from photon timestamp data and dynamically adapts the integration windows to minimize motion blur. Our simulation results show the applicability of this algorithm to a variety of motion profiles including translation, rotation and local object motion. We also demonstrate the real-world feasibility of our method on data captured using a 32x32 SPAD camera. 

   more » « less
2. Multi-version Tensor Completion for Time-delayed Spatio-temporal Data

   https://doi.org/10.24963/ijcai.2021/400  

   Qian, Cheng; Kargas, Nikos; Xiao, Cao; Glass, Lucas; Sidiropoulos, Nicholas; Sun, Jimeng (August 2021, Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI) 2021)

   null (Ed.)

   Real-world spatio-temporal data is often incomplete or inaccurate due to various data loading delays. For example, a location-disease-time tensor of case counts can have multiple delayed updates of recent temporal slices for some locations or diseases. Recovering such missing or noisy (under-reported) elements of the input tensor can be viewed as a generalized tensor completion problem. Existing tensor completion methods usually assume that i) missing elements are randomly distributed and ii) noise for each tensor element is i.i.d. zero-mean. Both assumptions can be violated for spatio-temporal tensor data. We often observe multiple versions of the input tensor with different under-reporting noise levels. The amount of noise can be time- or location-dependent as more updates are progressively introduced to the tensor. We model such dynamic data as a multi-version tensor with an extra tensor mode capturing the data updates. We propose a low-rank tensor model to predict the updates over time. We demonstrate that our method can accurately predict the ground-truth values of many real-world tensors. We obtain up to 27.2% lower root mean-squared-error compared to the best baseline method. Finally, we extend our method to track the tensor data over time, leading to significant computational savings. 

   more » « less
3. TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking

   Reddy, N Dinesh; Guigues, Laurent; Pischulini, Leonid; Eledath, Jayan; Narasimhan, Srinivasa (June 2021, International Conference on Computer Vision and Pattern Recognition (CVPR))

   We consider the task of 3D pose estimation and tracking of multiple people seen in an arbitrary number of camera feeds. We propose TesseTrack, a novel top-down approach that simultaneously reasons about multiple individuals’ 3D body joint reconstructions and associations in space and time in a single end-to-end learnable framework. At the core of our approach is a novel spatio-temporal formulation that operates in a common voxelized feature space aggregated from single- or multiple camera views. After a person detection step, a 4D CNN produces short-term persons pecific representations which are then linked across time by a differentiable matcher. The linked descriptions are then merged and deconvolved into 3D poses. This joint spatio-temporal formulation contrasts with previous piecewise strategies that treat 2D pose estimation, 2D-to-3D lifting, and 3D pose tracking as independent sub-problems that are error-prone when solved in isolation. Furthermore, unlike previous methods, TesseTrack is robust to changes in the number of camera views and achieves very good results even if a single view is available at inference time. Quantitative evaluation of 3D pose reconstruction accuracy on standard benchmarks shows significant improvements over the state of the art. Evaluation of multi-person articulated 3D pose tracking in our novel evaluation framework demonstrates the superiority of TesseTrack over strong baselines. 

   more » « less
4. First-Arrival Differential Counting for SPAD Array Design

   https://doi.org/10.3390/s23239445  

   White, Mel; Zhang, Tianyi; Dave, Akshat; Ghajari, Shahaboddin; Molnar, Alyosha; Veeraraghavan, Ashok (December 2023, Sensors)

   We present a novel architecture for the design of single-photon detecting arrays that captures relative intensity or timing information from a scene, rather than absolute. The proposed method for capturing relative information between pixels or groups of pixels requires very little circuitry, and thus allows for a significantly higher pixel packing factor than is possible with per-pixel TDC approaches. The inherently compressive nature of the differential measurements also reduces data throughput and lends itself to physical implementations of compressed sensing, such as Haar wavelets. We demonstrate this technique for HDR imaging and LiDAR, and describe possible future applications. 

   more » « less
5. Principled neuromorphic reservoir computing

   https://doi.org/10.1038/s41467-025-55832-y  

   Kleyko, Denis; Kymn, Christopher J; Thomas, Anthony; Olhausen, Bruno A; Sommer, Friedrich T; Frady, E Paxon (January 2025, Nature communications)

   Reservoir computing advances the intriguing idea that a nonlinear recurrent neural circuit—the reservoir—can encode spatio-temporal input signals to enable efficient ways to perform tasks like classification or regression. However, recently the idea of a monolithic reservoir network that simultaneously buffers input signals and expands them into nonlinear features has been challenged. A representation scheme in which memory buffer and expansion into higher-order polynomial features can be configured separately has been shown to significantly outperform traditional reservoir computing in prediction of multivariate time-series. Here we propose a configurable neuromorphic representation scheme that provides competitive performance on prediction, but with significantly better scaling properties than directly materializing higher-order features as in prior work. Our approach combines the use of randomized representations from traditional reservoir computing with mathematical principles for approximating polynomial kernels via such representations. While the memory buffer can be realized with standard reservoir networks, computing higher-order features requires networks of ‘Sigma-Pi’ neurons, i.e., neurons that enable both summation as well as multiplication of inputs. Finally, we provide an implementation of the memory buffer and Sigma-Pi networks on Loihi 2, an existing neuromorphic hardware platform. 

   more » « less