More Like this

1. What You Can Learn by Staring at a Blank Wall

   Sharma, P.; Aittala, M.; Schechner, Y. Y.; Torralba, A.; Wornell, G. W.; Freeman, W. T.; Durand, F. (October 2021, Int. Conf. Computer Vision (ICCV-2021))

   null (Ed.)

   We present a passive non-line-of-sight method that infers the number of people or activity of a person from the observation of a blank wall in an unknown room. Our technique analyzes complex imperceptible changes in indirect illumination in a video of the wall to reveal a signal that is correlated with motion in the hidden part of a scene. We use this signal to classify between zero, one, or two moving people, or the activity of a person in the hidden scene. We train two convolutional neural networks using data collected from 20 different scenes, and achieve an accuracy of 94% for both tasks in unseen test environments and real-time online settings. Unlike other passive non-line-of-sight methods, the technique does not rely on known occluders or controllable light sources, and generalizes to unknown rooms with no recalibration. We analyze the generalization and robustness of our method with both real and synthetic data, and study the effect of the scene parameters on the signal quality. 

   more » « less
2. FlowCam: Training generalizable 3D radiance fields without camera poses via pixel-aligned scene flow

   Smith, Cameron; Du, Yilun; Tewari, Ayush; Sitzmann, Vincent (December 2023, Neural Information Processing Systems)

   Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their dependence on precise camera poses from structure-from-motion, which is prohibitively expensive to run at scale. We propose a method that jointly reconstructs camera poses and 3D neural scene representations online and in a single forward pass. We estimate poses by first lifting frame-to-frame optical flow to 3D scene flow via differentiable rendering, preserving locality and shift-equivariance of the image processing backbone. SE(3) camera pose estimation is then performed via a weighted least-squares fit to the scene flow field. This formulation enables us to jointly supervise pose estimation and a generalizable neural scene representation via re-rendering the input video, and thus, train end-to-end and fully self-supervised on real-world video datasets. We demonstrate that our method performs robustly on diverse, real-world video, notably on sequences traditionally challenging to optimization-based pose estimation techniques. 

   more » « less
3. FlowCam: Training generalizable 3D radiance fields without camera poses via pixel-aligned scene flow

   Smith, Cameron; Du, Yilun; Tewari, Ayush; Sitzmann, Vincent (December 2023, Neural Information Processing Systems)

   Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their dependence on precise camera poses from structure-from-motion, which is prohibitively expensive to run at scale. We propose a method that jointly reconstructs camera poses and 3D neural scene representations online and in a single forward pass. We estimate poses by first lifting frame-to-frame optical flow to 3D scene flow via differentiable rendering, preserving locality and shift-equivariance of the image processing backbone. SE(3) camera pose estimation is then performed via a weighted least-squares fit to the scene flow field. This formulation enables us to jointly supervise pose estimation and a generalizable neural scene representation via re-rendering the input video, and thus, train end-to-end and fully self-supervised on real-world video datasets. We demonstrate that our method performs robustly on diverse, real-world video, notably on sequences traditionally challenging to optimization-based pose estimation techniques. 

   more » « less
4. OFDVDnet: A Sensor Fusion Approach for Video Denoising in Fluorescence-Guided Surgery

   Seets, Trevor; Lin, Wei; Lu, Yizhou; Lin, Christie; Uselmann, Adam; Velten, Andreas (June 2023, Proceedings of Machine Learning Research)

   Oguz, Ipek; Noble, Jack; Li, Xiaoxiao; Styner, Martin; Baumgartner, Christian; Rusu, Mirabela; Heinmann, Tobias; Kontos, Despina; Landman, Bennett; Dawant, Benoit (Ed.)

   Many applications in machine vision and medical imaging require the capture of images from a scene with very low radiance, which may result in very noisy images and videos. An important example of such an application is the imaging of fluorescently-labeled tissue in fluorescence-guided surgery. Medical imaging systems, especially when intended to be used in surgery, are designed to operate in well-lit environments and use optical filters, time division, or other strategies that allow the simultaneous capture of low radiance fluorescence video and a well-lit visible light video of the scene. This work demonstrates video denoising can be dramatically improved by utilizing deep learning together with motion and textural cues from the noise-free video. 

   more » « less
5. Sparse Representations for Object- and Ego-Motion Estimations in Dynamic Scenes

   https://doi.org/10.1109/TNNLS.2020.3006467  

   Kashyap, Hirak J.; Fowlkes, Charless C.; Krichmar, Jeffrey L. (January 2020, IEEE Transactions on Neural Networks and Learning Systems)

   Disentangling the sources of visual motion in a dynamic scene during self-movement or ego motion is important for autonomous navigation and tracking. In the dynamic image segments of a video frame containing independently moving objects, optic flow relative to the next frame is the sum of the motion fields generated due to camera and object motion. The traditional ego-motion estimation methods assume the scene to be static, and the recent deep learning-based methods do not separate pixel velocities into object- and ego-motion components. We propose a learning-based approach to predict both ego-motion parameters and object-motion field (OMF) from image sequences using a convolutional autoencoder while being robust to variations due to the unconstrained scene depth. This is achieved by: 1) training with continuous ego-motion constraints that allow solving for ego-motion parameters independently of depth and 2) learning a sparsely activated overcomplete ego-motion field (EMF) basis set, which eliminates the irrelevant components in both static and dynamic segments for the task of ego-motion estimation. In order to learn the EMF basis set, we propose a new differentiable sparsity penalty function that approximates the number of nonzero activations in the bottleneck layer of the autoencoder and enforces sparsity more effectively than L1- and L2-norm-based penalties. Unlike the existing direct ego-motion estimation methods, the predicted global EMF can be used to extract OMF directly by comparing it against the optic flow. Compared with the state-of-the-art baselines, the proposed model performs favorably on pixelwise object- and ego-motion estimation tasks when evaluated on real and synthetic data sets of dynamic scenes. 

   more » « less