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
Using Synthetic Data Generation to Probe Multi-View Stereo Networks
Synthetic data is highly useful for training machine learning systems performing image-based 3D reconstruction, as synthetic data has applications in both extending existing generalizable datasets and being tailored to train neural networks for specific learning tasks of interest. In this paper, we introduce and utilize a synthetic data generation suite capable of generating data given existing 3D scene models as input. Specifically, we use our tool to generate image sequences for use with Multi-View Stereo (MVS), moving a camera through the virtual space according to user-chosen camera parameters. We evaluate how the given camera parameters and type of 3D environment affect how applicable the generated image sequences are to the MVS task using five pre-trained neural networks on image sequences generated from three different 3D scene datasets. We obtain generated predictions for each combination of parameter value and input image sequence, using standard error metrics to analyze the differences in depth predictions on image sequences across 3D datasets, parameters, and networks. Among other results, we find that camera height and vertical camera viewing angle are the parameters that cause the most variation in depth prediction errors on these image sequences.
more »
« less
- Award ID(s):
- 1911230
- NSF-PAR ID:
- 10332456
- Date Published:
- Journal Name:
- 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
- Page Range / eLocation ID:
- 1583 to 1591
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We present 3DVNet, a novel multi-view stereo (MVS) depth-prediction method that combines the advantages of previous depth-based and volumetric MVS approaches. Our key idea is the use of a 3D scene-modeling network that iteratively updates a set of coarse depth predictions, resulting in highly accurate predictions which agree on the underlying scene geometry. Unlike existing depth-prediction techniques, our method uses a volumetric 3D convolutional neural network (CNN) that operates in world space on all depth maps jointly. The network can therefore learn meaningful scene-level priors. Furthermore, unlike existing volumetric MVS techniques, our 3D CNN operates on a feature-augmented point cloud, allowing for effective aggregation of multi-view information and flexible iterative refinement of depth maps. Experimental results show our method exceeds state-of-the-art accuracy in both depth prediction and 3D reconstruction metrics on the ScanNet dataset, as well as a selection of scenes from the TUM-RGBD and ICL-NUIM datasets. This shows that our method is both effective and generalizes to new settings.more » « less
-
Current deep neural network approaches for camera pose estimation rely on scene structure for 3D motion estimation, but this decreases the robustness and thereby makes cross-dataset generalization difficult. In contrast, classical approaches to structure from motion estimate 3D motion utilizing optical flow and then compute depth. Their accuracy, however, depends strongly on the quality of the optical flow. To avoid this issue, direct methods have been proposed, which separate 3D motion from depth estimation, but compute 3D motion using only image gradients in the form of normal flow. In this paper, we introduce a network NFlowNet, for normal flow estimation which is used to enforce robust and direct constraints. In particular, normal flow is used to estimate relative camera pose based on the cheirality (depth positivity) constraint. We achieve this by formulating the optimization problem as a differentiable cheirality layer, which allows for end-to-end learning of camera pose. We perform extensive qualitative and quantitative evaluation of the proposed DiffPoseNet’s sensitivity to noise and its generalization across datasets. We compare our approach to existing state-of-the-art methods on KITTI, TartanAir, and TUM-RGBD datasets.more » « less
-
High-quality 3D image recognition is an important component of many vision and robotics systems. However, the accurate processing of these images requires the use of compute-expensive 3D Convolutional Neural Networks (CNNs). To address this challenge, we propose the use of Spiking Neural Networks (SNNs) that are generated from iso-architecture CNNs and trained with quantization-aware gradient descent to optimize their weights, membrane leak, and firing thresholds. During both training and inference, the analog pixel values of a 3D image are directly applied to the input layer of the SNN without the need to convert to a spike-train. This significantly reduces the training and inference latency and results in high degree of activation sparsity, which yields significant improvements in computational efficiency. However, this introduces energy-hungry digital multiplications in the first layer of our models, which we propose to mitigate using a processing-in-memory (PIM) architecture. To evaluate our proposal, we propose a 3D and a 3D/2D hybrid SNN-compatible convolutional architecture and choose hyperspectral imaging (HSI) as an application for 3D image recognition. We achieve overall test accuracy of 98.68, 99.50, and 97.95% with 5 time steps (inference latency) and 6-bit weight quantization on the Indian Pines, Pavia University, and Salinas Scene datasets, respectively. In particular, our models implemented using standard digital hardware achieved accuracies similar to state-of-the-art (SOTA) with ~560.6× and ~44.8× less average energy than an iso-architecture full-precision and 6-bit quantized CNN, respectively. Adopting the PIM architecture in the first layer, further improves the average energy, delay, and energy-delay-product (EDP) by 30, 7, and 38%, respectively.more » « less
-
We present an unsupervised learning framework for simultaneously training single-view depth prediction and optical flow estimation models using unlabeled video sequences. Existing unsupervised methods often exploit brightness constancy and spatial smoothness priors to train depth or flow models. In this paper, we propose to leverage geometric consistency as additional supervisory signals. Our core idea is that for rigid regions we can use the predicted scene depth and camera motion to synthesize 2D optical flow by backprojecting the induced 3D scene flow. The discrepancy between the rigid flow (from depth prediction and camera motion) and the estimated flow (from optical flow model) allows us to impose a cross-task consistency loss. While all the networks are jointly optimized during training, they can be applied independently at test time. Extensive experiments demonstrate that our depth and flow models compare favorably with state-of-the-art unsupervised methods.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICCVW54120.2021.00183
