Visual Features and Their Own Optical Flow

Symmetries, invariances and conservation equations have always been an invaluable guide in Science to model natural phenomena through simple yet effective relations. For instance, in computer vision, translation equivariance is typically a built-in property of neural architectures that are used to solve visual tasks; networks with computational layers implementing such a property are known as Convolutional Neural Networks (CNNs). This kind of mathematical symmetry, as well as many others that have been recently studied, are typically generated by some underlying group of transformations (translations in the case of CNNs, rotations, etc.) and are particularly suitable to process highly structured data such as molecules or chemical compounds which are known to possess those specific symmetries. When dealing with video streams, common built-in equivariances are able to handle only a small fraction of the broad spectrum of transformations encoded in the visual stimulus and, therefore, the corresponding neural architectures have to resort to a huge amount of supervision in order to achieve good generalization capabilities. In the paper we formulate a theory on the development of visual features that is based on the idea that movement itself provides trajectories on which to impose consistency. We introduce the principle of Material Point Invariance which states that each visual feature is invariant with respect to the associated optical flow, so that features and corresponding velocities are an indissoluble pair. Then, we discuss the interaction of features and velocities and show that certain motion invariance traits could be regarded as a generalization of the classical concept of affordance. These analyses of feature-velocity interactions and their invariance properties leads to a visual field theory which expresses the dynamical constraints of motion coherence and might lead to discover the joint evolution of the visual features along with the associated optical flows.

Optical Flow Estimation by Matching Time Surface with Event-Based Cameras

In this work, we propose a novel method of estimating optical flow from event-based cameras by matching the time surface of events. The proposed loss function measures the timestamp consistency between the time surface formed by the latest timestamp of each pixel and the one that is slightly shifted in time. This makes it possible to estimate dense optical flows with high accuracy without restoring luminance or additional sensor information. In the experiment, we show that the gradient was more correct and the loss landscape was more stable than the variance loss in the motion compensation approach. In addition, we show that the optical flow can be estimated with high accuracy by optimization with L1 smoothness regularization using publicly available datasets.

New Measures of Visual Scanning Efficiency and Cognitive Effort

Visual scanning plays an important role in sampling visual information from the surrounding environments for a lot of everyday sensorimotor tasks, such as walking and car driving. In this paper, we consider the problem of visual scanning mechanism underpinning sensorimotor tasks in 3D dynamic environments. We exploit the use of eye tracking data as a behaviometric, for indicating the visuo-motor behavioral measures in the context of virtual driving. A new metric of visual scanning efficiency (VSE), which is defined as a mathematical divergence between a fixation distribution and a distribution of optical flows induced by fixations, is proposed by making use of a widely-known information theoretic tool, namely the square root of Jensen-Shannon divergence. Based on the proposed efficiency metric, a cognitive effort measure (CEM) is developed by using the concept of quantity of information. Psychophysical eye tracking studies, in virtual reality based driving, are conducted to reveal that the new metric of visual scanning efficiency can be employed very well as a proxy evaluation for driving performance. In addition, the effectiveness of the proposed cognitive effort measure is demonstrated by a strong correlation between this measure and pupil size change. These results suggest that the exploitation of eye tracking data provides an effective behaviometric for sensorimotor activity.

Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow

A major challenge for video semantic segmentation is the lack of labeled data. In most benchmark datasets, only one frame of a video clip is annotated, which makes most supervised methods fail to utilize information from the rest of the frames. To exploit the spatio-temporal information in videos, many previous works use pre-computed optical flows, which encode the temporal consistency to improve the video segmentation. However, the video segmentation and optical flow estimation are still considered as two separate tasks. In this paper, we propose a novel framework for joint video semantic segmentation and optical flow estimation. Semantic segmentation brings semantic information to handle occlusion for more robust optical flow estimation, while the non-occluded optical flow provides accurate pixel-level temporal correspondences to guarantee the temporal consistency of the segmentation. Moreover, our framework is able to utilize both labeled and unlabeled frames in the video through joint training, while no additional calculation is required in inference. Extensive experiments show that the proposed model makes the video semantic segmentation and optical flow estimation benefit from each other and outperforms existing methods under the same settings in both tasks.

Consistent Video Style Transfer via Compound Regularization

Recently, neural style transfer has drawn many attentions and significant progresses have been made, especially for image style transfer. However, flexible and consistent style transfer for videos remains a challenging problem. Existing training strategies, either using a significant amount of video data with optical flows or introducing single-frame regularizers, have limited performance on real videos. In this paper, we propose a novel interpretation of temporal consistency, based on which we analyze the drawbacks of existing training strategies; and then derive a new compound regularization. Experimental results show that the proposed regularization can better balance the spatial and temporal performance, which supports our modeling. Combining with the new cost formula, we design a zero-shot video style transfer framework. Moreover, for better feature migration, we introduce a new module to dynamically adjust inter-channel distributions. Quantitative and qualitative results demonstrate the superiority of our method over other state-of-the-art style transfer methods. Our project is publicly available at: https://daooshee.github.io/CompoundVST/.