The monocular depth estimation task has recently revealed encouraging prospects, especially for the autonomous driving task. To tackle the ill-posed problem of 3D geometric reasoning from 2D monocular images, multi-frame monocular methods are developed to leverage the perspective correlation information from sequential temporal frames. However, moving objects such as cars and trains usually violate the static scene assumption, leading to feature inconsistency deviation and misaligned cost values, which would mislead the optimization algorithm. In this work, we present CTA-Depth, a Context-aware Temporal Attention guided network for multi-frame monocular Depth estimation. Specifically, we first apply a multi-level attention enhancement module to integrate multi-level image features to obtain an initial depth and pose estimation. Then the proposed CTA-Refiner is adopted to alternatively optimize the depth and pose. During the CTA-Refiner process, context-aware temporal attention (CTA) is developed to capture the global temporal-context correlations to maintain the feature consistency and estimation integrity of moving objects. In particular, we propose a long-range geometry embedding (LGE) module to produce a long-range temporal geometry prior. Our approach achieves significant improvements (e.g., 13.5% for the Abs Rel metric on the KITTI dataset) over state-of-the-art approaches on three benchmark datasets.

Due to the lack of spatial cues giving merely a single image, many monocular depth estimation methods have been developed to leverage stereo or multi-view images to learn the spatial information of a scene in a self-supervised manner. However, these methods have limited performance gain since they are not able to exploit sufficient 3D geometry cues during inference, where only monocular images are available. In this work, we present V2Depth, a novel coarse-to-fine framework with Virtual View feature simulation for supervised monocular Depth estimation. Specifically, we first design a virtual-view feature simulator by leveraging the technique of novel view synthesis and contrastive learning to generate virtual view feature maps. In this way, we explicitly provide representative spatial geometry for subsequent depth estimation in both the training and inference stages. Then we introduce a 3DVA-Refiner to iteratively optimize the predicted depth map. During the optimization process, 3D-aware virtual attention is developed to capture the global spatial-context correlations to maintain the feature consistency of different views and estimation integrity of the 3D scene such as objects with occlusion relationships. Decisive improvements over state-of-the-art approaches on three benchmark datasets across all metrics demonstrate the superiority of our method.

Cooperation among unrelated individuals is pervasive in human societies, while natural selection favors the survival of the fittest. The theoretical explanation for this puzzle is a challenge across disciplines. Among other mechanisms that can promote cooperation is costly punishment, in which altruistic individuals privately bear the cost to punish defection. But it decreases the welfare of both the punisher and the punished, and defectors are hard and costly to be caught in many cases. Moreover, punishment may trigger a chain of retaliation between the punisher and the punished and induce second-order free riding - those who never punish will be better off than punishers. In this article we aim to get rid of these drawbacks by refining the mechanism of punishment. First we define an extended Public Goods game in which the defector is caught and punished with a certain probability and the cost of punishment is equally shared between the remainder of the group. Then we derive the fixation probability for one mutant cooperator to invade and take over the whole population. Our analysis shows that, when the probability for punishment is above a threshold, natural selection favors cooperating replacing defecting. Both analytical results and computer simulations show that severe punishment for a small fraction of defectors is enough for one mutant cooperator to become fixed with an advantageous probability in the population of defectors. In addition, this way of punishment can considerably decrease the total cost of inhibiting defection, especially for large populations.