Because of the generality of Definition 1.1, it may be that

For safety and robustness of AI systems, we introduce topological parallax as a theoretical and computational tool that compares a trained model to a reference dataset to determine whether they have similar multiscale geometric structure. Our proofs and examples show that this geometric similarity between dataset and model is essential to trustworthy interpolation and perturbation, and we conjecture that this new concept will add value to the current debate regarding the unclear relationship between "overfitting" and "generalization" in applications of deeplearning. In typical DNN applications, an explicit geometric description of the model is impossible, but parallax can estimate topological features (components, cycles, voids, etc.) in the model by examining the effect on the Rips complex of geodesic distortions using the reference dataset. Thus, parallax indicates whether the model shares similar multiscale geometric features with the dataset. Parallax presents theoretically via topological data analysis [TDA] as a bi-filtered persistence module, and the key properties of this module are stable under perturbation of the reference dataset.

A gaze-fixating robot perceives distance to the fixated object and relative positions of surrounding objects immediately, accurately, and robustly. We show how fixation, which is the act of looking at one object while moving, exploits regularities in the geometry of 3D space to obtain this information. These regularities introduce rotation-translation couplings that are not commonly used in structure from motion. To validate, we use a Franka Emika Robot with an RGB camera. We a) find that error in distance estimate is less than 5 mm at a distance of 15 cm, and b) show how relative position can be used to find obstacles under challenging scenarios. We combine accurate distance estimates and obstacle information into a reactive robot behavior that is able to pick up objects of unknown size, while impeded by unforeseen obstacles. Project page: https://oxidification.com/p/one-object-at-a-time/ .

The virtual viewpoint is perceived as a new technique in virtual navigation, as yet not supported due to the lack of depth information and obscure camera parameters. In this paper, a method for achieving close-up virtual view is proposed and it only uses optical flow to build parallax effects to realize pseudo 3D projection without using depth sensor. We develop a bidirectional optical flow method to obtain any virtual viewpoint by proportional interpolation of optical flow. Moreover, with the ingenious application of the optical-flow-value, we achieve clear and visual-fidelity magnified results through lens stretching in any corner, which overcomes the visual distortion and image blur through viewpoint magnification and transition in Google Street View system.

When used by autonomous vehicles for trajectory planning or obstacle avoidance, depth estimation methods need to be reliable. Therefore, estimating the quality of the depth outputs is critical. In this paper, we show how M4Depth, a state-of-the-art depth estimation method designed for unmanned aerial vehicle (UAV) applications, can be enhanced to perform joint depth and uncertainty estimation. For that, we present a solution to convert the uncertainty estimates related to parallax generated by M4Depth into uncertainty estimates related to depth, and show that it outperforms the standard probabilistic approach. Our experiments on various public datasets demonstrate that our method performs consistently, even in zero-shot transfer. Besides, our method offers a compelling value when compared to existing multi-view depth estimation methods as it performs similarly on a multi-view depth estimation benchmark despite being 2.5 times faster and causal, as opposed to other methods. The code of our method is publicly available at https://github.com/michael-fonder/M4DepthU .

Researchers have developed a new method to detect rogue planets outside the solar system, worlds that wander their galaxies alone without a parent star. The technique, devised by NASA Goddard Space Flight Center scientist, Richard K. Barry, unites astronomy's future--in the form of the soon-to-launch Nancy Grace Roman Space Telescope--with its past, a method used by 19th-century astronomers to measure distances. The Contemporaneous LEnsing Parallax and Autonomous TRansient Assay (CLEoPATRA) mission will use parallax to measure distances, but the method will be bolstered by artificial intelligence (AI) developed by Dr. Greg Olmschenk. Olmschenk's program, RApid Machine learnEd Triage (RAMjET), will learn patterns through provided examples filtering out useless information and ensuring that of the millions of stars observed by CLEoPATRA per hour, only useful information is transmitted back to Earth. Recent research published in The Astronomical Journal suggests that exoplanets that exist in the Universe without a parent star could be more common than stars themselves, but until now spotting them has been difficult.

Homography estimation is an important task in computer vision, such as image stitching, video stabilization, and camera calibration. Traditional homography estimation methods heavily depend on the quantity and distribution of feature points, leading to poor robustness in textureless scenes. The learning solutions, on the contrary, try to learn robust deep features but demonstrate unsatisfying performance in the scenes of low overlap rates. In this paper, we address the two problems simultaneously, by designing a contextual correlation layer, which can capture the long-range correlation on feature maps and flexibly be bridged in a learning framework. In addition, considering that a single homography can not represent the complex spatial transformation in depth-varying images with parallax, we propose to predict multi-grid homography from global to local. Moreover, we equip our network with depth perception capability, by introducing a novel depth-aware shape-preserved loss. Extensive experiments demonstrate the superiority of our method over other state-of-the-art solutions in the synthetic benchmark dataset and real-world dataset. The codes and models will be available at https://github.com/nie-lang/Multi-Grid-Deep-Homogarphy.

Kentucky Route Zero has won "game of the year" awards multiple times, was dubbed the "best musical of 2014," and has been called "the most important game of the decade"--and all this before it was finished. Over the past seven years, the three-person indie studio Cardboard Computer has released four episodic "acts" of its critically acclaimed game, along with four playable "interludes." Fans have eagerly awaited the fifth and final chapter, the one where maybe, just maybe, you will arrive at your destination. It's finally here, part of a new collected edition from Annapurna Interactive for PC and console. The menu takes the shape of a circle, each act arranged around it like numbers on a clock face.

At the RSA conference in February, Alphabet Chairman Eric Schmidt, Google's former CEO, said that when he and other computer scientists started working on AI problems in the 1970s, they didn't think that the proverbial bad guys would take a strong interest.