Toggle light / dark theme

Neural Radiance Fields (NeRF) were first developed, greatly enhancing the quality of new vision synthesis. It was first suggested as a way to rebuild a static picture using a series of posed photographs. However, it has been swiftly expanded to include dynamic and uncalibrated scenarios. With the assistance of sizable controlled datasets, recent work additionally concentrate on animating these human radiance field models, thereby broadening the application domain of radiance-field-based modeling to provide augmented reality experiences. In this study, They are focused on the case when just one video is given. They aim to rebuild the human and static scene models and enable unique posture rendering of the person without the need for pricey multi-camera setups or manual annotations.

Neural Actor can create inventive human poses, but it needs several films. Even with the most recent improvements in NeRF techniques, this is far from a simple task. The NeRF models must be trained using many cameras, constant lighting and exposure, transparent backgrounds, and precise human geometry. According to the table below, HyperNeRF cannot be controlled by human postures but instead creates a dynamic scene based on a single video. ST-NeRF uses many cameras to rebuild each person using a time-dependent NeRF model, although the editing is only done to change the bounding box. HumanNeRF creates a human model from a single video with masks that have been carefully annotated; however, it does not demonstrate generalization to novel postures.

With a model trained on a single video, Vid2Actor can produce new human poses, but it cannot model the surroundings. They solve these issues by proposing NeuMan, a system that can create unique human stances and novel viewpoints while reconstructing the person and the scene from a single in-the-wild video. Figure 1’s high-quality pose-driven rendering is made possible by NeuMan, a cutting-edge framework for training NeRF models for both the human and the scene. They first estimate the camera poses, the sparse scene model, the depth maps, the human stance, the human form, and the human masks from a moving camera’s video.

Synopsis: How can we think rigorously about the far future, and use this to guide near-term projects? In this talk I will outline my “grand futures” project of mapping the limits of what advanced civilizations can achieve – in terms of survival, expanding in space, computation, mastery over matter and energy, and so on – and how this may interact with different theories about what truly has value.

For some fun background reading, see ‘What is the upper limit of value?‘which Anders Sandberg co-authored with David Manheim.

This talk is part of the ‘Stepping Into the Future‘conference.

Anders Sandberg is a senior research fellow at the Future of Humanity Institute at the University of Oxford and research associate at the Institute for Future Studies in Stockholm. Anders background is computational neuroscience, but for the past 20 years he has been working on neuroethics, global catastrophic risk, long-range futures and reasoning about uncertainty.

Many thanks for tuning in!

Have any ideas about people to interview? Want to be notified about future events? Any comments about the STF series?

Some of us, when we hear the word quantum (plural quanta, from the German word Quanten), might think of health supplements, a sports car, or even the television show Quantum Leap. More recently, in Marvel Studios movies such as Ant-Man, Doctor Strange, and Avengers: Endgame, “the quantum realm” is presented where time flows differently from our ordinary reality and the Avengers may use the subatomic world “to go back in time”, a world that “is smaller than a single atom” (Woodward, 2019, para.20)

We might have also seen or known the meaning of words such as quantum mechanics, quantum computing, and quantum entanglement, but what is a quantum and how does it relate to our ordinary realm?

A quantum is a word that refers to “how much”; it is a specific amount. For example, if the speed of your car happens to be quantized in increments of 10 mph, then as you accelerate your car from 10 mph, the speed will jump to 20 mph, without passing through any speed between 10 mph and 20 mph. A speed of 12 mph or 19 mph is excluded because the speed of your car can only exist in those increments of 10 mph.

Oxford quantum physicist Nikita Gourianov tore into the quantum computing industry this week, comparing the “fanfare” around the tech to a financial bubble in a searing commentary piece for the Financial Times.

In other words, he wrote, it’s far more hype than substance.

It’s a scathing, but also perhaps insightful, analysis of a burgeoning field that, at the very least, still has a lot to prove.

A multinational group of scientists has made progress in the use of antiferromagnetic materials in memory storage devices.

Antiferromagnets are materials with an internal magnetic field induced by electron spin but virtually no external magnetic field. Since there is no external (or “long-range”) magnetic field, the data units, or bits, may be packed more densely inside the material, making them potentially useful for data storage.

The ferromagnets commonly utilized in typical magnetic memory devices are the opposite. These devices do have long-range magnetic fields produced by the bits that prevent them from being packed too tightly together since otherwise they would interact.

You need to wait till 2023 to get them though.

Lenovo has unveiled its T1 Glasses at its Tech Life 2022 event and promises to place a full HD video-watching experience right inside your pockets, a company press release.

Mobile computing devices have exploded in the past few years as gaming has become more intense, and various video streaming platforms have gathered steam. The computing power of smartphones and tablets has increased manifold. Whether you want to ambush other people in an online shooting game or sit back and watch a documentary in high-definition, a device in your pocket can help you do that with ease.

However, what is missing is the large screen experience; with the T1 Glasses, Lenovo wants to deliver just that.