Search

Efficient rendering of photo-realistic virtual worlds is a long standing effort of computer graphics. Modern graphics techniques have succeeded in synthesizing photo-realistic images from hand-crafted scene representations. However, the automatic generation of shape, materials, lighting, and other aspects of scenes remains a challenging problem that, if solved, would make photo-realistic computer graphics more widely accessible. Concurrently, progress in computer vision and machine learning have given rise to a new approach to image synthesis and editing, namely deep generative models. Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e.g., by the integration of differentiable rendering into network training. With a plethora of applications in computer graphics and vision, neural rendering is poised to become a new area in the graphics community, yet no survey of this emerging field exists. This state-of-the-art report summarizes the recent trends and applications of neural rendering. We focus on approaches that combine classic computer graphics techniques with deep generative models to obtain controllable and photo-realistic outputs. Starting with an overview of the underlying computer graphics and machine learning concepts, we discuss critical aspects of neural rendering approaches. This state-of-the-art report is focused on the many important use cases for the described algorithms such as novel view synthesis, semantic photo manipulation, facial and body reenactment, relighting, free-viewpoint video, and the creation of photo-realistic avatars for virtual and augmented reality telepresence. Finally, we conclude with a discussion of the social implications of such technology and investigate open research problems., Comment: Eurographics 2020 survey paper

SARS-COV-2 identified as COVID-19 in Wuhan city of China in the month of December, 2019 has now been declared as pandemic by World Health Organization whose transmission chain and cure both have emerged as a tough problem for the medical fraternity. The reports pertaining to the treatment of this pandemic are still lacking. We firmly believe that Nature itself provides a simple solution for any complicated problem created in it which motivated us to carry out In Silico investigations on some bioactive natural compounds reportedly found in the fruits and leaves of Anthocephalus Cadamba which is a miraculous plant found on the earth aiming to predict the potential inhibitors against aforesaid virus. Having modeled the ground state ligand structure of the such nine natural compounds applying density functional theory at B3LYP/631+G (d, p) level we have performed their molecular docking with SARS-COV-2 protease to calculate the binding affinity as well as to screen the binding at S-protein site during ligand-protein interactions. Out of these nine studied naturally occurring compounds; Oleanic Acid has been appeared to be potential inhibitor for COVID-19 followed by Ursolic Acid, IsoVallesiachotamine,Vallesiachotamine,Cadambine,Vincosamide-N-Oxide, Isodihydroamino-cadambine, Pentyle Ester of Chlorogenic Acid and D-Myo-Inositol. Hence these bioactive natural compounds or their structural analogs may be explored as anti-COVID19 drug agent which will be possessing the peculiar feature of cost-less synthesis and less or no side effect due to their natural occurrence. The solubility and solvent-effect related to the phytochemicals may be the point of concern. The In-vivo investigations on these proposed natural compounds or on their structural analogs are invited for designing and developing the potential medicine/vaccine for the treatment of COVID-19 pandemic., Comment: This research is dedicated to the peoples who have lost the lives, been struggling for the lives, been working hard to save the lives as well as been frightened for the lives while fighting against the pandemic COVID-19 i.e. the all CORONA WARRIORS

StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination. Three-dimensional morphable face models (3DMMs) on the other hand offer control over the semantic parameters, but lack photorealism when rendered and only model the face interior, not other parts of a portrait image (hair, mouth interior, background). We present the first method to provide a face rig-like control over a pretrained and fixed StyleGAN via a 3DMM. A new rigging network, RigNet is trained between the 3DMM's semantic parameters and StyleGAN's input. The network is trained in a self-supervised manner, without the need for manual annotations. At test time, our method generates portrait images with the photorealism of StyleGAN and provides explicit control over the 3D semantic parameters of the face., Comment: CVPR 2020 (Oral). Project page: https://gvv.mpi-inf.mpg.de/projects/StyleRig/

We construct a family of $S_n$ modules indexed by $c\in\{1,\dots,n\}$ with the property that upon restriction to $S_{n-1}$ they recover the classical parking function representation of Haiman. The construction of these modules relies on an $S_n$-action on a set that is closely related to the set of parking functions. We compute the characters of these modules and use the resulting description to classify them up to isomorphism. In particular, we show that the number of isomorphism classes is equal to the number of divisors $d$ of $n$ satisfying $ d\neq 2 \: (\!\!\!\!\mod 4)$. In the cases $c=n$ and $c=1$, we compute the number of orbits. Based on empirical evidence, we conjecture that when $c=1$, our representation is $h$-positive and is in fact the (ungraded) extension of the parking function representation constructed by Berget and Rhoades., Comment: 16 pages; comments welcome

The authors have withdrawn this paper due to an error in the proof of Lemma 3.4. -------------------------------------------------------------------------------------------- The authors have withdrawn this paper due to an error in the proof of Lemma 3.4z(Assadi, Chen, and Khanna, 2019) define a 4-player hidden-pointer-chasing ($\mathsf{HPC}^4$), and using it, give strong multi-pass lower bounds for graph problems in the streaming model of computation and a lower bound on the query complexity of sub-modular minimization. We present a two-player version ($\mathsf{HPC}^2$) of $\mathsf{HPC}^4$ that has matching communication complexity to $\mathsf{HPC}^4$. Our formulation allows us to lower bound its communication complexity with a simple direct-sum argument. Using this lower bound on the communication complexity of $\mathsf{HPC}^2$, we retain the streaming and query complexity lower bounds by (Assadi, Chen, and Khanna, 2019). Further, by giving reductions from $\mathsf{HPC}^2$, we prove new multi-pass space lower bounds for graph problems in turnstile streams. In particular, we show that any algorithm which computes the exact weight of the maximum weighted matching in an $n$-vertex graph requires $\tilde{O}(n^{2})$ space unless it makes $\omega(\log n)$ passes over the turnstile stream, and that any algorithm which computes the minimum $s\text{-}t$ distance in an $n$-vertex graph requires $n^{2-o(1)}$ space unless it makes $n^{\Omega(1)}$ passes over the turnstile stream. Our reductions can be modified to use $\mathsf{HPC}^4$ as well., Comment: The authors have withdrawn this paper due to an error in the proof of Lemma 3.4

We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs). We propose two near-optimal and oracle-efficient algorithms for FMDPs. Assuming oracle access to an FMDP planner, they enjoy a Bayesian and a frequentist regret bound respectively, both of which reduce to the near-optimal bound $\widetilde{O}(DS\sqrt{AT})$ for standard non-factored MDPs. We propose a tighter connectivity measure, factored span, for FMDPs and prove a lower bound that depends on the factored span rather than the diameter $D$. In order to decrease the gap between lower and upper bounds, we propose an adaptation of the REGAL.C algorithm whose regret bound depends on the factored span. Our oracle-efficient algorithms outperform previously proposed near-optimal algorithms on computer network administration simulations.

Tropical curves in $\mathbb{R}^2$ correspond to metric planar graphs but not all planar graphs arise in this way. We describe several new classes of graphs which cannot occur. For instance, this yields a full combinatorial characterization of the tropically planar graphs of genus at most five.

The recent experimental observations of decaying energy oscillations in semiconductor-superconductor Majorana nanowires is in contrast with the typical expectations based on the presence of Majorana zero modes localized at the ends of the system, when the amplitude of the hybridization energy oscillations is predicted to increase with the applied magnetic field. These observations have been theoretically justified recently by considering a position-dependent, step-like spin-orbit coupling near end of the nanowire, which could arise due to the presence of tunnel gates in a standard tunneling conductance experiment. Here, we show that the window in parameter space where this phenomenology occurs is vanishingly small, when compared to the parameter region where Majorana oscillations increase in amplitude with the applied field. Further, including a position-dependent effective potential, which is also induced naturally near the end of the wire by, e.g., tunnel gates, practically removes the small window associated with decaying oscillations. Using extensive numerical calculations, we show that, as expected, increasing amplitude oscillations of the hybridization energy represent a generic property of topological Majorana zero modes, while decreasing amplitude oscillations are a generic property of low-energy trivial Andreev bound states that typically emerge in non-homogeneous systems. By averaging over several realistic parameter configurations, we identify robust features of the hybridization energy that can be observed in a typical differential conductance experiment without fine-tuning the control parameters., Comment: 12 pages, 7 figures

This paper analyses how Time Series Analysis techniques can be applied to capture movement of an exchange traded index in a stock market. Specifically, Seasonal Auto Regressive Integrated Moving Average (SARIMA) class of models is applied to capture the movement of Nifty 50 index which is one of the most actively exchange traded contracts globally [1]. A total of 729 model parameter combinations were evaluated and the most appropriate selected for making the final forecast based on AIC criteria [8]. NIFTY 50 can be used for a variety of purposes such as benchmarking fund portfolios, launching of index funds, exchange traded funds (ETFs) and structured products. The index tracks the behaviour of a portfolio of blue chip companies, the largest and most liquid Indian securities and can be regarded as a true reflection of the Indian stock market [2].

We present Neural Voice Puppetry, a novel approach for audio-driven facial video synthesis. Given an audio sequence of a source person or digital assistant, we generate a photo-realistic output video of a target person that is in sync with the audio of the source input. This audio-driven facial reenactment is driven by a deep neural network that employs a latent 3D face model space. Through the underlying 3D representation, the model inherently learns temporal stability while we leverage neural rendering to generate photo-realistic output frames. Our approach generalizes across different people, allowing us to synthesize videos of a target actor with the voice of any unknown source actor or even synthetic voices that can be generated utilizing standard text-to-speech approaches. Neural Voice Puppetry has a variety of use-cases, including audio-driven video avatars, video dubbing, and text-driven video synthesis of a talking head. We demonstrate the capabilities of our method in a series of audio- and text-based puppetry examples, including comparisons to state-of-the-art techniques and a user study., Comment: Video: https://youtu.be/s74_yQiJMXA Project/Demo/Code: https://justusthies.github.io/posts/neural-voice-puppetry/

We investigate two perturbation approaches to overcome conservatism that optimism based algorithms chronically suffer from in practice. The first approach replaces optimism with a simple randomization when using confidence sets. The second one adds random perturbations to its current estimate before maximizing the expected reward. For non-stationary linear bandits, where each action is associated with a $d$-dimensional feature and the unknown parameter is time-varying with total variation $B_T$, we propose two randomized algorithms, Discounted Randomized LinUCB (D-RandLinUCB) and Discounted Linear Thompson Sampling (D-LinTS) via the two perturbation approaches. We highlight the statistical optimality versus computational efficiency trade-off between them in that the former asymptotically achieves the optimal dynamic regret $\tilde{O}(d^{7/8} B_T^{1/4}T^{3/4})$, but the latter is oracle-efficient with an extra logarithmic factor in the number of arms compared to minimax-optimal dynamic regret. In a simulation study, both algorithms show outstanding performance in tackling conservatism issue that Discounted LinUCB struggles with., Comment: An earlier version of this manuscript claimed two perturbation based algorithm and their dynamic regret upper bounds. The argument contained a technical mistake, and the current version presents a fix which deteriorates their dynamic regret bounds from $\tilde{O}(T^{2/3})$ to $\tilde{O}(T^{3/4})$