Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment. While learning, they repeatedly take actions based on their observation of the environment, and receive appropriate rewards which define the objective. This experience is then used to progressively improve the policy controlling the agent's behavior, typically represented by a neural network. This trained module can then be reused for similar problems, which makes this approach promising for the animation of autonomous, yet reactive characters in simulators, video games or virtual reality environments. This paper surveys the modern Deep Reinforcement Learning methods and discusses their possible applications in Character Animation, from skeletal control of a single, physically-based character to navigation controllers for individual agents and virtual crowds. It also describes the practical side of training DRL systems, comparing the different frameworks available to build such agents.
Virtual character animation control is a problem for which Reinforcement Learning (RL) is a viable approach. While current work have applied RL effectively to portray physics-based skills, social behaviours are challenging to design reward functions for, due to their lack of physical interaction with the world. On the other hand, data-driven implementations for these skills have been limited to supervised learning methods which require extensive training data and carry constraints on generalisability. In this paper, we propose RLAnimate, a novel data-driven deep RL approach to address this cha…
Motion synthesis in a dynamic environment has been a long-standing problem for character animation. Methods using motion capture data tend to scale poorly in complex environments because of their larger capturing and labeling requirement. Physics-based controllers are effective in this regard, albeit less controllable. In this paper, we present CARL, a quadruped agent that can be controlled with high-level directives and react naturally to dynamic environments. Starting with an agent that can imitate individual animation clips, we use Generative Adversarial Networks to adapt high-level control…
Instituto Nacional de Matemática Pura e Aplicada（国家纯数学与应用数学研究所）
In this paper, we propose the use of traditional animations, heuristic behavior and reinforcement learning in the creation of intelligent characters for computational media. The traditional animation and heuristic gives artistic control over the behavior while the reinforcement learning adds generalization. The use case presented is a dog character with a high-level controller in a 3D environment which is built around the desired behaviors to be learned, such as fetching an item. As the development of the environment is the key for learning, further analysis is conducted of how to build those …
Data-driven character animation based on motion capture can produce highly naturalistic behaviors and, when combined with physics simulation, can provide for natural procedural responses to physical perturbations, environmental changes, and morphological discrepancies. Motion capture remains the most popular source of motion data, but collecting mocap data typically requires heavily instrumented environments and actors. In this paper, we propose a method that enables physically simulated characters to learn skills from videos (SFV). Our approach, based on deep pose estimation and deep reinforc…
Physics-based character animation has seen significant advances in recent years with the adoption of Deep Reinforcement Learning (DRL). However, DRL-based learning methods are usually computationally expensive and their performance crucially depends on the choice of hyperparameters. Tuning hyperparameters for these methods often requires repetitive training of control policies, which is even more computationally prohibitive. In this work, we propose a novel Curriculum-based Multi-Fidelity Bayesian Optimization framework (CMFBO) for efficient hyperparameter optimization of DRL-based character c…
Learning to locomote is one of the most common tasks in physics-based animation and deep reinforcement learning (RL). A learned policy is the product of the problem to be solved, as embodied by the RL environment, and the RL algorithm. While enormous attention has been devoted to RL algorithms, much less is known about the impact of design choices for the RL environment. In this paper, we show that environment design matters in significant ways and document how it can contribute to the brittle nature of many RL results. Specifically, we examine choices related to state representations, initial…
University of California, Berkeley（加州大学伯克利分校）；University of British Columbia（不列颠哥伦比亚大学）
A longstanding goal in character animation is to combine data-driven specification of behavior with a system that can execute a similar behavior in a physical simulation, thus enabling realistic responses to perturbations and environmental variation. We show that well-known reinforcement learning (RL) methods can be adapted to learn robust control policies capable of imitating a broad range of example motion clips, while also learning complex recoveries, adapting to changes in morphology, and accomplishing user-specified goals. Our method handles keyframed motions, highly-dynamic actions such …
Animation and machine learning research have shown great advancements in the past decade, leading to robust and powerful methods for learning complex physically-based animations. However, learning can take hours or days, especially if no reference movement data is available. In this paper, we propose and evaluate a novel combination of techniques for accelerating the learning of stable locomotion movements through self-imitation learning of synthetic animations. First, we produce synthetic and cyclic reference movement using a recent online tree search approach that can discover stable walking…
Human character animation is often critical in entertainment content production, including video games, virtual reality or fiction films. To this end, deep neural networks drive most recent advances through deep learning and deep reinforcement learning. In this article, we propose a comprehensive survey on the state-of-the-art approaches based on either deep learning or deep reinforcement learning in skeleton-based human character animation. First, we introduce motion data representations, most common human motion datasets and how basic deep models can be enhanced to foster learning of spatial…
The production of animation is a resource intensive process in game companies. Therefore, techniques to synthesize animations have been developed. However, these procedural techniques offer limited adaptability by animation artists. In order to solve this, a fuzzy neural network model of the animation is proposed, where the parameters can be tuned either by machine learning techniques that use motion capture data as training data or by the animation artist himself. This paper illustrates how this real time procedural animation system can be developed, taking the human gait on flat terrain and …
2D animation is a common factor in game development, used for characters, effects and background art. It involves work that takes both skill and time, but parts of which are repetitive and tedious. Automated animation approaches exist, but are designed without animators in mind. The focus is heavily on real-life video, which follows strict laws of how objects move, and does not account for the stylistic movement often present in 2D animation. We propose a problem formulation that more closely adheres to the standard workflow of animation. We also demonstrate a model, SketchBetween, which learn…
In this paper we present a new deep learning-driven approach to image-based synthesis of animations involving humanoid characters. Unlike previous deep approaches to image-based animation our method makes no assumptions on the type of motion to be animated nor does it require dense temporal input to produce motion. Instead we generate new animations by interpolating between user chosen keyframes, arranged sparsely in time. Utilizing a novel configuration manifold learning approach we interpolate suitable motions between these keyframes. In contrast to previous methods, ours requires less data …
In animation, style can be considered as a distinctive layer over the content of a motion, allowing a character to achieve the same gesture in various ways. Editing existing animation to modify the style while keeping the same content is an interesting task, which can facilitate the re-use of animation data and cut down on production time. Existing animation edition methods either work directly on the motion data, providing precise but tedious tools, or manipulate semantic style categories, taking control away from the user. As a middle ground, we propose a new character motion edition paradig…
Dramatic progress has been made in animating individual characters. However, we still lack automatic control over activities between characters, especially those involving interactions. In this paper, we present a novel energy-based framework to sample and synthesize animations by associating the characters' body motions, facial expressions, and social relations. We propose a Spatial-Temporal And-Or graph (ST-AOG), a stochastic grammar model, to encode the contextual relationship between motion, emotion, and relation, forming a triangle in a conditional random field. We train our model from a …
This research paper addresses the problem of generating involuntary and precise animation of quadrupeds with automatic rigging system of various character types. The technique proposed through this research is based on a two tier animation control curve with base simulation being driven through dynamic mathematical model using procedural algorithm and the top layer with a custom user controlled animation provided with intuitive Graphical User Interface (GUI). The character rig is based on forward and inverse kinematics driven through trigonometric based motion equations. The User is provided w…
INESC-ID（INESC-ID（葡萄牙系统与计算机工程研究所））；Instituto Superior Técnico（高等理工学院）；University of Lisbon（里斯本大学）
Robot animation is a new form of character animation that extends the traditional process by allowing the animated motion to become more interactive and adaptable during interaction with users in real-world settings. This paper reviews how this new type of character animation has evolved and been shaped from character animation principles and practices. We outline some new paradigms that aim at allowing character animators to become robot animators, and to properly take part in the development of social robots. One such paradigm consists of the 12 principles of robot animation, which describes…
Character rigging is a process of endowing a character with a set of custom manipulators and controls making it easy to animate by the animators. These controls consist of simple joints, handles, or even separate character selection windows.This research paper present an automated rigging system for quadruped characters with custom controls and manipulators for animation.The full character rigging mechanism is procedurally driven based on various principles and requirements used by the riggers and animators. The automation is achieved initially by creating widgets according to the character ty…
Markerless motion capture is an active research in 3D virtualization. In proposed work we presented a system for markerless motion capture for 3D human character animation, paper presents a survey on motion and skeleton tracking techniques which are developed or are under development. The paper proposed a method to transform the motion of a performer to a 3D human character (model), the 3D human character performs similar movements as that of a performer in real time. In the proposed work, human model data will be captured by Kinect camera, processed data will be applied on 3D human model for …
DancingBox: A Lightweight MoCap System for Character Animation from Physical Proxies
University of Edinburgh 10 Crichton Street Edinburgh United Kingdom；Inria, Universit\' e C\ o te d'Azur 2004 route des lucioles Valbonne France；Tsinghua University No. 30 Shuangqing Road, Haidian District Beijing China；University of Edinburgh；Inria, Universit\' e C\ o te d'Azur；Tsinghua University
University of Washington（华盛顿大学）；Adobe Research（奥多比研究院）
The emergence of commercial tools for real-time performance-based 2D animation has enabled 2D characters to appear on live broadcasts and streaming platforms. A key requirement for live animation is fast and accurate lip sync that allows characters to respond naturally to other actors or the audience through the voice of a human performer. In this work, we present a deep learning based interactive system that automatically generates live lip sync for layered 2D characters using a Long Short Term Memory (LSTM) model. Our system takes streaming audio as input and produces viseme sequences with l…
This paper presents Master of Puppets (MOP), an animation-by-demonstration framework that allows users to control the motion of virtual characters (puppets) in real time. In the first step, the user is asked to perform the necessary actions that correspond to the character's motions. The user's actions are recorded, and a hidden Markov model (HMM) is used to learn the temporal profile of the actions. During the runtime of the framework, the user controls the motions of the virtual character based on the specified activities. The advantage of the MOP framework is that it recognizes and follows …
In character animation, direction invariance is a desirable property. That is, a pose facing north and the same pose facing south are considered the same; a character that can walk to the north is expected to be able to walk to the south in a similar style. To achieve such direction invariance, the current practice is to remove the facing direction's rotation around the vertical axis before further processing. Such a scheme, however, is not robust for rotational behaviors in the sagittal plane. In search of a smooth scheme to achieve direction invariance, we prove that in general a singularity…
University of Vienna（维也纳大学）；NTNU Trondheim（挪威科技大学）
Motions of virtual characters in movies or video games are typically generated by recording actors using motion capturing methods. Animations generated this way often need postprocessing, such as improving the periodicity of cyclic animations or generating entirely new motions by interpolation of existing ones. Furthermore, search and classification of recorded motions becomes more and more important as the amount of recorded motion data grows. In this paper, we will apply methods from shape analysis to the processing of animations. More precisely, we will use the by now classical elastic metr…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；University of Toronto（多伦多大学）
We present a learning method for predicting animation skeletons for input 3D models of articulated characters. In contrast to previous approaches that fit pre-defined skeleton templates or predict fixed sets of joints, our method produces an animation skeleton tailored for the structure and geometry of the input 3D model. Our architecture is based on a stack of hourglass modules trained on a large dataset of 3D rigged characters mined from the web. It operates on the volumetric representation of the input 3D shapes augmented with geometric shape features that provide additional cues for joint …
Design tools in the 3D industry, while powerful, are still tedious and labor-intensive when it comes to bringing a creative idea for a visual effect to life. In this position paper, we discussed how an infamous generative synthetic media, deepfakes, could be of use and embedded into common sophisticated 3D workflows to reduce user workloads in areas such as 3D model editing, material design, and character animation. As a case discussion, we also prototyped a tool to address the retargeting problem in character animation. Although deepfakes themselves have received a negative public image, the …
Semantic-Aware Motion Encoding for Topology-Agnostic Character Animation
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（虚拟现实技术与系统国家重点实验室，北京航空航天大学）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
University of Washington（华盛顿大学）；Facebook Inc.（脸书公司）
We present a method and application for animating a human subject from a single photo. E.g., the character can walk out, run, sit, or jump in 3D. The key contributions of this paper are: 1) an application of viewing and animating humans in single photos in 3D, 2) a novel 2D warping method to deform a posable template body model to fit the person's complex silhouette to create an animatable mesh, and 3) a method for handling partial self occlusions. We compare to state-of-the-art related methods and evaluate results with human studies. Further, we present an interactive interface that allows re…
Authoring an appealing animation for a virtual character is a challenging task. In computer-aided keyframe animation artists define the key poses of a character by manipulating its underlying skeletons. To look plausible, a character pose must respect many ill-defined constraints, and so the resulting realism greatly depends on the animator's skill and knowledge. Animation software provide tools to help in this matter, relying on various algorithms to automatically enforce some of these constraints. The increasing availability of motion capture data has raised interest in data-driven approache…
Polytechnique Montreal（蒙特利尔理工学院）；Mila（米拉研究所）；Ubisoft Montreal（育碧蒙特利尔）；Element AI
Manually authoring transition animations for a complete locomotion system can be a tedious and time-consuming task, especially for large games that allow complex and constrained locomotion movements, where the number of transitions grows exponentially with the number of states. In this paper, we present a novel approach, based on deep recurrent neural networks, to automatically generate such transitions given a past context of a few frames and a target character state to reach. We present the Recurrent Transition Network (RTN), based on a modified version of the Long-Short-Term-Memory (LSTM) n…
Computer graphics has wide range of applications which are implemented into computer animation, computer modeling among others. Since the invention of computer graphics researchers have not paid much of attentions toward the possibility of converting oral tales otherwise known as folktales into possible cartoon animated videos. This paper is based on how to develop cartoons of local folktales that will be of huge benefits to Nigerians. The activities were divided into 5 stages; analysis, design, development, implementation and evaluation which involved various processes and use of various spec…
This paper presents the three scripting commands and main functionalities of a novel character animation environment called CHASE. CHASE was developed for enabling inexperienced programmers, animators, artists, and students to animate in meaningful ways virtual reality characters. This is achieved by scripting simple commands within CHASE. The commands identified, which are associated with simple parameters, are responsible for generating a number of predefined motions and actions of a character. Hence, the virtual character is able to animate within a virtual environment and to interact with …
