SketchiMo: Sketch-based Motion Editing for Articulated Characters Visual Media Lab, KAIST 2016-04-21 | SketchiMo: Sketch-based Motion Editing for Articulated CharactersByungkuk Choi, Roger Blanco i Ribera, J. P. Lewis, Yeongho Seol, Seokpyo Hong, Haegwang Eom, Sunjin Jung, Junyong NohProject page: http://vml.kaist.ac.kr/publication/journal/2016/2016ByungkukChoi_TOG.htmlConference : SIGGRAPH, 2016Journal: ACM Transaction on Graphics, Volume 35, Issue 4, p.146:1-146:12, July 2016We present SketchiMo, a novel approach for the expressive editing of articulated character motion. SketchiMo solves for the motion given a set of projective constraints that relate the sketch inputs to the unknown 3D poses. We introduce the concept of sketch space, a contextual geometric representation of sketch targets —motion properties that are editable via sketch input— that enhances, right on the viewport, different aspects of the motion. The combination of the proposed sketch targets and space allows for seamless editing of a wide range of properties, from simple joint trajectories to local parent-child spatiotemporal relationships and more abstract properties such as coordinated motions. This is made possible by interpreting the user's input through a new sketch-based optimization engine in a uniform way. In addition, our view-dependent sketch space also serves the purpose of disambiguating the user inputs by visualizing their range of effect and transparently defining the necessary constraints to set the temporal boundaries for the optimization.────────────────Visual Media Lab, KAIST373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia_at_kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
Interactive Locomotion Style Control for a Human Character based on Gait Cycle Features Visual Media Lab, KAIST 2024-05-21 | Chaelin Kim, Haegwang Eom, Jung Eun Yoo, Soojin Choi, Junyong NohJournal: Computer Graphics Forum (CGF)This article introduces a data-driven locomotion style controller for full-body human characters using gait cycle features. Based on gait analysis, we define a set of gait features that can represent various locomotion styles as spatio-temporal patterns within a single gait cycle. We compute the gait features for every single gait cycle in motion capture data and use them to search for the desired motion. Our real-time style controller provides users with visual feedback for the changing inputs, exploiting the Motion Matching algorithm. We also provide a graphical controller interface that visualizes our style representation to enable intuitive control for users. We show that the proposed method is capable of retrieving appropriate locomotions for various gait cycle features, from simple walking motions to single-foot motions such as hopping and dragging. To validate the effectiveness of our method, we conducted a user study that compares the usability and performance of our system with those of an existing footstep animation tool. The results show that our method is preferred over the baseline method for intuitive control and fast visual feedback.────────────────Visual Media Lab, KAIST373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia_at_kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
User Performance in Consecutive Temporal Pointing: An Exploratory Study Visual Media Lab, KAIST 2024-05-21 | Dawon Lee, Sunjun Kim, Junyong Noh, Byungjoo LeeConference: ACM Conference on Human Factors in Computing Systems (CHI) 2024A significant amount of research has recently been conducted on user performance in so-called temporal pointing tasks, in which a user is required to perform a button input at the timing required by the system. Consecutive temporal pointing (CTP), in which two consecutive button inputs must be performed while satisfying temporal constraints, is common in modern interactions, yet little is understood about user performance on the task. Through a user study involving 100 participants, we broadly explore user performance in a variety of CTP scenarios. The key finding is that CTP is a unique task that cannot be considered as two ordinary temporal pointing processes. Significant effects of button input method, motor limitations, and different hand use were also observed.────────────────Visual Media Lab, KAIST373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia_at_kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
Real-Time CNN Training and Compression for Neural-Enhanced Adaptive Live Streaming Visual Media Lab, KAIST 2024-03-20 | Seunghwa Jeong, Bumki Kim, Seunghoon Cha, Kwanggyoon Seo, Hayoung Chang, Jungjin Lee, Younghui Kim, Junyong NohJournal: IEEE Transactions on Pattern Analysis and Machine Intelligence 2024We propose a real-time convolutional neural network (CNN) training and compression method for delivering high-quality livevideo even in a poor network environment. The server delivers a low-resolution video segment along with the corresponding CNN forsuper resolution (SR), after which the client applies the CNN to the segment in order to recover high-resolution video frames. Togenerate a trained CNN corresponding to a video segment in real-time, our method rapidly increases the training accuracy bypromoting the overfitting property of the CNN while also using curriculum-based training. In addition, assuming that the pretrained CNNis already downloaded on the client side, we transfer only residual values between the updated and pretrained CNN parameters. Thesevalues can be quantized with low bits in real time while minimizing the amount of loss, as the distribution range is significantly narrowerthan that of the updated CNN. Quantitatively, our neural-enhanced adaptive live streaming pipeline (NEALS) achieves higher SRaccuracy and a lower CNN compression loss rate within a constrained training time compared to the state-of-the-art CNN training andcompression method. NEALS achieves 15 to 48% higher quality of the user experience compared to state-of-the-art neural-enhancedlive streaming systems.────────────────Visual Media Lab, KAIST373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia_at_kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] WALDO (Presenter: YHH) Visual Media Lab, KAIST 2023-11-13 | 2023.11.10 YHHVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
Recurrent Motion Refiner for Locomotion Stitching Visual Media Lab, KAIST 2023-11-06 | Haemin Kim, Kyungmin Cho, Seokhyeon Hong, Junyong NohJournal: Computer Graphics Forum (CGF)Project page: onlinelibrary.wiley.com/doi/full/10.1111/cgf.14920Stitching different character motions is one of the most commonly used techniques as it allows the user to make new animations that fit one’s purpose from pieces of motions. However, current motion stitching methods often produce unnatural motion with foot sliding artifacts, depending on performance of the interpolation. In this paper, we propose a novel motion stitching technique based on a Recurrent Motion Refiner (RMR) that connects discontinuous locomotions into a single natural locomotion. Our model receives different locomotions as input, in which the root of the last pose of the previous motion and that of the first pose of the next motion are aligned. During runtime, the model slides through the sequence, editing frames window by window to output a smoothly connected animation. Our model consists of a 2-layer recurrent network that comes between a simple encoder and decoder. To train this network, we created a sufficient number of paired data with a newly designed data generation. This process employs a K-nearest neighbor search that explores a predefined motion database to create the corresponding input to the ground truth. Once trained, the suggested model can connect various lengths of locomotion sequences into a single natural locomotion.────────────────Visual Media Lab, KAIST373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia_at_kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Score: A very brief overview about Score and Score-based models (Presenter: CSH) Visual Media Lab, KAIST 2023-10-16 | 2023.09.22 CSHVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Diffusion Features (Presenter: YK) Visual Media Lab, KAIST 2023-10-16 | 2023.09.15 YKVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Introduction to Statistical Analysis (Presenter: YJE) Visual Media Lab, KAIST 2023-07-04 | 2023.06.30 YJEVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Skeleton Free Character Motion Retargeting (Presenter: KCL) Visual Media Lab, KAIST 2023-07-04 | 2023.06.23 KCLVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
Online Avatar Motion Adaptation to Morphologically-similar Spaces Visual Media Lab, KAIST 2023-05-25 | Soojin Choi, Seokpyo Hong, Kyungmin Cho, Chaelin Kim, Junyong NohConference: Eurographics 2023Project page: https://vml.kaist.ac.kr/main/international/individual/196In avatar-mediated telepresence systems, a similar environment is assumed for involved spaces, so that the avatar in a remote space can imitate the user's motion with proper semantic intention performed in a local space. For example, touching on the desk by the user should be reproduced by the avatar in the remote space to correctly convey the intended meaning. It is unlikely, however, that the two involved physical spaces are exactly the same in terms of the size of the room or the locations of the placed objects. Therefore, a naive mapping of the user's joint motion to the avatar will not create the semantically correct motion of the avatar in relation to the remote environment. Existing studies have addressed the problem of retargeting human motions to an avatar for telepresence applications. Few studies, however, have focused on retargeting continuous full-body motions such as locomotion and object interaction motions in a unified manner. In this paper, we propose a novel motion adaptation method that allows to generate the full-body motions of a human-like avatar on-the-fly in the remote space. The proposed method handles locomotion and object interaction motions as well as smooth transitions between them according to given user actions under the condition of a bijective environment mapping between morphologically-similar spaces. Our experiments show the effectiveness of the proposed method in generating plausible and semantically correct full-body motions of an avatar in room-scale space.────────────────Visual Media Lab, KAIST373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia_at_kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Guided Image Inpainting with Stable Diffusion (Presenter: SKG) Visual Media Lab, KAIST 2023-05-21 | 2023.05.12 SKGVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] WRAP: A powerful tool for 3d data processing (Presenter: YSY) Visual Media Lab, KAIST 2023-04-21 | 2023.04.21 YSYVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] PointCloud Pre-Training with Natural 3D Structures (Presenter: LIY) Visual Media Lab, KAIST 2023-04-14 | 2023.04.14 LIYVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] MDM: Human Motion Diffusion Model (Presenter: HSH) Visual Media Lab, KAIST 2023-04-10 | 2023.04.07 HSHVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Audio Driven Neural Gesture Reenactment with Video Motion Graphs (Presenter: LDW) Visual Media Lab, KAIST 2023-03-24 | 2023.03.24 LDW Visual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] PointNet (Presenter: YSY) Visual Media Lab, KAIST 2023-03-03 | 2023.03.03 YSYVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Synthesizing Physical Character Scene Interactions (Presenter: SYR) Visual Media Lab, KAIST 2023-02-10 | 2023.02.10 SYR Visual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Deep Deformable 3D Caricatures with Learned Shape Control (Presenter: CSH) Visual Media Lab, KAIST 2022-11-04 | 2022.11.04 CSHVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Age Transformation Using a Style-Based Regression Model(Presenter: JJY) Visual Media Lab, KAIST 2022-10-28 | 2022.10.28 JJY Visual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] MoDi: Unconditional Motion Synthesis from Diverse Data (Presenter: KCL) Visual Media Lab, KAIST 2022-10-21 | 2022.10.21 KCLVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Learning Dynamic 3D Geometry and Texture for Video Face Swapping (Presenter: NHH) Visual Media Lab, KAIST 2022-10-20 | 2022.10.14 NHHVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Local Motion Phases for Learning Multi-contact Character Movements(Presenter: CSJ) Visual Media Lab, KAIST 2022-10-07 | 2022.10.07 CSJVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Cross Domain and Disentangled Face Manipulation with 3D Guidance (Presenter: CYS) Visual Media Lab, KAIST 2022-05-12 | 220506 Cross Domain and Disentangled Face Manipulation with 3D Guidance (Presenter: CYS)
[VML Lab Seminar] Playable Video Generation (Presenter: LDW) Visual Media Lab, KAIST 2022-04-14 | 220401 Playable Video Generation (Presenter: LDW)
[VML Lab Seminar] Distortion Aware Convolutional Filters (Presenter: PHN) Visual Media Lab, KAIST 2022-03-21 | Distortion Aware Convolutional Filters
[VML Lab Seminar] Spatio-temporal Manifold Learning (Presenter: JSJ) Visual Media Lab, KAIST 2022-03-16 | Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling
Year-End Party Praise 2021 Visual Media Lab, KAIST 2021-12-22 | ────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of Korea Tel. +82-42-350-2958Email : visualmedia_at_kaist.ac.krMore Information @http://vml.kaist.ac.kr/ http://ct.kaist.ac.kr/ http://www.kaist.ac.kr/
[VML Lab Seminar] Vision Transformers for Dense Prediction (Presenter: YJE) Visual Media Lab, KAIST 2021-11-26 | 2021.11.19 YJE Visual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] First Order Motion Model for Image Animation (Presenter: CYS) Visual Media Lab, KAIST 2021-11-15 | 2021.11.12 CYSVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] A Deep Learning Framework for Character Motion Synthesis and Editing Visual Media Lab, KAIST 2021-11-01 | 2021.10.29 CSJVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] DeepFormableTag (Presenter: KJD) Visual Media Lab, KAIST 2021-10-29 | 2021.10.15 KJDDeepFormableTag: End-to-end Generation and Recognition of Deformable Fiducial MarkersVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Stochastic Scene Aware Motion Prediction (Presenter: KCL) Visual Media Lab, KAIST 2021-10-14 | 2021.10.08 KCLVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
Deep Learning-Based Unsupervised Human Facial Retargeting Visual Media Lab, KAIST 2021-09-17 | Seonghyeon Kim, Sunjin Jung, Kwanggyoon Seo, Roger Blanco i Ribera, Junyong NohConference: Pacific Graphics 2021Project page: https://vml.kaist.ac.kr/assets/Contents/Publications/International/2021SeonghyeonKim_CGF/2021SeonghyeonKim_CGF.htmlTraditional approaches to retarget existing facial blendshape animations to other characters rely heavily on manually paired data including corresponding anchors, expressions, or semantic parametrizations to preserve the characteristics of the original performance. In this paper, inspired by recent developments in face swapping and reenactment, we propose a novel unsupervised learning method that reformulates the retargeting of 3D facial blendshape-based animations in the image domain. The expressions of a source model is transferred to a target model via the rendered images of the source animation. For this purpose, a reenactment network is trained with the rendered images of various expressions created by the source and target models in a shared latent space. The use of shared latent space enable an automatic cross-mapping obviating the need for manual pairing. Next, a blendshape prediction network is used to extract the blendshape weights from the translated image to complete the retargeting of the animation onto a 3D target model. Our method allows for fully unsupervised retargeting of facial expressions between models of different configurations, and once trained, is suitable for automatic real-time applications.────────────────Visual Media Lab, KAIST373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia_at_kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
Motion Recommendation for Online Character Control Visual Media Lab, KAIST 2021-09-17 | Kyungmin Cho, Chaelin Kim, Jungjin Park, Joonkyu Park, Junyong NohConference: SIGGRAPH Asia 2021Project page: https://vml.kaist.ac.kr/main/international/individual/183Reinforcement learning (RL) has been proven effective in many scenarios, including environment exploration and motion planning. However, its application in data-driven character control has produced relatively simple motion results compared to recent approaches that have used large complex motion data without RL. In this paper, we provide a real-time motion control method that can generate high-quality and complex motion results from various sets of unstructured data while retaining the advantage of using RL, which is the discovery of optimal behaviors by trial and error. We demonstrate the results for a character achieving different tasks, from simple direction control to complex avoidance of moving obstacles. Our system works equally well on biped/quadruped characters, with motion data ranging from 1 to 48 minutes, without any manual intervention. To achieve this, we exploit a finite set of discrete actions, where each action represents full-body future motion features. We first define a subset of actions that can be selected in each state and store these pieces of information in databases during the preprocessing step. The use of this subset of actions enables the effective learning of control policy even from a large set of motion data. To achieve interactive performance at run-time, we adopt a proposal network and a k-nearest neighbor action sampler.────────────────Visual Media Lab, KAIST373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia_at_kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Understanding and Representing Motion: Human to Character (Presenter: PJJ) Visual Media Lab, KAIST 2021-09-17 | 2021.09.17 PJJVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Reference Based Sketch Image Colorization (Presenter: SCW) Visual Media Lab, KAIST 2021-09-07 | 2021.09.03 SCWVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] 360-Degree Textures of People in Clothing from a Single Image (Presenter: CSH) Visual Media Lab, KAIST 2021-07-31 | 2021.07.30 CSHVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] PCA: Principal Component Analysis (Presenter: PJK) Visual Media Lab, KAIST 2021-07-24 | 2021.07.23 PJKVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] SinGAN: Learning a Generative Model from a Single Natural Image (Presenter: CHY) Visual Media Lab, KAIST 2021-07-09 | 2021.07.09 CHYVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] StyleRig: Rigging StyleGAN for 3D Control over Portrait Images (Presenter: KSH) Visual Media Lab, KAIST 2021-07-03 | 2021.07.02 KSHVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
Autonomous Digital Companion - Final Demo Visual Media Lab, KAIST 2021-06-08 | Visual Media Lab, KAIST373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia_at_kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Neural Discrete Representation Learning (Presenter: CKM) Visual Media Lab, KAIST 2021-06-04 | 2021.06.04 CKM Visual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Convolutional Autoencoder for Human Motion Infilling (Presenter: KHM) Visual Media Lab, KAIST 2021-05-07 | 2021.05.07 KHMVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] ReStyle: Residual Based StyleGAN Encoder via Iterative Refinement (Presenter: SKG) Visual Media Lab, KAIST 2021-04-23 | 2021.04.23 SKGVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] GANimation (Presenter: JSJ) Visual Media Lab, KAIST 2021-04-09 | 2021.04.09 JSJVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Enhanced Geometric Techniques for point marking in Model (Presenter: KJD) Visual Media Lab, KAIST 2021-04-03 | 2021.03.05 KJDVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Web Crawling (Presenter: SHG) Visual Media Lab, KAIST 2021-04-02 | 2021.03.26 SHGVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
[VML Lab Seminar] Introduction to mTurk (Presenter: KCM) Visual Media Lab, KAIST 2021-04-02 | 2021.03.19 KCMVisual Media Lab - Weekly Lab Seminar────────────────Visual Media Lab, KAIST 373-1 Guseong-dong, Yuseong-gu Daejeon, 305-701, Republic of KoreaTel. +82-42-350-2958Email : visualmedia@kaist.ac.krMore Information @http://vml.kaist.ac.kr/http://ct.kaist.ac.kr/http://www.kaist.ac.kr/
