Meta tags:
author=Peizhuo Li;
description=Direct Doctorate in Computer Science;

Headings (most frequently used words):

motion, with, via, neural, synthesis, in, dancing, pose, cross, retargeting, aware, from, search, short, bio, recent, publications, peizhuo, li, direct, doctorate, computer, science, igl, eth, zurich, interests, education, gradient, descent, the, alps, abstracted, low, poly, stylization, and, fabrication, points, synthesizing, ballroom, three, point, inputs, to, domain, prior, walkthedog, morphology, alignment, phase, manifolds, garment, dynamics, manifold, transformers, example, based, generative, matching, modi, unconditional, diverse, data, ganimator, single, sequence, learning, skeletal, articulations, blend, shapes, skeleton, networks, for, deep, cite,

Text of the page (most frequently used words):
peizhuo (15), #motion (15), cite (11), olga (11), sorkine (11), hornung (11), paper (10), and (10), code (9), supplemental (9), website (9), graphics (8), computer (7), the (6), for (6), siggraph (6), learning (6), neural (6), with (6), chen (5), generative (5), from (5), synthesis (5), acm (4), transactions (4), tog (4), baoquan (4), kfir (4), aberman (4), deep (4), data (4), present (4), motions (4), diverse (4), introduce (3), novel (3), retargeting (3), 2021 (3), ganimator (3), that (3), via (3), 2024 (3), animation (3), pose (3), character (3), dancing (3), direct (3), doctorate (3), daniel (2), cohen (2), driven (2), between (2), which (2), have (2), different (2), structure (2), aware (2), networks (2), rana (2), hanocka (2), characters (2), skeletal (2), model (2), single (2), short (2), sequence (2), 2023 (2), yet (2), synthesizing (2), matching (2), based (2), forum (2), wang (2), modeling (2), manifold (2), yuting (2), sebastian (2), starke (2), approach (2), phase (2), cross (2), prior (2), 2026 (2), ballroom (2), low (2), poly (2), peking (2), university (2), science (2), eth (2), zurich (2), student (2), geometry (2), prof (2), lab (2), download, copy, powered, hugo, academic, theme, 2020, dani, lischinski, framework, skeletons, may, skeleton, libin, liu, develop, technique, articulating, using, enveloping, pre, defined, essential, articulations, blend, shapes, 2022, zihan, zhang, learns, synthesize, cvpr, inbal, leibovitch, sigal, raab, emergence, revolutionized, remains, challenging, modi, unconditional, live, demo, xuelin, weiyu, genmm, mines, many, possible, example, eurographics, duygu, ceylan, timur, levent, kesdogan, tuanfeng, solutions, dynamic, garments, significantly, advanced, especially, context, garment, dynamics, transformers, technical, papers, track, learn, common, datasets, across, such, human, dog, walkthedog, morphology, alignment, manifolds, symposium, sca, gordon, wetzstein, yifan, qingqing, zhao, uses, accessible, generate, plausible, transferring, domain, arxiv, structured, expressive, category, its, highly, movement, complex, interactions, leader, points, three, point, inputs, overview, video, supplementary, project, page, jing, ren, marcel, padilla, danielle, luterbacher, aviv, segall, annika, oehri, tanguy, magne, alexandre, binninger, ruben, wiersma, vector, art, represents, image, small, set, flat, shaded, polygons, limited, color, palette, making, results, easy, gradient, descent, alps, abstracted, stylization, fabrication, recent, publications, turing, class, bsc, 2017, education, interests, name, 李沛卓, under, supervision, research, lies, intersection, emphasis, control, models, well, related, problems, physics, phd, study, was, researcher, advised, visual, computing, interactive, bio, igl, automatic, dark, light, search,

Text of the page (random words):
peizhuo li search peizhuo li peizhuo li light dark automatic peizhuo li direct doctorate in computer science igl eth zurich short bio my name is peizhuo li 李沛卓 i am a direct doctorate student at interactive geometry lab under the supervision of prof olga sorkine hornung my research lies at the intersection of deep learning and computer graphics with an emphasis on modeling control and generative models for character animation as well as related problems in geometry and physics prior to my phd study i was a student researcher at visual computing and learning lab at peking university and advised by prof baoquan chen interests computer graphics character animation deep learning education direct doctorate 2021 present eth zurich bsc in computer science 2017 2021 turing class peking university recent publications gradient descent in the alps abstracted low poly stylization and fabrication low poly vector art represents an image with a small set of flat shaded polygons and a limited color palette making results easy to ruben wiersma alexandre binninger peizhuo li tanguy magne annika oehri aviv segall danielle luterbacher marcel padilla jing ren olga sorkine hornung siggraph 2026 cite project page paper supplementary overview video code dancing points synthesizing ballroom dancing with three point inputs ballroom dancing is a structured yet expressive motion category its highly diverse movement and complex interactions between leader peizhuo li sebastian starke yuting ye olga sorkine hornung arxiv 2026 cite website paper supplemental pose to motion cross domain motion retargeting with pose prior we introduce a neural motion synthesis approach that uses accessible pose data to generate plausible character motions by transferring qingqing zhao peizhuo li wang yifan olga sorkine hornung gordon wetzstein symposium on computer animation sca 2024 computer graphics forum cite website paper supplemental code walkthedog cross morphology motion alignment via phase manifolds we introduce a novel approach to learn a common phase manifold from motion datasets across different characters such as human and dog peizhuo li sebastian starke yuting ye olga sorkine hornung siggraph 2024 technical papers track cite website paper supplemental code neural garment dynamics via manifold aware transformers data driven and learning based solutions for modeling dynamic garments have significantly advanced especially in the context of peizhuo li tuanfeng y wang timur levent kesdogan duygu ceylan olga sorkine hornung eurographics 2024 computer graphics forum cite website paper supplemental code example based motion synthesis via generative motion matching we present generative motion matching genmm a generative model that mines as many diverse motions as possible from a weiyu li xuelin chen peizhuo li olga sorkine hornung baoquan chen siggraph 2023 acm transactions on graphics tog cite website live demo paper supplemental code modi unconditional motion synthesis from diverse data the emergence of neural networks revolutionized motion synthesis yet synthesizing diverse motions remains challenging we present sigal raab inbal leibovitch peizhuo li kfir aberman olga sorkine hornung daniel cohen or cvpr 2023 cite website paper supplemental code ganimator neural motion synthesis from a single sequence we present ganimator a generative model that learns to synthesize novel motions from a single short motion sequence ganimator peizhuo li kfir aberman zihan zhang rana hanocka olga sorkine hornung siggraph 2022 acm transactions on graphics tog cite website paper supplemental code learning skeletal articulations with neural blend shapes we develop a neural technique for articulating 3d characters using enveloping with a pre defined skeletal structure which is essential peizhuo li kfir aberman rana hanocka libin liu olga sorkine hornung baoquan chen siggraph 2021 acm transactions on graphics tog cite website paper supplemental code skeleton aware networks for deep motion retargeting we introduce a novel deep learning framework for data driven motion retargeting between skeletons which may have different structure kfir aberman peizhuo li dani lischinski olga sorkine hornung daniel cohen or baoquan chen siggraph 2020 acm transactions on graphics tog cite website paper supplemental code powered by the academic theme for hugo cite copy download