見出し画像

#SIGGRAPH2023 Technical Papers (for me)

しらいはかせ(AI研究/Hacker作家)

SIGGRAPH2023 技術論文の中から白井の興味を抜き出しておきました。
（追記）加筆できるものは加筆しておきます。

まずは自分のPosters発表

https://s2023.siggraph.org/full-program/

Sunday, 6 August 2023


6pm - 8:30pm PDT Technical Paper
Papers Fast Forward West Hall B
Livestreamed Recorded


Monday, 7 August 2023


基調講演: 量子コンピュータのnextは何か

10:45am - 12:15pm Motion Recipes and Simulation

Yi Zhou Room 502 AB

10:45am - 10:56am PDT

Anatomically Detailed Simulation of Human TorsoAuthorsSeunghwan LeeYifeng JiangC. Karen LiuLivestreamedRecorded

10:56am - 11:07am PDT

HACK: Learning a Parametric Head and Neck Model for High-fidelity AnimationAuthorsLongwen ZhangZijun ZhaoXinzhou CongQixuan ZhangShuqi GuYuchong GaoRui ZhengWei YangLan XuJingyi YuLivestreamedRecorded

11:07am - 11:17am PDT

Bidirectional GaitNet: A Bidirectional Prediction Model of Human Gait and Anatomical ConditionsAuthorsJungnam ParkMoon Seok ParkJehee LeeJungdam WonLivestreamedRecorded

11:17am - 11:27am PDT

Acting as Inverse Inverse Planning

AuthorsKartik ChandraTzu-Mao LiJoshua TenenbaumJonathan Ragan-Kelley

11:27am - 11:37am PDT

PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling

AuthorsZhe LiZerong ZhengYuxiao LiuBoyao ZhouYebin Liu

リモート講演だったけどこれはなかなか良かった


11:37am - 11:47am PDT

DARAM: Dynamic Avatar-human Motion Remapping Technique for Realistic Virtual Stair Ascending Motions

Authors SooBin LimSeungWon SeoHyeongYeop Kang

11:47am - 12:15pm PDTMotion Recipes and Simulation - Q&A and Interactive Discussion

PoseVocabの著者に、今後のアプリケーションを考える上で、クエリーインターフェイスについて具体的なアイディアや参照すべき研究があれば聞きたかったけどリモートで不在。残念。

2pm - 3:30pm PDT Technical Paper

Character Animation: Knowing What To Do With Your Hands

これは絶対みたいやつなので別途レポートしました

Michael Neff Petree Hall C

2pm - 2:11pm PDT

GestureDiffuCLIP: Gesture Diffusion Model With CLIP LatentsAuthorsTenglong AoZeyi ZhangLibin LiuLivestreamedRecorded

2:11pm - 2:22pm PDT

Bodyformer: Semantics-guided 3D Body Gesture Synthesis With TransformerAuthorsKunkun PangDafei QinYingruo FanJulian HabekostTakaaki ShiratoriJunichi YamagishiTaku KomuraLivestreamedRecorded

2:22pm - 2:33pm PDT

Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion ModelsAuthorsSimon AlexandersonRajmund NagyJonas BeskowGustav Eje HenterLivestreamedRecorded

2:33pm - 2:44pm PDT

How Important Are Detailed Hand Motions for Communication for a Virtual Character Through the Lens of Charades?AuthorsAlex AdkinsAline NormoyleLorraine LinYu SunYuting YeMassimiliano Di LucaSophie JörgLivestreamedRecorded

2:44pm - 2:55pm PDT

Contact Edit: Artist Tools for Intuitive Modeling of Hand-object InteractionsAuthorsArjun LakshmipathyNicole FengYu Xi LeeMoshe MahlerNancy PollardLivestreamedRecorded

2:55pm - 3:05pm PDT

Synthesizing Dexterous Nonprehensile Pregrasp for Ungraspable ObjectsAuthorsSirui ChenAlbert WuC. Karen LiuLivestreamedRecorded

3:05pm - 3:30pm PDTCharacter Animation: Knowing What To Do With Your Hands - Q&A and Interactive Discussion

2pm - 3:30pm PDT Technical Paper

Image and Video Editing


Michael Wimmer Petree Hall D

2pm - 2:11pm PDT

Eventfulness for Interactive Video AlignmentAuthorsJiatian SunLongxiulin DengTriantafyllos AfourasAndrew OwensAbe DavisLivestreamedRecorded

2:11pm - 2:22pm PDT

Parsing-conditioned Anime Translation: A New Dataset and MethodAuthorsZhansheng LiYangyang XuNanxuan ZhaoYang ZhouYongtuo LiuDahua LinShengfeng HeLivestreamedRecorded

2:22pm - 2:33pm PDT

FactorMatte: Redefining Video Matting for Re-composition TasksAuthorsZeqi GuWenqi XianNoah SnavelyAbe DavisLivestreamedRecorded

2:33pm - 2:44pm PDT

Computational Long Exposure Mobile PhotographyAuthorsEric TabellionNikhil KarnadNoa GlaserBen WeissDavid JacobsYael PritchLivestreamedRecorded

2:44pm - 2:54pm PDT

Zero-shot Image-to-image TranslationAuthorsGaurav ParmarKrishna Kumar SinghRichard ZhangYijun LiJingwan LuJun-Yan ZhuLivestreamedRecorded

2:54pm - 3:04pm PDT

Key-locked Rank One Editing for Text-to-image PersonalizationAuthorsYoad TewelRinon GalGal ChechikYuval AtzmonLivestreamedRecorded

3:04pm - 3:30pm PDTImage and Video Editing - Q&A and Interactive DiscussionNot LivestreamedNot Recorded

3:45pm - 5:15pm PDT Technical Paper

Magical Sketching

Ariel Shamir Petree Hall C

3:45pm - 3:56pm PDT

HiGAN+: Handwriting Imitation GAN With Disentangled RepresentationsAuthorsJi GanWeiqiang WangJiaxu LengXinbo GaoLivestreamedRecorded

3:56pm - 4:07pm PDT

A Method for Animating Children's Drawings of the Human FigureAuthorsHarrison Jesse SmithQingyuan ZhengYifei LiSomya JainJessica HodginsLivestreamedRecorded

4:07pm - 4:18pm PDT

VideoDoodles: Hand-drawn Animations on Videos With Scene-aware CanvasesAuthorsEmilie YuCuong NguyenKevin MatzenOliver WangRubaiat Habib KaziAdrien BousseauLivestreamedRecorded

4:18pm - 4:29pm PDT

StripMaker: Perception-driven Learned Vector Sketch ConsolidationAuthorsChenxi LiuToshiki AokiMikhail BessmeltsevAlla ShefferLivestreamedRecorded

4:29pm - 4:40pm PDT

Semi-supervised Reference-based Sketch Extraction Using a Contrastive Learning FrameworkAuthorsChang Wook SeoAmirsaman AshtariJunyong NohLivestreamedRecorded

4:40pm - 4:50pm PDT

AniFaceDrawing: Anime Portrait Exploration During Your SketchingAuthorsZhengyu HuangHaoran XieTsukasa FukusatoKazunori MiyataLivestreamedRecorded

4:50pm - 5:15pm PDTMagical Sketching - Q&A and Interactive Discussion

Tuesday, 8 August 2023


2pm - 3:30pm PDT Technical Paper
Full-Body XR: Beyond The Headset
Markus Steinberger Petree Hall D

Presentations
2pm - 2:11pm PDT
EgoLocate: Real-time Motion Capture, Localization, and Mapping With Sparse Body-mounted Sensors
Authors
Xinyu YiYuxiao ZhouMarc HabermannVladislav GolyanikShaohua PanChristian TheobaltFeng Xu
2:11pm - 2:22pm PDT
Differential Frequency Heterodyne Time-of-flight Imaging for Instantaneous Depth and Velocity Estimation
Authors: Yunpu Hu Masatoshi Ishikawa Leo Miyashita
2:22pm - 2:32pm PDT
MoiréTag: Angular Measurement and Tracking With a Passive Marker
Authors: Simeng Qiu Hadi Amata Wolfgang Heidrich
2:32pm - 2:42pm PDT
Toward Optimized VR/AR Ergonomics: Modeling and Predicting User Neck Muscle Contraction
Authors: Yunxiang Zhang Kenneth Chen Qi Sun
2:42pm - 2:52pm PDT
In the Blink of an Eye: Event-based Emotion Recognition
Authors: Haiwei ZhangJiqing ZhangBo DongPieter PeersWenwei WuXiaopeng WeiFelix HeideXin Yang
2:52pm - 3:03pm PDT
Towards Attention–Aware Foveated Rendering
Authors: Brooke KrajancichPetr Kellnhofer Gordon Wetzstein

その次のセッションも興味深い
Neural Light Transport
Session Chair: Nathan Carr (Adobe)
https://s2023.siggraph.org/session/?sess=sess130


Wednesday, 9 August 2023

9am - 10:30am PDT
Technical Paper
Cloud Rendering: Your GPU Is Somewhere Else
Rafal K. Mantiuk Petree Hall D

9am - 10:30am PDT Technical Paper
Diffusion for Geometry
Vladimir Kim Room 502 AB

10:45am - 12:15pm PDT Technical Paper
Character Animation
Yuting Ye Petree Hall C

3:45pm - 5:15pm PDT Technical Paper
Neural Capturing
Derek Bradley Petree Hall C

Thursday, 10 August 2023

9am - 10:30am PDT Technical Paper
Real-Time Rendering: Gotta Go Fast!
Anton Kaplanyan Room 515 A

10:45am - 12:15pm PDT Technical Paper
Character Animation: Interaction
Carol O'Sullivan Petree Hall C

10:45am - 12:15pm PDT Technical Paper
Environment Rendering: NeRFs on Earth
Elmar Eisemann Room 502 AB

10:45am - 12:15pm PDT Technical Paper
Making Faces With Neural Avatars
Amit H. Bermano Petree Hall D

12:30pm - 1:30pm PDT Technical Paper
SIGGRAPH 2023 Technical Papers Town Hall
Room 502 AB

3:45pm - 5:15pm PDT Technical Paper
NeRFs for AvatarsPeter Hedman Petree Hall C

5:15pm - 5:30pm PDT Technical Paper
Technical Papers Closing Session Petree Hall C

忙しそうだな！

この記事が気に入ったらサポートをしてみませんか？