Shunsuke Saito
@psyth91
Followers
4K
Following
2K
Media
96
Statuses
935
Research Scientist @AIatMeta Digital Human/Vision/Graphics デジタルヒューマンの研究してます。 #pifuhd #sapiens Tweets in Japanese and English, All opinions are my own. V4-6
Pittsburgh
Joined April 2020
Relightable Codec Avatars is now extended to full-body! At #SIGGRAPH2025, we will present Relightable Full-body Gaussian Codec Avatars. Key contributions include learnable Zonal Harmonics and deferred learnable radiance transfer for specular! Check it out!.
2
32
177
RT @park_jinhyung1: Introducing ATLAS: A high-fidelity, parametric human body model enabling precise, independent control of surface and sk….
0
33
0
Want Gaussian Avatar on mobile? Turns out the bottleneck is decoding of pose correctives. At #SIGGRAPH2025, we present a simple yet highly effective solution. We make *any* Gaussian avatars mobile-ready via linear distillation and corrective sharing. 👉
2
13
107
RT @_c_he_: 📢 #SIGGRAPH2025 I'll be presenting our paper "3DGH: 3D Head Generation with Composable Hair and Face". Swing by and let's talk….
0
4
0
RT @kashu_yamazaki: AIロボット分野で米国大学院進学希望していて今年出願する人がいるなら気軽に声かけてください。できる範囲で手伝います。. もっとこの分野に日本人プレーヤー増やさないと！！. トップ大学のめぼしい研究室に最低1人はいるような状況にしないと、ダ….
0
84
0
RT @TobiasKirschst1: We will present Avat3r at #ICCV2025! 🥳.Avat3r brings animation to Large Reconstruction Models. One surprising finding….
0
30
0
RT @MattNiessner: Seven papers accepted at #ICCV2025!. Exciting topics: lots of generative AI using transformers, diffusion, 3DGS, etc. foc….
0
30
0
RT @jack_r_saunders: 3DGH: 3D Head Generation with Composable Hair and Face. TLDR: A Generative model of (static) Gaussian Avatars using a….
0
21
0
「専門領域の問題を解ける」というプライドはあった方がいいと思うけど、特定の手法にプライド持ち始めたらあかんよね。.
これからAI全盛になっていく時代でほぼ全ての領域でリスクになるのがサンクコストとプライドだと思う. 過渡期には専門知識を使ってリードすることはあるし、むしろ今はそれやりまくった方がいいんだけど、プライドが高すぎると思わぬ形でドツボに嵌る可能性あるから何事に対しても柔軟に構える方が良い.
0
0
6
RT @Frozen_Burning: Please drop by and check our 🌟highlight🌟 #3DTopia-XL today afternoon @CVPR ! . ExHall D Poster #40.Sun 15 Jun 4:00 PM C….
3dtopia.github.io
Project page for 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
0
11
0
RT @seunghy23235: Thank you for presenting awesome work @psyth91. The talk was about the way to generate photorealistic avatar, communicati….
0
2
0
I'm giving a keynote talk in a very interesting workshop on virtual humans and humanoid robots today at 2:25-2:50pm at 101B @CVPR 2025!.
🚀Join our #CVPR2025 2nd POETs Workshop --Embodied "Humans": Symbiotic Intelligence Between Virtual Humans and Humanoid Robots. We have super cool live demo sessions, and awesome lineup of speakers @UnitreeRobotics @GerardPonsMoll1, @pathak2206, Karen Liu, @chelseabfinn @psyth91
0
8
53
RT @TobiasKirschst1: Happening now in room 110A!.Shunsuke Saito @psyth91 talking about Codec Avatars!
0
3
0
RT @TobiasKirschst1: Join us at the workshop on Photo-realistic 3D Head Avatars at #CVPR2025, featuring invited talks by leading academic r….
0
18
0
RT @ky_lin0305: 🚀Join our #CVPR2025 2nd POETs Workshop --Embodied "Humans": Symbiotic Intelligence Between Virtual Humans and Humanoid Rob….
0
10
0
RT @_TianyeLi: Join us at #CVPR2025 workshop on Photo-realistic 3D Head Avatars, featuring invited talks by leading experts as well as new….
0
9
0