Sign in

thibaultgroueix.bsky.social

@thibaultgroueix.bsky.social
197 followers 201 following 22 posts
PostsRepliesMedia
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 07/01/2026
✨ My 2025 best of: 📺 Series: Adolescence 🎬 Animated movie: K-Pop Demon Hunters 📖 Book: Onyx Storm — Rebecca Yarros 🎵 Music: ESTL 📄 Papers: 1️⃣ Flow Matching Policy Gradients 2️⃣ VGGT 3️⃣ Treillis
110
Reposted by @thibaultgroueix.bsky.social
NAVER LABS Europe @naverlabseurope.bsky.social · 18/12/2025
Check out our 2025 highlights in computer vision! 🚀Five new *St3R models (MASt3R-SfM, MUSt3R, PanSt3R, HAMSt3R, HOSt3R) 🤩Anny parametric 3D human model (Apache 2.0) 🤟Universal encoder for all-in-one vision FM Watch the highlights 👇 More info ▶️ tinyurl.com/muvs5vnu
0113
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 14/12/2025
I will be in Hong Kong until Thursday for SIGGRAPH ASIA 25 \o/ DM if you want to meet!
010
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 22/10/2025
Given N image generation jobs, can we do better than N calls to text-to-image ? @daledecatur.bsky.social proposes to share compute across a batch of jobs, achieving higher efficiency at similar quality. Check out our #ICCV2025 poster #153 today during Poster Session #4 from 2:45-4:45 HST!
060
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 22/05/2025
000
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 13/05/2025
Man-made objects are often repeated in urban scene. 🎳 Can we leverage these repetitions to improve 3D reconstruction 📷? Exploration led by the titan Nicolas Violante Grezzi 👇🧵
150
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 25/04/2025
Great opportunity! This is a dream team, and they are located 20 minutes from Paris.
020
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 18/04/2025
OpenAi Ghibli style + the new FramePack (ControlNet team). I am very impressed by this model, and it was super easy to run. Is it a commoditization moment for video GenAi?
010
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 05/03/2025
Would anyone know the best current code for human keypoint estimation from a video of a single human?
000
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 17/01/2025
Proposal: Reviewers who have not given any sign-of-life to the AC get an automatic flag on the rebuttal of the papers they submitted, to be considered at the discretion of the reviewers of those papers.
100
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 28/12/2024
Best of 2024 ? Movies : Perfect Days (runner-up Anora) Series: three-body problem Animated series: Arcane Research paper: Dust3r Manga: Oshi no ko What about you?
180
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 10/12/2024
From a few user clicks to 3D material segmentation - in seconds ⌛. It's exciting to see so many pieces in 3D generation and analysis starting to work reliably and fast ! Super nice work from Michael and team (mfischer-ucl.github.io)
010
thibaultgroueix.bsky.social @thibaultgroueix.bsky.social · 04/12/2024
🌟 Text-to-3D is awesome ! But how do we iterate on the generated 3D model, to get just the right result? Do we tweak the prompt endlessly? Revert to traditional 3D modeling techniques? We propose a solution to "3D inpainting” 🤩🎨 Project: amirbarda.github.io/Instant3dit.... A thread. 🧵 1/
191