RT @AnpeiC: The fields are moving extremely fast, we tried to summarize them base on 3D representations. Please let us know if we missed a….

RT @XianghuiXie: 📢Is your multi-view generation (MVG) model 3D consistent? Do they produce high-quality and semantically correct novel view….

Join millions who have switched to Grok.

RT @AnpeiC: 📢 Our new paper GaVS – 3D-Grounded Video Stabilization is out!. Key idea: feed-forward Dynamic Gaussian Splatting + test-time o….

RT @yuliangxiu: Easi3R has been accepted to #ICCV2025. See y'all in Hawaii 🌴🥥.

RT @GerardPonsMoll1: Had a blast at cvpr! Unfortunately, I have to return earlier! Really nice to see many researchers excited to share the….

Got you, Kosta!

Thanks for all the likes! Brilliant t-shirt idea from Yuliang.

RT @CSProfKGD: Fun poster alert!

RT @AnpeiC: 📢 We’re presenting two posters at #CVPR2025 today!.🗓️ June 13 | 🕓 16:00–18:00 | 📍 Exhibit Hall D. 🔹 Genfusion — Booth 61.🔹 Feat….

📍 June 12.🕙 10:00–11:00AM @ EMACS Workshop (Poster #67–76, ExHall D).🕒 3:00–4:30PM @ 3D Human Understanding Workshop (Poster #320, ExHall D).🗣️ 4:40–4:50PM @ EMACS Workshop (Oral, Room 208B). 📍 June 13.🕓 4:00–6:00PM @ Main Conference (Poster #93, ExHall D).

We're presenting Feat2GS at #CVPR2025 — probing the 3D awareness of Visual Foundation Models using only 2D images!. Come chat with us to explore:.🔹 Why 2D and 3D are more aligned than you think.🔹 Which VFMs best capture geometry & appearance.🔹 How to make VFMs more 3D-aware

RT @tingtin36139994: 🚀 Introducing SOAP: Style-Omniscient Animatable Portraits - a style-agnostic method for one-view, animation-ready 3D p….

RT @AnpeiC: Feature up up up 🖼️✨. We tackle the resolution bottleneck of Vision Foundation Models (like DINOv2 & CLIP) with a coordinate-ba….

RT @AnpeiC: Too many artifacts for GS reconstruction? Please checkout GenFusion: Closing the Loop between Reconstruction and Generation via….

RT @yuliangxiu: If you're into digital humans, you know how tough it is to fit a SMPL body onto a 3D clothed scan—rendering, OpenPose, tria….

RT @zhenjun_zhao: Easi3R: Estimating Disentangled Motion from DUSt3R Without Training. @RoverXingyu, @faneggchen, @yuliangxiu, Andreas Geig….

RT @yuliangxiu: Checkout the thread of #Feat2GS, the 3D awareness of visual foundation models (VFMs) "should" and "could" be evaluated on l….

RT @GerardPonsMoll1: If you want to know which foundation models are best for 3D, check out @faneggchen feat2gs. Key idea is to predict Ga….

RT @kwangmoo_yi: Preprint of today: Chen et al., "Easi3R: Estimating Disentangled Motion from DUSt3R Without Training" -- .

RT @_akhaliq: Easi3R just dropped on Hugging Face . Estimating Disentangled Motion from DUSt3R Without Training