Log inSign up
Image
user avatar
Xingguang Yan
@yan_xg
Ph.D. in progress at @SFU 3DLG lab @sfu_cs_3dlg and GrUVi lab. I generate stuff in 3D. X. Y.
Vancouver
yanxg.art
Joined December 2011
266
Following
437
Followers
RepliesMedia
  • Pinned
    user avatar
    Xingguang Yan
    @yan_xg
    Aug 20, 2024
    Excited to share our recent work! 😁 An Object is Worth 64x64 Pixels: Generating 3D Objects via Image Diffusion We generate meshes as a set of UV patches packed in an image, which we term as "Object Images" or "omages”. Code is now live! omages.github.io 8 cool facts
    Image
    00:00
  • user avatar
    Xingguang Yan
    @yan_xg
    Jun 2
    If you're working on embodied AI, don't miss this articulated-objects dataset by @iliashdo and the team, premiering at #CVPR2026. ➡️ Honestly, it's pretty fun just exploring the dataset!
    user avatar
    Denys Iliash
    @iliashdo
    Jun 2
    Introducing 𝗔𝗿𝘁𝗶𝘃𝗲𝗿𝘀𝗲 dataset: 5.4K articulated objects for embodied AI 🤖 • 88 categories • Functional part segmentation + articulation • Per-part material + mass • Procedural interiors #CVPR2026 — Poster 164 Session 2 & ActiVis Workshop Website + paper below 🧵
    Image
    00:00
  • user avatar
    Xingguang Yan
    @yan_xg
    Apr 5
    Exciting progress in the auto-seam & auto-UV space!🔥 Thrilled to share our recent work MeshTailor. Huge congrats to @qixuema for driving this incredible project. We finally brought AI to native seam generation, learning directly from professional data. Check the video below!
    user avatar
    Xueqi (Sebastian) Ma
    @qixuema
    Apr 5
    AI Native Seams... Finally? #3D 🔥 Excited to share our recent work MeshTailor: learned from real artist seam layouts, it places edge-aligned, coherent seams on low-poly meshes in seconds, enabling strong UV unwrapping. 🔗 Check out the paper below! ⬇️
    Image
    00:00