跳过导航
🔥Diffusion Masters Transparent Objects in Videos!
0:00 / 0:57

🔥Diffusion Masters Transparent Objects in Videos!

Chongjie Ye

@ychngji62734 位关注者

在 X 上查看
305 个赞下载原帖

28,181 次观看 #DKT

🔥Diffusion Masters Transparent Objects in Videos! We introduce #DKT, a foundation model that repurposes video diffusion for zero-shot depth and normal estimation on Transparent and Reflective Objects with Superior Temporal Consistency Demo: Code:

6 条评论

评论来自 X (Twitter) 上的原帖

  • Chris make some 3D scans 的头像

    @ChrisAtKIRI

    Good work brother

    2 个赞

  • A.I.Warper 的头像

    @AIWarper

    Does that released checkpoint also work on normals? If so I’ll implement it in Comfy.

    1 个赞

  • James 的头像

    @AwokeKnowing

    what does this do when walking up to a big mirror?

  • Alexandre Morgand 的头像

    @Almorgand

    Oh great stuff!

  • Chen Yiwen @eccv 2026 的头像

    @NTU_chenyiwen

    Nice work!

  • Himanshu Kumar 的头像

    @codewithimanshu

    DKT model processes video, generating depth maps at 25 FPS.