Aymen Mir (@aymenmmir) - Twitter Profili | Zamantika Mersobahis Locabet

Aymen Mir@aymenmmir·5d

@HaoZhang623 Thanks!

English

0

31

Hao Zhang@HaoZhang623·5d

@aymenmmir @CSProfKGD Wow the quality is so good!

English

1

0

1

110

Aymen Mir@aymenmmir·6d

1/4 📢 AHOY! accepted at #ECCV2026! 🎉 From a single in-the-wild YouTube video, often heavily occluded, AHOY builds a complete, animatable 3D human avatar. Each clip below runs input → 360° avatar → animation. 🧵👇 🔗 miraymen.github.io/ahoy/

English

6

21

137

22.2K

Aymen Mir@aymenmmir·5d

@8Infinite8 Great work with the scans! Thanks!

English

0

1

8

Infinite-Realities@8Infinite8·5d

@aymenmmir So cool to see our scan data being used out in the wild.

English

1

0

1

55

Aymen Mir@aymenmmir·30 Haz

1/5 Dropping a 3D Gaussian Splatting avatar into a captured 3DGS scene is easy. Making it cast a believable shadow is not. Happy to share RAGA, accepted at #ECCV2026.

English

5

17

146

10.2K

Aymen Mir@aymenmmir·5d

@8Infinite8 thanks for this post. happy to correct. can you please provide links to the original images so I can use the correct links on the page.

English

1

0

1

94

Infinite-Realities@8Infinite8·5d

Hi. Your github webpage incorrectly credits "PixPro" for the rig images you guys used who also incorrectly list one of the rigs as being built by Esper when it was Ten24 who built the rig. You might want to correct that and credit correctly i.e. not PixPro but Ten24 Media (left) and Esper (right) respectively.

English

1

0

1

240

Aymen Mir retweetledi

Robert Scoble@Scobleizer·6d

Virtual humans finally arriving.

Aymen Mir@aymenmmir

1/4 📢 AHOY! accepted at #ECCV2026! 🎉 From a single in-the-wild YouTube video, often heavily occluded, AHOY builds a complete, animatable 3D human avatar. Each clip below runs input → 360° avatar → animation. 🧵👇 🔗 miraymen.github.io/ahoy/

English

7

4

74

14.8K

Aymen Mir@aymenmmir·6d

4/4 The avatars are drivable and drop cleanly into 3DGS scenes captured on a phone. State of the art on occluded video. 📄 arXiv:2603.17975 🔗 miraymen.github.io/ahoy/ w/ @Xiangjun_Tang @peter_wonka @GerardPonsMoll1

English

3

0

3

331

Aymen Mir@aymenmmir·6d

3/4 The key idea: identity-finetuned video diffusion models hallucinate the unobserved regions and supervise the full body. This turns partial, occluded views into a complete 3D Gaussian human that stays consistent from every angle.

English

1

0

1

406

Aymen Mir@aymenmmir·2 Tem

Something for @iclr_conf to remember as well - especially given the debacle that was ICLR 2026.

Torsten Sattler@SattlerTorsten

Very grateful for the @eccvconf Program Chairs for all their efforts they spent on appeals! I think allowing appeals is very important for the community and provides valuable feedback to PCs and ACs. Something @CVPR and @ICCVConference have lost.

English

0

274

Aymen Mir retweetledi

Torsten Sattler@SattlerTorsten·2 Tem

Very grateful for the @eccvconf Program Chairs for all their efforts they spent on appeals! I think allowing appeals is very important for the community and provides valuable feedback to PCs and ACs. Something @CVPR and @ICCVConference have lost.

English

2

4

44

7K

Aymen Mir retweetledi