• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Niessner Announces ECCV Presentations in Malmö

    TU Munich professor shares group projects on generative AI for scenes and avatars.

    MN
    1 Source, 24d ago, first seen 24d ago

    TLDR

    Professor Matthias Niessner posted about his group's upcoming presentations at ECCV in Malmö. The works focus on generative AI covering 3D scene generation, photo-realistic avatars, and agentic modeling. Linked projects include TriFlow for artist-like 3D mesh topology, DynHair for dynamic hair on head avatars, Face Anything for 4D face reconstruction, World Reconstruction From Inconsistent Views, GaussianGPT for autoregressive 3D Gaussian scenes, Seen2Scene for scene completion, Pix2NPHM for NPHM regression from images, and DreamEdit3D for personalized 3D editing.

    Combined views

    10.6K

    1 Source, first seen 24d ago

    Combined views

    10.6K

    1 Source, first seen 24d ago

    191 likes
    191 likes
    2 comments
    117 saves
    28 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    2 comments
    117 saves
    28 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    1 Source

    @MattNiessnerSuper excited for #ECCV'26 in Malmö! Our group will present a series of cutting-edge works, including two orals and a spotlight, around generative AI that cover 3D scene generation, photo-realistic avatars, agentic modeling, and much more! I'll also give several workshop talks about our recent research, including a few exciting updates what we're cooking at @SpAItial_AI :) 1. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation *(oral)* https://nicolasvonluetzow.github.io/GaussianGPT/ 2. TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields *(oral)* https://derkleineli.github.io/triflow/ 3. Face Anything: 4D Face Reconstruction from Any Image Sequence *(spotlight)* https://kocasariumut.github.io/FaceAnything/ 4. Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image https://simongiebenhain.github.io/Pix2NPHM/ 5. Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow https://quan-meng.github.io/projects/seen2scene/ 6. DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing https://www.jinxinai.org/dreamedit3d/ 7. WorldAgents: Can Foundation Image Models be Agents for 3D World Models? https://ziyaerkoc.com/worldagents/ 8. World Reconstruction From Inconsistent Views https://lukashoel.github.io/video_to_world/ 9. Head Avatars with Dynamic Explicit Hair https://dynhair.is.tue.mpg.de/ Great work by @nicolasvluetzow @hcxrli @ErkocZiya @UmutKocasa4344 @ness_pirs @LukasHollein @QTDSMQ @Jinxin_Ai @SGiebenhain and all amazing collaborators!

    1 Source

    @MattNiessnerSuper excited for #ECCV'26 in Malmö! Our group will present a series of cutting-edge works, including two orals and a spotlight, around generative AI that cover 3D scene generation, photo-realistic avatars, agentic modeling, and much more! I'll also give several workshop talks about our recent research, including a few exciting updates what we're cooking at @SpAItial_AI :) 1. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation *(oral)* https://nicolasvonluetzow.github.io/GaussianGPT/ 2. TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields *(oral)* https://derkleineli.github.io/triflow/ 3. Face Anything: 4D Face Reconstruction from Any Image Sequence *(spotlight)* https://kocasariumut.github.io/FaceAnything/ 4. Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image https://simongiebenhain.github.io/Pix2NPHM/ 5. Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow https://quan-meng.github.io/projects/seen2scene/ 6. DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing https://www.jinxinai.org/dreamedit3d/ 7. WorldAgents: Can Foundation Image Models be Agents for 3D World Models? https://ziyaerkoc.com/worldagents/ 8. World Reconstruction From Inconsistent Views https://lukashoel.github.io/video_to_world/ 9. Head Avatars with Dynamic Explicit Hair https://dynhair.is.tue.mpg.de/ Great work by @nicolasvluetzow @hcxrli @ErkocZiya @UmutKocasa4344 @ness_pirs @LukasHollein @QTDSMQ @Jinxin_Ai @SGiebenhain and all amazing collaborators!