1. X
  2. Donny Y. Chen
Log inSign up
Donny Y. Chen
36 posts
Image
user avatar
Donny Y. Chen
@donydchen
Researcher at ByteDance Seed (Singapore) I Previously PhD @MonashUni | Working on 3D Vision | ALL VIEWS ARE SOLELY HIS OWN.
Singapore
donydchen.github.io
Joined May 2013
138
Following
315
Followers
RepliesRepliesMediaMedia
  • user avatar
    Donny Y. Chen
    @donydchen
    Jun 24, 2025
    Had a fantastic experience working with Chuanxia as his co-supervised PhD student. I highly recommend joining his Physical Vision Group (physicalvision.github.io) at NTU Singapore, and I believe it will be an inspiring place to grow as a researcher!
    user avatar
    Chuanxia Zheng
    @ChuanxiaZ
    Jun 24, 2025
    After two amazing years with @Oxford_VGG, I will be joining @NTUsg as a Nanyang Assistant Professor in Fall 2025! I’ll be leading the Physical Vision Group (physicalvision.github.io) — and we're hiring for next year!🚀 If you're passionate about vision or AI, get in touch!
    Image
    00:00
    353
  • user avatar
    Donny Y. Chen
    @donydchen
    Jun 9, 2025
    Thanks Zhenjun for sharing. Our PM-Loss tackles low geometry quality in feed-forward 3DGS caused by "discontinuity" in predicted depth, and features a plug-and-play training loss that leverages geometry priors from pointmap-based models like VGGT. More at aim-uofa.github.io/PMLoss
    Image
    00:00
    Image
    Image
    Image
    Image
    user avatar
    Zhenjun Zhao
    @zhenjun_zhao
    Jun 8, 2025
    Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting @Duochao_Shi, @wjwang2003, @donydchen, Zeyu Zhang, Jia-Wang Bian, @supremeZhuang, @chunhua_shen tl;dr: pre-trained 3D reconstruction models->pointmaps->geometry prior->loss arxiv.org/abs/2506.05327
    4.3K
  • user avatar
    Donny Y. Chen
    @donydchen
    Jun 2, 2025
    ZPressor, an architecture-agnostic module that enables existing feed-forward #3DGS models to effectively handle dense input views (up to 100 on an 80G GPU). More at: lhmd.top/zpressor/
    Image
    00:00
    Image
    user avatar
    Weijie Wang @ ICML
    @wjwang2003
    May 30, 2025
    🚀 We're excited to introduce ZPressor, a bottleneck-aware compression module for scalable feed-forward 3DGS. Existing feed-forward 3DGS models struggle with dense views, facing performance drops & massive redundancy. ZPressor leverages Information Bottleneck Theory to compress
    3.8K
  • user avatar
    Donny Y. Chen
    @donydchen
    Dec 12, 2024
    Fantastic dinner @theworldlabs, glad to meet so many nice people around.
    user avatar
    Rajko Radovanović
    @rajko_rad
    Dec 12, 2024
    ❤️ @theworldlabs cc @chlassner @drfeifei @donydchen @venturetwins
    Image
    Image
    238
  • user avatar
    Donny Y. Chen
    @donydchen
    Oct 2, 2022
    Well summarised, thanks for the hard work! Glad to share that me and @QianyiWu7 have managed to make our contributions to such a fast developing community. More details please refer to Sem2NeRF(donydchen.github.io/sem2nerf/) and ObjectSDF(wuqianyi.top/objectsdf/).
    user avatar
    Mark Boss
    @markb_boss
    Oct 1, 2022
    As #ECCV2022 is approaching rapidly, I wanted to find all @neural_fields related papers. I've compiled my gatherings in another post of (hopefully) all NeRFy papers. Feel free to message me about anything I have missed :) markboss.me/post/nerf_at_e…
  • See @donydchen's full profile

    Sign up
    Log in

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement