🤖 3D Computer Vision, SLAM, SfM, 3D Reconstruction
🎓 MSc CS at ETH Zurich
🏠 ganlinzhang.xyz
Monocular Visual SLAM with a symmetric, lightweight frontend.
🔗 GitHub: github.com/zhangganlin/...
📄 arXiv: arxiv.org/abs/2509.01584
👏 Kudos to co-authors
@shenhanqian.bsky.social @xiwang1212.bsky.social @dcremers.bsky.social
Monocular Visual SLAM with a symmetric, lightweight frontend.
🔗 GitHub: github.com/zhangganlin/...
📄 arXiv: arxiv.org/abs/2509.01584
👏 Kudos to co-authors
@shenhanqian.bsky.social @xiwang1212.bsky.social @dcremers.bsky.social
‼️ The application portal will be open from 15 October to 14 November 2025.
Find out more: mcml.ai/opportunitie...
‼️ The application portal will be open from 15 October to 14 November 2025.
Find out more: mcml.ai/opportunitie...
@ganlinzhang.xyz, @shenhanqian.bsky.social, @xiwang1212.bsky.social, @dcremers.bsky.social
arxiv.org/abs/2509.01584
@ganlinzhang.xyz, @shenhanqian.bsky.social, @xiwang1212.bsky.social, @dcremers.bsky.social
arxiv.org/abs/2509.01584
🌍: visinf.github.io/scenedino/
📃: arxiv.org/abs/2507.06230
🤗: huggingface.co/spaces/jev-a...
@jev-aleks.bsky.social @fwimbauer.bsky.social @olvrhhn.bsky.social @stefanroth.bsky.social @dcremers.bsky.social
🌍: visinf.github.io/scenedino/
📃: arxiv.org/abs/2507.06230
🤗: huggingface.co/spaces/jev-a...
@jev-aleks.bsky.social @fwimbauer.bsky.social @olvrhhn.bsky.social @stefanroth.bsky.social @dcremers.bsky.social
Turns out distortion calibration from multiview 2D correspondences can be fully decoupled from 3D reconstruction, greatly simplifying the problem
arxiv.org/abs/2504.16499
github.com/DaniilSinits...
Turns out distortion calibration from multiview 2D correspondences can be fully decoupled from 3D reconstruction, greatly simplifying the problem
arxiv.org/abs/2504.16499
github.com/DaniilSinits...
Surprisingly, yes!
Our #CVPR2025 paper with @neekans.bsky.social and @dcremers.bsky.social shows that the pairwise distances in both modalities are often enough to find correspondences.
⬇️ 1/4
Surprisingly, yes!
Our #CVPR2025 paper with @neekans.bsky.social and @dcremers.bsky.social shows that the pairwise distances in both modalities are often enough to find correspondences.
⬇️ 1/4
Weirong Chen, @ganlinzhang.xyz, @fwimbauer.bsky.social, Rui Wang, @neekans.bsky.social, Andrea Vedaldi, @dcremers.bsky.social
tl;dr: learning-based 3D point tracker decouples camera and object-based motion
arxiv.org/abs/2504.14516
Weirong Chen, @ganlinzhang.xyz, @fwimbauer.bsky.social, Rui Wang, @neekans.bsky.social, Andrea Vedaldi, @dcremers.bsky.social
tl;dr: learning-based 3D point tracker decouples camera and object-based motion
arxiv.org/abs/2504.14516
For more details check out cvg.cit.tum.de
For more details check out cvg.cit.tum.de
Apply by January 13, 2025 to receive cross-sectional training in AI and a full salary for three years for your PhD at @tumuenchen.bsky.social or LMU.
Link: zuseschoolrelai.de/application/
@daadworldwide.bsky.social
Apply by January 13, 2025 to receive cross-sectional training in AI and a full salary for three years for your PhD at @tumuenchen.bsky.social or LMU.
Link: zuseschoolrelai.de/application/
@daadworldwide.bsky.social
go.bsky.app/PkAKJu5
go.bsky.app/PkAKJu5