Daniel Barath

VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM

Zihan Zhu, Wei Zhang, Norbert Haala, @marcpollefeys.bsky.social, @danielbarath.bsky.social

tl;dr: in title

arxiv.org/abs/2512.02293

03.12.2025 16:07 — 👍 2    🔁 1    💬 0    📌 0

ReSplat: Learning Recurrent Gaussian Splats

@haofeixu.bsky.social, @danielbarath.bsky.social, @andreasgeiger.bsky.social, @marcpollefeys.bsky.social

tl;dr: rendering error->recurrent network->Gaussian updates

arxiv.org/abs/2510.08575

10.10.2025 19:14 — 👍 3    🔁 1    💬 0    📌 0

SupeRANSAC: One RANSAC to Rule Them All
@danielbarath.bsky.social
tl;dr: most accurate, but slow-ish RANSAC,

arxiv.org/abs/2506.04803
github.com/danini/super...

Sampling: PROSAC + P-NAPSAC for homography & rigid pose, PROSAC for epipolar
1/

16.06.2025 07:25 — 👍 9    🔁 1    💬 1    📌 1

Excited to present our #CVPR2025 paper DepthSplat next week!
DepthSplat is a feed-forward model that achieves high-quality Gaussian reconstruction and view synthesis in just 0.6 seconds.
Looking forward to great conversations at the conference!

05.06.2025 12:09 — 👍 27    🔁 7    💬 3    📌 0

🏠 Introducing DepthSplat: a framework that connects Gaussian splatting with single- and multi-view depth estimation. This enables robust depth modeling and high-quality view synthesis with state-of-the-art results on ScanNet, RealEstate10K, and DL3DV.
🔗 haofeixu.github.io/depthsplat/

24.04.2025 08:58 — 👍 39    🔁 13    💬 1    📌 1

🏆 CrossOver is accepted as a 𝗛𝗶𝗴𝗵𝗹𝗶𝗴𝗵𝘁 at #CVPR2025! ✨
💻 Fully open-sourced code with all pre-trained checkpoints: github.com/GradientSpac...

📡 Stay tuned for a deep-dive thread and what else we are cooking 🍳

07.04.2025 22:20 — 👍 5    🔁 1    💬 0    📌 0

Learning Affine Correspondences by Integrating Geometric Constraints

Pengju Sun, Banglei Guan, Zhenbao Yu, Yang Shang, Qifeng Yu, @danielbarath.bsky.social

tl;dr: DKM+AffNet?

arxiv.org/abs/2504.04834

08.04.2025 05:23 — 👍 2    🔁 1    💬 0    📌 0

Joint work with @sayandsarkar.bsky.social, Ondrej Miksik, @marcpollefeys.bsky.social, and @danielbarath.bsky.social

27.02.2025 20:52 — 👍 3    🔁 1    💬 0    📌 0

CrossOver: 3D Scene Cross-Modal Alignment Multi-modal 3D object understanding has gained significant attention, yet current approaches often assume complete data availability and rigid alignment across all modalities. We present CrossOver, a ...

🔗 arXiv: arxiv.org/abs/2502.15011
📂 Project page: sayands.github.io/crossover/

Joint work with Ondrej Miksik, @marcpollefeys.bsky.social, @danielbarath.bsky.social and @ir0armeni.bsky.social 🤝💡

26.02.2025 22:02 — 👍 5    🔁 1    💬 0    📌 0

Protip: Add poselib refinement to opencv magsac, you can thank me later.

17.02.2025 08:06 — 👍 21    🔁 3    💬 2    📌 0

Just wrapped up an incredible time at KEPAF conference with the Hungarian image processing, machine learning, and computer vision community — great talks, fresh ideas, and inspiring discussions. Excited to see you next time! #KEPAF #ComputerVision #MachineLearning

31.01.2025 09:54 — 👍 8    🔁 0    💬 0    📌 0