iiinova — where your digital self keeps evolving

Reposted by Daniel Barath

Zhenjun Zhao @ericzzj.bsky.social · 02/10/2026

CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction Moyang Li, Zihan Zhu, Wei Zhang, @marcpollefeys.bsky.social, @danielbarath.bsky.social tl;dr: LoGeR + loop closure arxiv.org/abs/2610.01927

011

Reposted by Daniel Barath

Zhenjun Zhao @ericzzj.bsky.social · 05/09/2026

Stable and Scalable Bundle Adjustment of Holistic 3D Structures Shaohui Liu, Rémi Pautrat, @danielbarath.bsky.social, Richard Hartley, Viktor Larsson, @marcpollefeys.bsky.social tl;dr: planes, vanishing points, 3D primitives -> Point-Line BA arxiv.org/abs/2609.04026

041

Reposted by Daniel Barath

Zhenjun Zhao @ericzzj.bsky.social · 19/08/2026

GenRec: Knowing Where to Reconstruct and Where to Generate Ata Çelen, Jaewoo Jung, Federico Tombari, @marcpollefeys.bsky.social, Sunghwan Hong, @miniemeyer.bsky.social, @danielbarath.bsky.social arxiv.org/abs/2608.17832

111

Reposted by Daniel Barath

Dmytro Mishkin @ducha-aiki.bsky.social · 21/07/2026

Rolling Shutter Relative Pose Estimation Made Practical @danielbarath.bsky.social tl;dr: affine correspondences for rolling shutter, because you need 20 PC otherwise. You also can get them from dense matcher like RoMa. P.S. (or we can ignore RS first?) arxiv.org/abs/2606.26863

1102

Reposted by Daniel Barath

Zhenjun Zhao @ericzzj.bsky.social · 04/06/2026

ZipSplat: Fewer Gaussians, Better Splats @veichta.bsky.social, Sunghwan Hong, @danielbarath.bsky.social, @marcpollefeys.bsky.social tl;dr: predict Gaussians directly in 3D from a compact set of scene tokens->decouple primitive placement from the 2D pixel grid arxiv.org/abs/2606.05102

032

Reposted by Daniel Barath

Zhenjun Zhao @ericzzj.bsky.social · 11/06/2026

SG2Loc: Sequential Visual Localization on 3D Scene Graphs Nicole Damblon, Olga Vysotska, Federico Tombari, @marcpollefeys.bsky.social, @danielbarath.bsky.social tl;dr: scene graph (SceneGraphLoc)->object meshes->semantic features->particle filtering arxiv.org/abs/2606.11880

021

Reposted by Daniel Barath

Zhenjun Zhao @ericzzj.bsky.social · 20/03/2026

DROID-SLAM in the Wild Moyang Li, Zihan Zhu, @marcpollefeys.bsky.social, @danielbarath.bsky.social tl;dr: uncertainty-aware BA->DROID-SLAM arxiv.org/abs/2603.19076

131

Reposted by Daniel Barath

Dmytro Mishkin @ducha-aiki.bsky.social · 27/02/2026

Global-Aware Edge Prioritization for Pose Graph Initialization @weitong8591.bsky.social @gtolias.bsky.social Jiri Matas, @danielbarath.bsky.social tl;dr: another global desc->GNN->MST. Supervision:# triangulated points/pair. +heuristic MST postprocessing. Eval on IMC-PT. arxiv.org/abs/2602.21963

072

Reposted by Daniel Barath

Zhenjun Zhao @ericzzj.bsky.social · 26/02/2026

Global-Aware Edge Prioritization for Pose Graph Initialization @weitong8591.bsky.social, @gtolias.bsky.social, Jiri Matas, @danielbarath.bsky.social tl;dr: rank pose graph edges->global consistency->improve SfM arxiv.org/abs/2602.21963

192

Reposted by Daniel Barath

Zhenjun Zhao @ericzzj.bsky.social · 03/12/2025

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

021

Reposted by Daniel Barath

Zhenjun Zhao @ericzzj.bsky.social · 10/10/2025

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

031

Reposted by Daniel Barath

Dmytro Mishkin @ducha-aiki.bsky.social · 16/06/2025

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/

191

Reposted by Daniel Barath

Haofei Xu @haofeixu.bsky.social · 05/06/2025

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!

3267

Reposted by Daniel Barath

Andreas Geiger @andreasgeiger.bsky.social · 24/04/2025

🏠 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/

13913

Reposted by Daniel Barath

Sayan Deb Sarkar @sayandsarkar.bsky.social · 07/04/2025

🏆 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 🍳

051

Reposted by Daniel Barath

Zhenjun Zhao @ericzzj.bsky.social · 08/04/2025

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

021

Reposted by Daniel Barath

Johan Edstedt @parskatt.bsky.social · 17/02/2025

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

2203

Daniel Barath @danielbarath.bsky.social · 31/01/2025

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

080