VGGT-GS SLAM: uncalibrated monocular Gaussian Splatting SLAM built on feed-forward VGGT priors
zhenjun_zhao · x · 2026-09-19
arXiv paper VGGT-GS SLAM (Yuhang Han, Hao Wang, Jiaxi Cao, Xingyu Liu) targets monocular 3D Gaussian Splatting SLAM on uncalibrated videos.
- Starts from feed-forward VGGT pose and depth priors.
- Performs submap differentiable bundle adjustment jointly refining camera poses and a 3D Gaussian map, while optimizing submap-shared intrinsics and radial-tangential distortion via analytic calibration Jacobians.
- Introduces Gaussian-native Alignment (GNA) for camera-anchored scale refinement between sequential submaps and loop-closure verification.
On standard indoor benchmarks it delivers consistent localization accuracy and strong rendering under uncalibrated settings, establishing a strong baseline for uncalibrated Gaussian SLAM.
More from Research
- Resolution-Inspired Pretraining Experiments 'Pretty Much a Disaster,' Researcher Says — gordic_aleksa · 2026-09-19
- Auto-Formalizing a 76-Page Paper With Opus 5 High Would Take ~40 Days — kfountou · 2026-09-19
- ICLR Submissions Near 45,000 as Researcher Decries AI-Generated Paper Slop — DimitrisPapail · 2026-09-19
- Quanta video explains why Navier-Stokes is so hard and how an OpenAI proof could resolve it — eigensteve · 2026-09-19
- BBFM conjectures see formalization progress building on Axiom Math's prior work — ctjlewis · 2026-09-19
- Blog argues pretraining data, not verifiability, makes LLMs good at math and coding — _arohan_ · 2026-09-19