# When pose graphs are not enough: a failure analysis of pose-graph-based camera estimation for Gaussian splatting

arXiv: https://arxiv.org/abs/2610.14090 · HTML: https://mlsanity.com/paper/2610.14090/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in SLAM and driving scene reconstruction, one of 15 directions in 3D reconstruction and neural rendering.
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- 3D reconstruction and neural rendering / [SLAM and driving scene reconstruction](https://mlsanity.com/recon3d/slam-and-driving-scene-reconstruction/)

## Builds on (most cited first, 11 of 11)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [GauU-Scene V2: Assessing the Reliability of Image-Based Metrics with Expansive Lidar Image Dataset Using 3DGS and NeRF](https://mlsanity.com/paper/2404.04880/) (2024)

## Abstract (arXiv)

Exterior Gaussian-splat twins for real-estate listings are captured to a fixed recipe: a consumer drone orbits a single property in several overlapping passes at stepped altitudes, with occasional vertical ascents, so the imagery is dense, sequential, GPS- and time-tagged, and revisits each facade from many angles. This structure is tantalizing: it suggests camera poses could be recovered by a dense pose-graph optimization (PGO) whose only unknowns are the poses, far fewer than the joint pose-and-point problem bundle adjustment (BA) solves. PGO is mature in robotics, but almost always as post-processing: it redistributes the drift of an already-decent trajectory once loop closures tie it together. Splatting captures push that regime to its limit, every frame closing loops with dozens of others, raising a clean question: does pose-only optimization reach BA accuracy? We built a system specialized to this capture structure, not a general-purpose SfM tool, to test it. It beat COLMAP on speed but never on quality; this paper is the candid post-mortem. The shortfall arises from several interacting causes, hand-set weights, greedy merging and a noisy GPS ruler, together with two limits inherent to the formulation: SE(3) edges carry no scale degree of freedom, so independently scaled sub-maps drift when merged, and a two-view edge stops short of the coupling one 3D point imposes on every frame that sees it. A viable design must add back Sim(3) constraints, absolute GPS priors, retained structure, and uncertainty-aware weighting