# Triangulation-Free Bundle Adjustment with Graduated Non-Convexity for Camera Pose Refinement from Coarse Priors

arXiv: https://arxiv.org/abs/2608.21008 · HTML: https://mlsanity.com/paper/2608.21008/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 70 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 30 of 37)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos](https://mlsanity.com/paper/2412.04463/) (2024)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [Self-Calibrating Neural Radiance Fields](https://mlsanity.com/paper/2108.13826/) (2021)
- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [SPARF: Neural Radiance Fields from Sparse and Noisy Poses](https://mlsanity.com/paper/2211.11738/) (2022)
- [COLMAP-Free 3D Gaussian Splatting](https://mlsanity.com/paper/2312.07504/) (2023)
- [ViPE: Video Pose Engine for 3D Geometric Perception](https://mlsanity.com/paper/2508.10934/) (2025)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (2024)
- [LaMAR: Benchmarking Localization and Mapping for Augmented Reality](https://mlsanity.com/paper/2210.10770/) (2022)
- [Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection](https://mlsanity.com/paper/1909.08605/) (2019)
- [Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer](https://mlsanity.com/paper/2404.14351/) (2024)
- [Detector-Free Structure from Motion](https://mlsanity.com/paper/2306.15669/) (2023)
- [InstantSplat: Sparse-view Gaussian Splatting in Seconds](https://mlsanity.com/paper/2403.20309/) (2024)
- [Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2211.11505/) (2022)
- [CamP: Camera Preconditioning for Neural Radiance Fields](https://mlsanity.com/paper/2308.10902/) (2023)
- [Shonan Rotation Averaging: Global Optimality by Surfing SO(p)n](https://mlsanity.com/paper/2008.02737/) (2020)
- [Certifiably Optimal Outlier-Robust Geometric Perception: Semidefinite Relaxations and Scalable Global Optimization](https://mlsanity.com/paper/2109.03349/) (2021)
- [A Pose-only Solution to Visual Reconstruction and Navigation](https://mlsanity.com/paper/2103.01530/) (2021)
- [PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction](https://mlsanity.com/paper/2310.07449/) (2023)
- [MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices](https://mlsanity.com/paper/2303.01932/) (2023)
- [Adaptive Robust Kernels for Non-Linear Least Squares Problems](https://mlsanity.com/paper/2004.14938/) (2020)
- [Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment](https://mlsanity.com/paper/2405.05079/) (2024)

## Abstract (arXiv)

Mobile AR frameworks attach a metric pose prior to every casual phone capture, and turning it into reconstruction-grade poses cheaply on CPU is the step before novel-view synthesis. The least a refiner owes an accurate prior is not to make it worse. The workhorse refiner does. On 15 ScanNet++ iPhone room captures, COLMAP triangulation plus prior-seeded bundle adjustment degrades an accurate ARKit prior in all 15, 0.55 degrees to 0.74 degrees by scene-mean. The cause is the seeding. Structure is triangulated from the prior before anything is optimized, so the prior's error is baked into the structure the optimizer trusts. We remove the triangulation. Every keypoint owns a scalar depth along its own back-projected ray and each match contributes two symmetric cross-projection residuals, so structure is re-expressed at every iterate. The same solve holds the room prior at 0.57 degrees and never fails in 330 perturbed room runs, and at object scale reaches 0.265 degrees/1.80 mm from a prior at 0.456 degrees in a median of 10 s per scene on one CPU, against 2.5 GPU-hours for a learned refiner. Because no structure is committed, the objective also admits graduated non-convexity, which measures how deep the defect goes. Classical refinement collapses past 1-2 degrees of prior error, barely beyond a real ARKit prior, and no classical refinement arm survives 32 degrees. Ours recovers 425 of 425 runs through 16 degrees/80 mm and 85% at 32 degrees/160 mm, and perturbed rooms through 32 degrees. Nominal object-scale accuracy is on par rather than better, on a benchmark at its own noise floor, where classical bundle adjustment is a strong baseline absent from the literature. One scene fails for every solver already at zero perturbation. Re-mapping from position priors matches us in the prior's frame but discards it, so it cannot exploit a prior worth keeping or be warm-started.