# Geometry Beats Estimated Depth: RGB-Only Multi-Camera 3D Tracking under Sim2Real

arXiv: https://arxiv.org/abs/2608.07579 · HTML: https://mlsanity.com/paper/2608.07579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 19 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 18 of 18)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image](https://mlsanity.com/paper/2307.10984/) (2023)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection](https://mlsanity.com/paper/2202.06934/) (2022)
- [Efficiently Reconstructing Dynamic Scenes One D4RT at a Time](https://mlsanity.com/paper/2512.08924/) (2025)
- [V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection](https://mlsanity.com/paper/2308.04409/) (2023)
- [The 7th AI City Challenge](https://mlsanity.com/paper/2304.07500/) (2023)

## Abstract (arXiv)

The AI City Challenge 2026 Track 1 evaluates multi-camera 3D perception in large indoor warehouses under a synthetic-to-real (Sim2Real) setting; depth is available only for training and validation, so inference is RGB-only. We use two RGB-only routes as a controlled test of one hypothesis: that cross-view geometric consistency, not monocular depth accuracy, governs performance under Sim2Real. The first is a geometry-first pipeline: YOLO11x detection, homography lifting to the world frame, class-level 3D size priors, multi-camera fusion, world-coordinate tracking, and offline tracklet stitching. The second is estimated-depth pseudo-LiDAR: monocular depth (D4RT, Metric3D~v2) back-projected into a fused point cloud and passed to a 3D detector (V-DETR), mirroring prior point-cloud winners that used depth. The gap is decisive: geometry-first reaches 13.0 3D HOTA (51.6 LocA), whereas pseudo-LiDAR collapses to 0.12 (9.2 LocA). We trace the collapse to cross-view inconsistency of monocular depth---scale correction is necessary but not sufficient---which domain-adaptation fine-tuning does not repair within budget. Within the geometry pipeline, offline stitching is the only intervention that helps; SAHI detection, appearance Re-ID, learned lifting, RT-DETR ensembling, test-time augmentation, and domain randomization all fail to beat the baseline detector. The bottlenecks are complementary: detection quality bounds the geometry route (DetA), localization consistency bounds pseudo-LiDAR (LocA). We release a complete, reproducible RGB-only pipeline and ablation.