# SeMoLi: What Moves Together Belongs Together

Source: [SeMoLi: What Moves Together Belongs Together](<https://www.sota2.com/research/paper/68fa729a1e209131cea576ce>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T05:15:18.128Z

Authors: Jenny Seidenschwarz, Aljo\\v{s}a O\\v{s}ep, Francesco Ferroni, Simon Lucey, Laura Leal-Taix\\'e

Published: 2024-02-29T18:54:53.000Z

## Abstract

We tackle semi-supervised object detection based on motion cues. Recent results suggest that heuristic-based clustering methods in conjunction with object trackers can be used to pseudo-label instances of moving objects and use these as supervisory signals to train 3D object detectors in Lidar data without manual supervision. We re-think this approach and suggest that both, object detection, as well as motion-inspired pseudo-labeling, can be tackled in a data-driven manner. We leverage recent advances in scene flow estimation to obtain point trajectories from which we extract long-term, class-agnostic motion patterns. Revisiting correlation clustering in the context of message passing networks, we learn to group those motion patterns to cluster points to object instances. By estimating the full extent of the objects, we obtain per-scan 3D bounding boxes that we use to supervise a Lidar object detection network. Our method not only outperforms prior heuristic-based approaches (57.5 AP, +14 improvement over prior work), more importantly, we show we can pseudo-label and train object detectors across datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Object Detection on Waymo Open All objects (val)](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-all-objects-val.md>): 3D Object Detection; Waymo Open All objects (val); Pr @ 0.7: 25.4.

- [3D Object Detection on Waymo Open Moving objects (val)](<https://www.sota2.com/research/sota/3d-object-detection-on-waymo-open-moving-objects-val.md>): 3D Object Detection; Waymo Open Moving objects (val); Precision @ IoU=0.7: 0.094.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2402.19463>)

[PDF](<https://arxiv.org/pdf/2402.19463.pdf>)
