Xiamen University researcher building neuro-symbolic frameworks for explainable 3D reconstruction from point clouds
2
papers here
1
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-17) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Output volume cannot be scored yet: this snapshot covers only two 2026 arXiv preprints, with no publication counts, venue record, or cumulative totals, so this axis — total papers, venues, and yearly output over time — remains unmeasured.
Impact—
Impact cannot be scored: no citation counts, h-index, or uptake data accompany the two reviewed preprints, so this axis — citation influence and adoption by other researchers — has insufficient underlying data to estimate.
Focus100/100
Focus scores 100/100: the bibliometric field distribution is concentrated in a single field — computer vision / geometric modeling (3D reconstruction) — and both reviewed 2026 papers, NeuSOGA and NeuSOGA3D, advance one coherent neuro-symbolic program from point-cloud symbolic abstraction to explainable 3D geometric reconstruction, indicating a tightly specialized research agenda rather than dispersed topics.
Collaboration36/100
Collaboration scores 36/100, based on 5 distinct coauthors in the snapshot. The recurring partners are Qingde Li, Zihan Li, and Jie Tian; on both 2026 preprints the researcher holds a middle author position without corresponding-author role, pointing to a small, stable, senior-led team rather than a broad independent network.
Activity—
Activity is not yet scored: the snapshot holds only two 2026 arXiv preprints with no multi-year publication series, so this axis — publication cadence and sustained output pace over time — lacks sufficient data to evaluate.
Reproducibility20/100
Reproducibility scores 20/100, from a reproMean of 20 computed over 1 paper. Evolve's verdicts report purely visual or qualitative evaluation — no quantitative metrics, no baselines, no released code — and both NeuSOGA papers carry a low reproReadiness rating, leaving empirical validation and artifact availability as the program's clearest gap.
Research summary
Qingqi Hong is a researcher at Xiamen University whose Evolve-visible work centers on neuro-symbolic methods for 3D geometry: turning raw visual observations into explicit, human-readable symbolic mathematical representations. The catalog currently contains two 2026 arXiv preprints. NeuSOGA introduces a training-free O→T→G→S pipeline that transforms point clouds and segmentation masks into symbolic implicit area splines, drawing on Segment Anything, the Euclidean Distance Transform, and scale-space theory, with Scan-to-CAD as the motivating application. NeuSOGA3D extends the program to explainable 3D geometric reconstruction, combining visual-hull extraction with PSPS lofting and neuro-symbolic point-cloud reasoning grounded in constructive solid geometry and shape-preserving blending. Evolve's verdicts credit both papers with coherent mathematics while flagging a consistent weakness: evaluation is purely visual or qualitative, with no quantitative metrics, baselines, or released code — yielding low reproducibility readiness and a reproducibility score of 20/100. The radar profile is sharply specialized, with a focus score of 100/100 and the field distribution concentrated in computer vision / geometric modeling (3D reconstruction). Collaboration scores 36/100 across 5 distinct coauthors, with recurring partners Qingde Li, Zihan Li, and Jie Tian, and middle authorship without corresponding role on both preprints. Output, impact, and activity axes remain unscored pending fuller bibliometric coverage.
Collaboration pattern
The snapshot shows a compact collaboration footprint: 5 distinct coauthors and a collaboration score of 36/100. Work recurs with Qingde Li, Zihan Li, and Jie Tian, and in both 2026 arXiv preprints Qingqi Hong appears in a middle author position without corresponding-author status — consistent with contributing to a small, stable, senior-led group rather than leading an independent network. No international collaboration data is available.
Research keywords
Highlights
Training-free path from point clouds to symbolic math (NeuSOGA)
NeuSOGA3D: explainable 3D reconstruction via visual hull and PSPS lofting
Timeline
- 2026Posts the NeuSOGA preprint to arXiv: a training-free O→T→G→S pipeline converting point clouds and segmentation masks into symbolic implicit area splines.
- 2026Posts the NeuSOGA3D preprint to arXiv, extending the program to explainable 3D geometric reconstruction via visual hull and PSPS lofting.
- 2026Both preprints enter the Evolve catalog; reviews note coherent mathematics but purely qualitative evaluation and low reproducibility readiness.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Profile is name-resolved from public bibliographic data; no ORCID or country record was available to confirm identity.
- Bibliometric scores derive from an OpenAlex-scope public snapshot only; citation counts, venue history, and publication totals are not included.
- Coverage is limited to two 2026 arXiv preprints reviewed by Evolve; journal or conference publications may exist outside this snapshot.
- Output, impact, and activity axes are unscored because their underlying data is insufficient; the reproducibility score (20/100) reflects only 1 assessed paper.