REPOGEO REPORT · LITE

minghanqin/LangSplat

Default branch main · commit d70edb86 · scanned 5/31/2026, 8:48:08 AM

GitHub: 1,054 stars · 110 forks

AI VISIBILITY SCORE

40 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

2 pass · 0 warn · 0 fail

Objective metadata checks

AI knows your name

3 / 3

Direct prompts that named your repo

HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface minghanqin/LangSplat, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION

highreadme#1

Reposition README opening to state problem/solution first

Why:

CURRENT

# [CVPR2024 Highlight] LangSplat: 3D Language Gaussian Splatting 
Minghan Qin*, Wanhua Li*†, Jiawei Zhou*, Haoqian Wang†, Hanspeter Pfister<br>(\* indicates equal contribution, † means Co-corresponding author)<br>| Webpage | Full Paper | Video |<br>
| Preprocessed Dataset | BaiduWangpan | GoogleDrive |<br>
| Pre-trained Models | BaiduWangpan | GoogleDrive |<br>
| Datasets |<br>

This repository contains the official authors implementation associated with the paper "LangSplat: 3D Language Gaussian Splatting" (CVPR 2024), which can be found here. We further provide the preprocessed datasets 3D-OVS with language feature, as well as pre-trained models.

COPY-PASTE FIX

LangSplat enables natural language interaction and semantic understanding for 3D scenes by integrating language features directly into 3D Gaussian Splatting. This repository provides the official implementation of our CVPR 2024 Highlight paper, 'LangSplat: 3D Language Gaussian Splatting'. We further provide preprocessed datasets (3D-OVS with language features) and pre-trained models.

# [CVPR2024 Highlight] LangSplat: 3D Language Gaussian Splatting 
Minghan Qin*, Wanhua Li*†, Jiawei Zhou*, Haoqian Wang†, Hanspeter Pfister<br>(\* indicates equal contribution, † means Co-corresponding author)<br>| Webpage | Full Paper | Video |<br>
| Preprocessed Dataset | BaiduWangpan | GoogleDrive |<br>
| Pre-trained Models | BaiduWangpan | GoogleDrive |<br>
| Datasets |<br>

mediumtopics#2

Expand topics with semantic and multimodal keywords

Why:

CURRENT

3d, 3d-gaussian-splatting, 3d-reconstruction, language

COPY-PASTE FIX

3d, 3d-gaussian-splatting, 3d-reconstruction, language, semantic-understanding, multimodal-ai, scene-representation, embodied-ai, computer-vision, nlp

lowlicense#3

Clarify license details in README

Why:

COPY-PASTE FIX

## License
This project is licensed under a custom license as detailed in the [LICENSE](LICENSE) file. Please refer to the LICENSE file for full details.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall

0 / 2

0% of queries surface minghanqin/LangSplat

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

OpenScene

Recommended in 2 of 2 queries

COMPETITOR LEADERBOARD

OpenScene · recommended 2×
3D-LLM · recommended 2×
CLIP · recommended 1×
CLIP-NeRF · recommended 1×
PointCLIP · recommended 1×

CATEGORY QUERY
How to represent 3D scenes with language features for semantic understanding?
you: not recommended
AI recommended (in order):
1. CLIP
2. CLIP-NeRF
3. PointCLIP
4. CLIP-Forge
5. OpenScene
6. L-NeRF
7. 3D-LLM
8. LLaVA-3D
9. 3DSSG
10. SG-Former
11. AI2-THOR
12. Habitat
13. OWL-ViT
AI recommended 13 alternatives but never named minghanqin/LangSplat. This is the gap to close.
Show full AI answer
CATEGORY QUERY
Need a 3D reconstruction technique that integrates language understanding for detailed scene representation.
you: not recommended
AI recommended (in order):
1. OpenScene
2. CLIP-NeRF / CLIP-Field
3. LISA
4. 3D-LLM
5. SceneGraphFusion / ScanNet with Language Annotations
AI recommended 5 alternatives but never named minghanqin/LangSplat. This is the gap to close.
Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

Metadata completeness
pass
README presence
pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

Compared to common alternatives in this category, what is the core differentiator of minghanqin/LangSplat?
pass
AI named minghanqin/LangSplat explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts minghanqin/LangSplat in production, what risks or prerequisites should they evaluate first?
pass
AI named minghanqin/LangSplat explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
In one sentence, what problem does the repo minghanqin/LangSplat solve, and who is the primary audience?
pass
AI named minghanqin/LangSplat explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of minghanqin/LangSplat. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/minghanqin/LangSplat.svg)](https://repogeo.com/en/r/minghanqin/LangSplat)

HTML

<a href="https://repogeo.com/en/r/minghanqin/LangSplat"><img src="https://repogeo.com/badge/minghanqin/LangSplat.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

minghanqin/LangSplat — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

Deep reports10 / month
Brand-free category queries5 vs 2 in Lite
Prioritized action items8 vs 3 in Lite