AI Paper Atlas

Research map / 3D vision / Gaussian splatting

LESV:Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding

Fusang WANG, Nathan Piasco, Moussab Bennehar, Luis G Roldao Jimenez, Dzmitry Tsishkou, Fabien Moutarde

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add monocular patch-depth and normal supervision to SVRaster (ablation)LESV · Architecture ablation (SAM+CLIP features), ScanNet 19 classesmIoU (%): 30.62 -> 31.37Improved
Add multi-level TSDF depth confidence gating (ablation)LESV · Architecture ablation (SAM+CLIP features), ScanNet 19 classesmIoU (%): 31.37 -> 32.06Improved
Add depth confidence on LERF retrieval (ablation)LESV · Architecture ablation, LERF 3D retrievalmIoU (%): 53.32 -> 53.37No clear effect
Swap SAM+CLIP for AM-RADIO in Dr. Splat (ablation)Dr. Splat · Backbone ablation, ScanNet 19 classesmIoU (%): 31.66 -> 37.57Mixed
Use dense AM-RADIO patch features in LESV vs SAM+CLIP features (ablation)LESV · Backbone ablation, ScanNet 19 classesmIoU (%): 32.06 -> 53.22Improved
Replace deep upsampler (AnyUp) with sliding window + SCRA/SCGA (ablation)LESV · Upsampling ablation, LERF 3D retrievalmIoU (%): 48.02 -> 56.11Improved
Add SCRA and SCGA self-correlating aggregation (ablation)LESV · Upsampling ablation, LERF 3D retrievalmIoU (%): 49.79 -> 56.11Improved
Sliding window upsampling without SCRA/SCGA vs raw features (ablation)LESV · Upsampling ablation, LERF 3D retrievalmIoU (%): 51.19 -> 49.79Hurt
SVRaster-based LESV vs Dr. Splat on ScanNet-19LESV · ScanNet 19 classesmIoU (%): 31.66 -> 53.22Improved
LESV vs 2D-specialised methods on LERF 2D retrievalLESV · LERF 2D object retrieval (4 scenes avg)mIoU (%): 61.28 -> 56.84Hurt
Dense feature lifting vs hierarchical multi-level masksLESV · LERF 3D object retrieval (4 scenes avg)mIoU (%): 58.82 -> 56.11Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy