AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Scene Grounding in the Wild

Tamir Cohen, Leo Segre, Shay Shomer-Chai, Shai Avidan, Hadar Averbuch-Elor

CVPR 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 semantic inverse optimization on COLMAP initCOLMAP · WikiEarthrotation error (deg): 4.99 -> 2.48Improved
add semantic inverse optimization on gDLS+++ initgDLS+++ · WikiEarthrotation error (deg): 2.86 -> 2.69 (translation 0.12 -> 0.13)Mixed
add semantic inverse optimization on SP+LG initSP+LG · WikiEarthrotation error (deg): 3.74 -> 3.13Improved
use semantic DINOv2 features instead of photometric loss (ablation)Ours (COLMAP init) · WikiEarthrotation error (deg): 6.48 -> 2.48Improved
use DINOv2 instead of LSeg features (ablation)Ours (COLMAP init) · WikiEarthtranslation error: 0.34 -> 0.12Improved
use DINOv2 instead of DINOv2 + DVT (ablation)Ours (COLMAP init) · WikiEarthrotation error (deg): 2.86 -> 2.48Improved
add Least Trimmed Squares robust optimization (ablation)Ours (COLMAP init) · WikiEarthrotation error (deg): 3.78 -> 2.48Improved
soft (per-iteration) LTS instead of fixed LTS (ablation)Ours (COLMAP init) · WikiEarthrotation error (deg): 2.78 -> 2.48Improved
LTS instead of IRLS (ablation)Ours (COLMAP init) · WikiEarthrotation error (deg): 3.51 -> 2.48Improved
L1 feature loss instead of L2 (ablation)Ours (COLMAP init) · WikiEarthrotation error (deg): 4.21 -> 2.48Improved
ground to reference model instead of feed-forward 3D modelsVGGT/MASt3R/DUSt3R/pi3 · WikiEarth meta-to-referencerotation error (deg): 24.18 (best baseline MASt3R) -> 2.59Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 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