AI Paper Atlas

Research map / 3D vision / Depth and stereo

SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for RGB+Thermal 3D Reconstruction

Vsevolod Skorokhodov, Chenghao Xu, Shuo Sun, Olga Fink, Malcolm Mielle

ECCV 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction

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
fine-tune VGGT with LoRA adapters and thermal camera tokens for RGB-TVGGT · Public datasets (RGB-T)AUC@30: 22.9 -> 70.0Improved
fine-tune VGGT with LoRA adapters and thermal camera tokens for RGB-TVGGT · SEAR dataset (RGB-T)AUC@30: 23.3 -> 62.8Improved
fine-tune VGGT with LoRA adaptersVGGT · Public datasetsFPS: 10.46 -> 9.94No clear effect
use SEAR instead of MINIMA_ROMARGB-T pose estimation · Public datasetsFPS: 0.05 -> 9.94Improved
add learnable thermal camera token (ablation)SEAR · Public + SEAR datasetsAUC@30: 67.8 -> 68.4No clear effect
add learnable thermal projector instead of thermal camera token (ablation)SEAR · Public + SEAR datasetsAUC@30: 68.4 -> 67.2Hurt
add learnable thermal embedding instead of thermal camera token (ablation)SEAR · Public + SEAR datasetsAUC@30: 68.4 -> 66.1Hurt
apply LoRA to frame-attention layers in addition to global-attention (ablation)SEAR · Public + SEAR datasetsAUC@30: 69.1 -> 68.4No clear effect
apply LoRA to global-attention layers in addition to frame-attention (ablation)SEAR · Public + SEAR datasetsAUC@30: 62.4 -> 68.4Improved
increase LoRA rank r (ablation)SEAR · Public + SEAR datasetsAUC, RRA, RTAImproved
increase thermal-to-RGB image ratio tau (ablation)SEAR · camera pose estimationAUC, RRA, RTAMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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