AI Paper Atlas

Research map / 3D vision / Depth and stereo

GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction

Enpeng Li, Yunzhou Zhang, Zhiyao Zhang, Dexuan Lyu, Chenyu Wang, Chiyuan Cui, Cheng Cheng

ECCV 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 0 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 re-normalized LoRA distillation of monocular priors (ablation)DA3 front-end · KITTI seq 00ATE RMSE (m): 6.80 -> 4.35Improved
add re-normalized LoRA fine-tuning to DA3DA3 · KITTI DepthRel: 5.14 -> 4.50Improved
add hybrid ray-matching module (ablation)GRF-Recon · KITTI seq 00ATE RMSE (m): 7.35 -> 4.35Improved
add loop closure (ablation)GRF-Recon · KITTI seq 00ATE RMSE (m): 8.12 -> 4.35Improved
add global backend optimization (ablation)GRF-Recon · KITTI seq 00ATE RMSE (m): 12.35 -> 4.35Improved
use all three ray-matching terms (ray, gradient, photometric) instead of two (ablation)GRF-Recon · KITTI seq 07ATE RMSE (m): 2.45 -> 1.64 (vs ray+grad only)Improved
change chunk size/overlap among 30/10, 60/10, 60/20 (ablation)GRF-Recon · KITTI seq 00ATE RMSE (m): 4.41 / 4.35 / 4.32No clear effect
use GRF-Recon instead of DA3-Streaming for camera trackinglong-sequence feed-forward reconstruction · KITTI (avg excl. seq 01)ATE RMSE (m): 12.72 -> 7.18Improved
use GRF-Recon instead of DA3-Streaminglong-sequence feed-forward reconstruction · Waymo OpenATE RMSE (m): 1.76 -> 1.39Improved
use GRF-Recon vs VGGT-Long on Waymo Chamferlong-sequence reconstruction · Waymo reconstruction seq 460Chamfer: 1.420 (VGGT-Long) vs 1.480Hurt
GRF-Recon vs calibrated ORB-SLAM3tracking · KITTI seq 01ATE RMSE (m): 7.23 (ORB-SLAM3) vs 76.52Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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