AI Paper Atlas

Research map / 3D vision / Depth and stereo

Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation

Guangkai Xu, Hua Geng, Huanyi Zheng, Songyi Yin, Yanlong Sun, Hao Chen, Chunhua Shen

CVPR 2026 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 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
scale training data from Data1 to Data3 (ablation)VGGT finetuning · KITTI camera poseATE: 1.411 -> 0.937Improved
add noisy datasets (Data3 over Data2) (ablation)VGGT finetuning · KITTI camera poseATE: 1.267 -> 0.937Improved
add spatial gradient loss (ablation)L_reg(W_inv) · KITTI point cloudChamfer L1: 0.254 -> 0.270Hurt
replace learnable confidence weighting with fixed inverse-depth weight (ablation)L_reg + L_conf · KITTI point cloudChamfer L1: 0.270 -> 0.254Improved
add confidence loss L_conf with learnable weights (ablation)VGGT loss · KITTI camera poseATE: 0.937 -> 1.059 (with L_conf, without L_sg: 1.059)Hurt
add temporal gradient loss (ablation)L_reg(W_inv) · KITTI camera poseATE: 0.866 -> 1.270Hurt
add per-frame scale-shift alignment loss L_F (ablation)L_reg(W_inv) · KITTI point cloudChamfer L1: 0.254 -> 0.245Improved
add local region alignment loss L_S (ablation)L_reg(W_inv) + L_F · KITTI point cloudChamfer L1: 0.245 -> 0.255Hurt
add geometric consistency loss (ablation)L_reg(W_inv) + L_F · KITTI camera poseATE: 1.042 -> 0.919Improved
add efficient cross-attention high-resolution fusion (ablation)CARVE · KITTI point cloudChamfer L1: 0.249 -> 0.238Improved
add efficient high-resolution fusion instead of direct high-resolution VGGT input (max 100 frames) (ablation)CARVE · KITTI camera poseATE: 0.355 -> 0.289Improved
use efficient high-resolution fusion instead of direct 1036x1036 inputVGGT · Inference speed, 32 framesFPS: 2.54 -> 15.26Improved

Earlier methods this paper compares with

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