AI Paper Atlas

Research map / 3D vision / Depth and stereo

GTT-Net: Learned Generalized Trajectory Triangulation

Xiangyu Xu, Enrique Dunn

ICCV 2021 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 3 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
replace iterative DLOE optimization with learned affinity estimationDLOE · affinity matrix estimation across sequence lengthsruntime: ~30X average speedupImproved
keep only Q=2 highest affinities per row (sparsity level) (ablation)GTT-Net · CMU mocap reconstruction3D reconstruction errorImproved
train with decorrelated joint motion instead of original motion (ablation)PointNet GTT-Net · mocap, cross-domain testreconstruction errorHurt
add 3D supervision cascade stage 2 on top of self-supervised stage 1 (ablation)GTT-Net · CMU mocapreconstruction errorNo clear effect
use multi-domain PointNet variant instead of single-domain 3D-supervised training (ablation)GTT-Net · mocap, unseen test domainreconstruction errorNo clear effect

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