AI Paper Atlas

Research map / 3D vision / Depth and stereo

Neural Prior for Trajectory Estimation

Chaoyang Wang, Xueqian Li, Jhony Kaesemodel Pontes, Simon Lucey

CVPR 2022 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 19 citations (OpenAlex)

Check 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
Use NTP instead of the strongest listed baselineNRSfM · drink, pickup, stretch, and dancenormalized mean 3D error ×100: drink: 0.47 -> 0.34; pickup: 2.03 -> 1.84; stretch: 1.62 -> 1.51; dance: 10.22 -> 9.78Improved
Use NTP instead of PAULNRSfM · yoganormalized mean 3D error ×100: 1.71 -> 2.10Hurt
Use NTP instead of PNDNRSfM · sharknormalized mean 3D error ×100: 1.35 -> 9.42Hurt
Add NTP to PAULNRSfM · drink, pickup, yoga, stretch, dance, and sharknormalized mean 3D error ×100: drink: 0.47 -> 0.28; pickup: 2.03 -> 1.16; yoga: 1.71 -> 1.20; stretch: 1.62 -> 1.32; dance: 10.22 -> 8.53; shark: 0.37 Improved
Use NTP rather than JMDense NRSfM · Synthetic face traj. Anormalized mean 3D error: 0.028 -> 0.031Hurt
Use NTP rather than EM-FEMDense NRSfM · Synthetic face traj. Bnormalized mean 3D error: 0.030 -> 0.034Hurt
Replace NSFP Euler integration with direct NTP trajectory estimationLidar scene-flow integration · Argoverse fullAcc 0.5 (%): 45.28 -> 52.28Improved
Replace NSFP Euler integration with direct NTP trajectory estimationLidar scene-flow integration · Argoverse dynamic regionsAcc 0.5 (%): 63.56 -> 69.49Improved
Replace NSFP Euler integration with direct NTP trajectory estimationLidar scene-flow integration · Argoverse fullAcc 1 (%): 59.52 -> 69.88Improved
Replace NSFP Euler integration with direct NTP trajectory estimationLidar scene-flow integration · Argoverse fullOut. (%): 29.33 -> 20.95Improved
Replace NSFP Euler integration with direct NTP trajectory estimationLidar scene-flow integration · Argoverse fullcd-24 (m): 14.09 -> 9.77Improved
Add continuous depth field fz and trajectory code field fϕ (ablation)Dense NRSfM · Synthetic face traj. Anormalized mean 3D error: 0.097 -> 0.032Improved

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