AI Paper Atlas

Research map / 3D vision / Depth and stereo

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild

Wang Zhao, Shaohui Liu, Hengkai Guo, Wenping Wang, Yong-Jin Liu

ECCV 2022 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 52 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 trajectory-based motion segmentation to dense trajectories with global BA (ablation)Traj + Global BA · Sintel, successful subsetATE: 0.071 -> 0.046Improved
add trajectory-based motion segmentation (ablation)Traj + Global BA · Sintel, successful subsetRPE rot: 0.969 -> 0.212Improved
add trajectory optimization with path consistency (ablation)Traj + Seg + Global BA · Sintel, full setATE: 0.146 -> 0.129Improved
add trajectory optimization without segmentation (ablation)Traj + Global BA · Sintel, successful subsetATE: 0.071 -> 0.072No clear effect
add MAT motion masks to SIFT global BA (ablation)SIFT + Global BA · Sintel, successful subsetATE: 0.060 -> 0.054Mixed
use dense trajectories with segmentation and optimization instead of SIFT features (ablation)SIFT + Global BA · Sintel, successful subsetATE: 0.060 -> 0.042Improved
add relative depth (MiDaS) input to segmentation network (ablation)Trajectory segmentation network · Sintel motion segmentationmIoU: 54.6 -> 60.6Improved
use transformer encoder instead of MLP encoder (ablation)Trajectory segmentation network · Sintel motion segmentationmIoU: 54.8 -> 60.6Improved
use OANet decoder instead of PointNet decoder (ablation)Trajectory segmentation network · Sintel motion segmentationmIoU: 46.3 -> 60.6Improved
ParticleSfM vs COLMAP on static ScanNet subsetParticleSfM · ScanNet COLMAP subsetATE: 0.171 vs 0.319Hurt
ParticleSfM vs COLMAP on static ScanNet subsetParticleSfM · ScanNet COLMAP subsetRPE rot: 2.900 -> 0.632Improved
ParticleSfM vs DROID-SLAM on SintelParticleSfM · Sintel full setATE: 0.175 -> 0.129Improved

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