AI Paper Atlas

Research map / 3D vision / Gaussian splatting

TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks

Jinjie Mai, Wenxuan Zhu, Sara Rojas, Jesus Zarzar, Abdullah Hamdi, Guocheng Qian, Bing Li, Silvio Giancola, Bernard Ghanem

ECCV 2024 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 13 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 feature-track reprojection loss to BARF (ablation)BARF · DTU (3 views, 15% noise)PSNR: 10.70 -> 18.07Improved
add track keypoint refinement (ablation)TrackNeRF · DTU (3 views, 15% noise)PSNR: 18.07 -> 18.39Improved
add depth regularization loss (ablation)TrackNeRF · DTU (3 views, 15% noise)PSNR: 18.39 -> 18.53Improved
add feature-track loss on forward-facing LLFFTrackNeRF vs SPARF · LLFF (3 views, no poses)PSNR: 19.58 -> 19.60No clear effect
allow longer feature tracks (max length 2 to 6) (ablation)TrackNeRF · DTU 6 views (one scene)PSNR: 13.15 -> 19.56Improved
increase initial pose noise from 15% to 45% (ablation)TrackNeRF · DTU 3 views (one scene)PSNR: 16.14 -> 8.34Hurt
add track keypoint adjustment to SPARF (ablation)SPARF · DTU (3 views, 15% noise)PSNR: 17.74 -> 17.84Improved
apply depth loss in both stages instead of only stage 2 (ablation)TrackNeRF · DTU (3 views, 15% noise)Rotation error (deg): 1.12 -> 1.49Hurt
increase depth regularization weight to 10^0 or lower to 10^-2 (ablation)TrackNeRF · DTUvisual and numeric qualityHurt
use global feature tracks instead of pairwise (SPARF) correspondences, 6 viewsTrackNeRF vs SPARF · DTU (6 noisy views)PSNR: 21.39 -> 22.78Improved
reduce training to 23K iterations (ablation)TrackNeRF · DTU (3 views, 15% noise)PSNR (masked): 19.65 -> 19.35 at 10.3h vs 27.4hMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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