AI Paper Atlas

Research map / 3D vision / Human pose estimation

SC-wLS: Towards Interpretable Feed-Forward Camera Re-localization

Xin Wu, Hao Zhao, Shunkai Li, Yingdian Cao, Hongbin Zha

ECCV 2022 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 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 end-to-end fine-tuning stage (ablation)SC-wLS (dlt) · 7Scenes Stairsmedian translation error (m): 0.179 -> 0.123Improved
add end-to-end fine-tuning stage (ablation)SC-wLS (dlt) · Cambridge King's Collegemedian translation error (m): 0.22 -> 0.14Improved
add end-to-end fine-tuning stage (ablation)SC-wLS (dlt) · 7Scenes Chessmedian translation error (m): 0.029 -> 0.029No clear effect
add self-supervised test-time adaptation (ablation)SC-wLS (dlt+e2e) · 7Scenes Stairsmedian translation error (m): 0.123 -> 0.055Improved
add self-supervised test-time adaptation (ablation)SC-wLS (dlt+e2e) · Cambridge Greatcourtmedian translation error (m): 1.64 -> 0.94Improved
add self-supervised test-time adaptation (ablation)SC-wLS (dlt+e2e) · Cambridge Churchmedian translation error (m): 0.39 -> 0.17Improved
add end-to-end stage to LM-Refine pipeline (ablation)SC-wLS (dlt+ref) · Cambridge King's Collegemedian translation error (m): 0.09 -> 0.08Improved
add end-to-end stage to LM-Refine pipeline (ablation)SC-wLS (dlt+ref) · 7Scenes Stairsmedian translation error (m): 0.067 -> 0.058Improved
add end-to-end stage to LM-Refine pipeline (ablation)SC-wLS (dlt+ref) · 7Scenes Pumpkinmedian translation error (m): 0.045 -> 0.051Hurt
replace DLT-initialized LM-Refine with DSAC* post-processing (ablation)SC-wLS (dlt+e2e) · 7Scenes average recallrecall (%): 64.7 -> 80.0Improved
replace DSAC* with SC-wLS weighted DLT feed-forwardMS-Transformer · 7Scenes Chessmedian translation error (m): 0.11 -> 0.029Improved
add LM-Refine to SC-wLS vs DSAC*DSAC* w/o model · Old Hospitalmedian translation error (m): 0.21 -> 0.11Improved

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