AI Paper Atlas

Research map / 3D vision / Human pose estimation

DFNet: Enhance Absolute Pose Regression with Direct Feature Matching

Shuai Chen, Xinghui Li, Zirui Wang, Victor Adrian Prisacariu

ECCV 2022 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 104 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 Random View Synthesis (online NeRF-rendered training views) (ablation)DFNet · Shop Facadetranslation/rotation error: 1.49m/5.80 -> 0.86m/4.05Improved
replace original triplet loss with customized in-triplet mining loss (ablation)DFNet · Shop Facadetranslation/rotation error: 0.86m/4.05 -> 0.72m/2.58Improved
add direct feature matching using NeRF-W renderer (ablation)DFNet · Shop Facadetranslation/rotation error: 0.72m/2.58 -> 0.43m/1.62Improved
use histogram-assisted NeRF instead of NeRF-W for direct feature matching (ablation)DFNet_dm · Shop Facadetranslation/rotation error: 0.43m/1.62 -> 0.15m/0.65Improved
add histogram-assisted NeRF to photometric direct matching (ablation)Direct-PN+U · Shop Facadetranslation/rotation error: 1.41m/6.97 -> 0.72m/3.39Improved
add middle-level features to direct matching (ablation)DFNet_dm · Shop Facadetranslation error: 0.15m -> 0.19mHurt
add middle and coarse features to direct matching (ablation)DFNet_dm · Shop Facadetranslation error: 0.15m -> 0.20mHurt
replace triplet loss with MSE loss (ablation)DFNet feature extractor · Kings (Cambridge)feature qualityHurt
add unlabeled feature-metric direct matching finetuning (ablation)DFNet · 7-Scenes (avg)translation/rotation error: 0.12/3.71 -> 0.07/2.21Improved
add unlabeled feature-metric direct matching finetuning (ablation)DFNet · Cambridge Landmarks (avg)translation/rotation error: 1.19/2.90 -> 0.39/0.96Improved
swap VGG16 backbone for EfficientNet-B0 (ablation)DFNet · 7-Scenes (avg)translation/rotation error: 0.12/3.71 -> 0.08/3.47Improved
use online RVS instead of offline LENS-style generation (EfficientNet-B0 vs EB3)DFNet · 7-Scenes (avg)translation/rotation error: 0.08/3.47 vs 0.08/3.00No clear effect

Later papers that compared with this method

6 later accepted papers report DFNet as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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