AI Paper Atlas

Research map / Point clouds / Registration and matching

E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning

Xiuhong Lin, Changjie Qiu, zhipeng cai, Siqi Shen, Yu Zang, Weiquan Liu, Xuesheng Bian, Matthias Müller, Cheng Wang

NeurIPS 2023 · Point clouds › Registration and matching · approach: Learned feature-based registration · 4 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
remove separation of spatial and temporal domains in STA (ablation)E2PNet · MVSEC-E2P (LCD)RE (deg): 3.710 -> 3.606Improved
add the STA module (ablation)E2PNet · MVSEC-E2P (LCD)RE (deg): 3.922 -> 3.606Improved
add LA and FP modules (ablation)E2PNet · MVSEC-E2P (LCD)RE (deg): 4.878 -> 3.606Improved
add LA, STA and FP (full EP2T) (ablation)E2PNet · MVSEC-E2P (LCD)TE (m): 1.297 -> 0.821Improved
replace grayscale images with event tensor from E2PNetLCD · MVSEC-E2PRE (deg): 6.335 -> 3.606Improved
replace grayscale images with event tensor from E2PNetDeepI2P · VECtor-E2PTE (m): 3.176 -> 2.454Improved
replace grayscale images with event tensor from E2PNetLCD · VECtor-E2PTE (m): 13.200 -> 7.403Improved
use tensor output (TR) instead of point-based features (ablation)E2PNet · MVSEC-E2P (LCD)RE (deg): 4.422 -> 3.606Improved
use tensor output (TR) instead of point-based features (ablation)E2PNet · MVSEC-E2P (LCD)TE (m): 0.768 -> 0.821Mixed
add EP2T module to cGAN flow baselinecGAN · Flow estimationAEE: 0.34 -> 0.30Improved
add EP2T module to EV-FlowNetEV-Flow · Flow estimationoutlier %: 0.03 -> 0.03No clear effect
add EP2T module to ESTEST · N-caltech101 recognitionaccuracy: 0.746 -> 0.771Improved

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