AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Learning 1-Bit LiDAR-based Localization with Auxiliary Objective

Kaijie Yin, Zhiyuan Zhang, Tian Gao, Wentao Zhu, Cheng-zhong Xu, Hui Kong

ECCV 2026 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 0 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 the BiLoc auxiliary objective (information-bottleneck distillation) to 1-bit DiffLoc versus the strongest binarized baseline BHViT1-bit DiffLoc · Oxford Radar RobotCaravg position/orientation error: 8.41 -> 7.56 m, 2.15 -> 1.91 degImproved
add the BiLoc auxiliary objective to 1-bit DiffLoc versus BHViT1-bit DiffLoc · NCLTavg position/orientation error: 3.56 -> 3.14 m, 4.47 -> 4.36 degImproved
binarize DiffLoc to 1-bit (BiLoc) versus real-valuedDiffLoc · Oxford Radar RobotCaravg position error: 3.53 -> 7.56Hurt
binarize DiffLoc to 1-bit (BiLoc) versus real-valuedDiffLoc · NCLTavg position error: 1.19 -> 3.14Hurt
binarize DiffLoc with BiLoc versus real-valued DiffLoc: computeDiffLoc · Model complexityParams (M) / OPs (G): 39.96 -> 3.01 M params, 77.06 -> 0.17 G OPsImproved
binarize DiffLoc with BiLoc versus real-valued: latencyDiffLoc · Latency (RTX 5090)latency (ms): 30.72 -> 14.83Improved
add the auxiliary objective to 1-bit BHViT at inference time1-bit DiffLoc + BHViT · Latency (RTX 5090)latency (ms): 14.83 -> 14.83No clear effect
add auxiliary losses (lambda1 and lambda2 nonzero) versus none (ablation)1-bit DiffLoc + BHViT · Oxford 18-14-14-42 subsetmean position errorImproved
raise distillation weight lambda1 above 0.80 (ablation)BiLoc · Oxford 18-14-14-42 subsetmean position error: optimum at 0.80Hurt
raise structural alignment weight lambda2 above 0.05 (ablation)BiLoc · Oxford 18-14-14-42 subsetmean position error: best at 0.05Hurt

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