AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

MemDistill: Distilling LiDAR Knowledge into Memory for Camera-Only 3D Object Detection

Donghyeon Kwon, Youngseok Yoon, Hyeongseok Son, Suha Kwak

ICCV 2025 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 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
add student fine-tuning after memory distillation (ablation)MemDistill · nuScenes val (R50)mAP: 0.348 -> 0.425Improved
add student fine-tuning after memory distillation (ablation)MemDistill · nuScenes val (R50)NDS: 0.475 -> 0.531Improved
add memory distillation before fine-tuning (ablation)MemDistill · nuScenes val (R50)mAP: 0.382 -> 0.425Improved
add memory distillation before fine-tuning (ablation)MemDistill · nuScenes val (R50)NDS: 0.498 -> 0.531Improved
use two-stage training instead of end-to-end (ablation)MemDistill · nuScenes val (R50)mAP: 0.369 -> 0.425Improved
use two-stage training instead of end-to-end (ablation)MemDistill · nuScenes val (R50)NDS: 0.475 -> 0.531Improved
add scene-dependent memory retriever instead of scene-agnostic encoder (ablation)MemDistill · nuScenes val (R50)mAP: 0.392 -> 0.425Improved
add scene-dependent memory retriever instead of scene-agnostic encoder (ablation)MemDistill · nuScenes val (R50)NDS: 0.499 -> 0.531Improved
use LiDAR teacher neck and head in student instead of camera neck and head (ablation)MemDistill student · nuScenes val feature discrepancyL2 distance: 501.1 -> 395.7Improved
add memory distillation to LiDAR neck/head student (ablation)MemDistill student · nuScenes val feature discrepancyL2 distance: 395.7 -> 344.3Improved
add fine-tuning on top of memory distillation (ablation)MemDistill student · nuScenes val feature discrepancyL2 distance: 344.3 -> 333.9Improved
add memory retrieval and fusion (ablation)camera BEV features · nuScenes val feature discrepancyL2 distance: 975.2 -> 604.5Improved

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