AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images

Antonín Vobecký, Oriane Siméoni, David Hurych, Spyros Gidaris, Andrei Bursuc, Patrick Perez, Josef Sivic

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Region-level vision-language alignment · 8 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
use detailed nuScenes class descriptions as text queries instead of class names (ablation)POP-3D · nuScenes val 25%, 16 classesmIoU: 10.2 -> 23.0Improved
replace original-5 queries with manmade-5 queries (ablation)POP-3D · nuScenes val 25%, 5 classesmIoU: 27.5 -> 34.7Improved
replace original-5 queries with pedestrian-5 queries (ablation)POP-3D · nuScenes val 25%, 5 classesmIoU: 27.5 -> 35.0Improved
distill into 3D instead of directly transferring MaskCLIP+ featuresPOP-3D · nuScenes LiDAR pointsLiDAR mIoU: 23.0 -> 26.4Improved
POP-3D vs MaskCLIP+ for text-query 3D retrievalPOP-3D · Retrieval benchmarkmAP: 14.9 -> 18.4Improved
class-agnostic occupancy head instead of supervised TPVFormer trainingPOP-3D · nuScenes valclass-agnostic IoU: +11.5 pointsImproved
zero-shot POP-3D vs fully supervised TPVFormerPOP-3D · nuScenes val(16+1)-class mIoU: approx 78%Hurt
lower loss weight lambda from 1.00 to 0.25 (ablation)POP-3D · nuScenes half-res RN50mIoU: 12.0 -> 11.9No clear effect
lower loss weight lambda from 1.00 to 0.50 (ablation)POP-3D · nuScenes half-res RN50IoU: 30.0 -> 30.5No clear effect
RN50 to RN101 backbone (ablation)POP-3D · nuScenes half-resmIoU: 12.0 -> 15.1Improved
half to full input resolution with RN50 (ablation)POP-3D · nuScenesmIoU: 12.0 -> 12.3No clear effect
half to full input resolution with RN101 (ablation)POP-3D · nuScenesmIoU: 15.1 -> 15.2No clear effect

Later papers that compared with this method

1 later accepted paper reports POP-3D as a baseline in their results tables; 1 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