AI Paper Atlas

Research map / 3D vision / 3D generation

MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots

Junseo Kim, Guido Dumont, Xinyu Gao, Gang Chen, Holger Caesar, Javier Alonso-Mora

ECCV 2026 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 2 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 3D LiDAR alignment term L_3D (ablation)human mesh optimization (Ouster-128) · 3DPW full test setPVE: 174.9 -> 50.5Improved
add 3D LiDAR alignment term L_3D (ablation)human mesh optimization (Ouster-32) · 3DPW full test setPVE: 171.2 -> 73.2Improved
add occlusion-aware pose prior L_theta,occ (ablation)human mesh optimization (Ouster-32) · 3DPW full test setPVE: 75.9 -> 73.2Improved
add occlusion-aware pose prior L_theta,occ (ablation)human mesh optimization (Ouster-128) · 3DPW full test setPVE: 52.4 -> 50.5Improved
add visibility filter for occluded body parts (ablation)human mesh optimization (Ouster-64) · 3DPW occluded subset (1,063 frames)PVE: 69.3 -> 66.9Improved
add visibility filter for occluded body parts (ablation)human mesh optimization (Ouster-128) · 3DPW occluded subset (1,063 frames)PA-MPJPE: 38.7 -> 37.2Improved
increase simulated LiDAR density from Ouster-32 to Ouster-128human mesh optimization · 3DPWPVE: 73.2 -> 50.5Improved
add LiDAR-guided test-time optimization to CLIFFCLIFF · SLOPER4DPA-MPJPE: 69.3 -> 43.5Improved
add LiDAR-guided test-time optimization to CLIFFCLIFF · HumanM3PA-MPJPE: 66.5 -> 58.1Improved
use panoptic multi-task head instead of semantic-only FlashOccFlashOcc (8f) · MobileOcc occupancymIoU: 27.18 -> 26.64Hurt
add stereo depth input (VoxFormer-T) versus monocular FlashOccFlashOcc (8f) · MobileOcc occupancypedestrian IoU: 31.91 -> 32.79Mixed
add velocity head to Panoptic-FlashOcc versus BEVDet4DBEVDet4D · MobileOcc pedestrian velocityAVE-T (m/s): 1.00 -> 0.97No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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