AI Paper Atlas

Research map / 3D vision / 3D generation

FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Prediction

Guangcheng Chen, Lihuang Fang, Huaqi Tao, Yicheng He, Li He, Zhang Hong

ECCV 2026 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 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
fine-tune the DAv2 ViT (relative features) (ablation)FLM-Occ (128 superquadrics) · Occ-ScanNetmIoU: 43.9 -> 59.2Improved
fine-tune the DAv2 ViT (metric features) (ablation)FLM-Occ (128 superquadrics) · Occ-ScanNetmIoU: 48.9 -> 59.6Improved
use metric DAv2 instead of relative (frozen ViT) (ablation)FLM-Occ (128 superquadrics) · Occ-ScanNetmIoU: 43.9 -> 48.9Improved
use metric DAv2 instead of relative (finetuned ViT) (ablation)FLM-Occ (128 superquadrics) · Occ-ScanNetmIoU: 59.2 -> 59.6No clear effect
add density regularization loss L_reg (ablation)FLM-Occ (128 superquadrics) · Occ-ScanNetmIoU: 59.6 -> 62.0Improved
increase refinement blocks from 2 to 4 (ablation)FLM-Occ (128 superquadrics) · Occ-ScanNetmIoU: 60.7 -> 62.0Improved
increase refinement blocks from 4 to 5 (ablation)FLM-Occ (128 superquadrics) · Occ-ScanNetmIoU: 62.0 -> 61.8No clear effect
scale encoder from DAv2-ViT-B to ViT-L (ablation)FLM-Occ (128 superquadrics) · Occ-ScanNetmIoU: 62.0 -> 65.0Improved
use superquadrics instead of Gaussians (32 primitives) (ablation)FLM-Occ · Occ-ScanNetmIoU: 48.8 -> 55.9Improved
use superquadrics instead of Gaussians (1024 primitives) (ablation)FLM-Occ · Occ-ScanNetmIoU: 63.6 -> 64.0Improved
increase primitives from 32 to 1024 (superquadrics) (ablation)FLM-Occ · Occ-ScanNetmIoU: 55.9 -> 64.0Improved
increase primitives from 32 to 1024 (superquadrics) (ablation)FLM-Occ · Occ-ScanNetFPS: 32.1 -> 25.4Hurt

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