AI Paper Atlas

Research map / 3D vision / 3D generation

OccAny: Generalized Unconstrained Urban 3D Occupancy

Anh-Quan Cao, Tuan-Hung Vu

CVPR 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
add Test-Time View Augmentation via Novel View Rendering (ablation)OccAny · SemanticKITTI sequenceIoU (%): 19.64 -> 25.91Improved
add Test-Time View Augmentation (ablation)OccAny · SemanticKITTI monocularIoU (%): 11.55 -> 24.03Improved
add Segmentation Forcing loss (ablation)OccAny · SemanticKITTI sequenceIoU (%): 24.23 -> 25.91Improved
add geometry-aware confidence weighting in segmentation forcing (ablation)OccAny · SemanticKITTI sequenceIoU (%): 24.88 -> 25.91Improved
add task tokens tg and ts (ablation)OccAny · SemanticKITTI single-frameIoU (%): 22.67 -> 24.03Improved
add encoder distillation loss Lenc in rendering (ablation)OccAny · SemanticKITTI single-frameIoU (%): 23.46 -> 24.03Improved
add Segmentation Forcing for semantic occupancy with Grounded SAM2 (ablation)OccAny · SemanticKITTI sequencemIoU (%): 6.83 -> 7.28Improved
add Segmentation Forcing and NVR over base fine-tuning of MUSt3R (ablation)OccAny base · Occ3D-NuScenes surround-viewIoU (%): 18.53 -> 34.15Improved
add rotations, larger steps and lateral moves to forward-only TTVA (ablation)OccAny · SemanticKITTI sequenceIoU (%): 21.41 -> 25.91Improved
apply TTVA to baselines (CUT3R, AnySplat)CUT3R / AnySplat · SemanticKITTI sequenceIoU (%): CUT3R 13.11 -> 15.93; AnySplat 11.67 -> 12.39Mixed
swap base foundation models to DA3 and SAM3 (OccAny+)OccAny · SemanticKITTI sequence / Occ3D-NuScenes surroundIoU (%): KITTI 25.91 -> 27.33; NuScenes 34.15 -> 33.49Mixed
zero-shot OccAny versus in-domain self-supervised methods on nuScenes surroundOccAny · Occ3D-NuScenes surround-viewIoU (%): 45.19 (GaussTR) vs 34.15Hurt

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