AI Paper Atlas

Research map / 3D vision / 3D generation

LLaVA³: Representing 3D Scenes Like a Cubist Painter to Boost 3D Scene Understanding of VLMs

Doriand Petit, Steve Bourgeois, Vincent Gay-Bellile, Florian Chabot, Loïc Barthe

AAAI 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 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
object-based scene decomposition (ablation)Ray-NeRF · MSR3D testoverall correctness: +6.85Improved
multi-scale hierarchical sampling (ablation)LLaVA3 · MSR3D testoverall correctness: +2.5Improved
filtering segmentation (ablation)LLaVA3 · MSR3D testoverall correctness: +0.55Improved
radar sweeping ordering (ablation)LLaVA3 · MSR3D testoverall correctness: +2.09Improved
adaptive VI-VD instead of even split (ablation)LLaVA3 · MSR3D testoverall correctness: 43.84 -> 44.89Improved
2D object-based decomposition (SAM masks) on LLaVA-OVLLaVA-OV · ScanQA valCIDEr: -3.60Hurt
NeRF reconstruction instead of 2D multi-viewLLaVA-OV · ScanQA valCIDEr: +5.18Improved
joint training of decoder instead of frozen AE (ablation)LLaVA3 · ScanQA subset (4 scenes)CIDEr: 79.63 -> 97.82Improved
pre-train auto-encoder before joint training (ablation)LLaVA3 · ScanQA subset (4 scenes)CIDEr: 96.77 -> 97.82No clear effect
add VI-VD double loss (ablation)LLaVA3 (100% VI) · ScanQA subset (4 scenes)CIDEr: 72.73 -> 90.82Improved
add all three filtering steps (ablation)LLaVA3 · ScanQA subset (4 scenes)CIDEr: 91.68 -> 97.82Improved
add radar sweeping (ablation)LLaVA3 (no multi-scale) · ScanQA subset (4 scenes)CIDEr: 82.19 -> 87.67Improved

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