AI Paper Atlas

Research map / 3D vision / 3D generation

Beyond Single-View Sufficiency: CVBench for Cross-View Human Understanding

Tianchen Guo, Chen Liu, Xin Yu

CVPR 2026 · 3D vision › 3D generation · approach: Semantic scene completion

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
scale open-source MLLM from 7B to 72B/78BQwen2.5-VL · CVBench spatial (All)accuracy (%): 27.2 -> 33.3Improved
use closed-source model instead of best open-source modelMLLMs · CVBench spatial (All)accuracy (%): 34.8 -> 38.6Improved
use closed-source model instead of best open-source modelMLLMs · CVBench temporal (All)accuracy (%): 32.8 -> 34.9Improved
move from coarse-grained to fine-grained tasksGPT-5 · CVBench spatialaccuracy (%): 41.2 -> 35.5Hurt
move from spatial to temporal tasksInternVL3-78B · CVBenchaccuracy (%): 34.8 -> 32.8Hurt
remove images (text-only Blind baseline) (ablation)Gemini-2.5-Flash · CVBench spatial (All)accuracy (%): 37.1 -> 18.5Hurt
compare best model to human performanceGemini-2.5-Pro · CVBench spatial (All)accuracy (%): 94.4 -> 38.6Hurt

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