AI Paper Atlas

Research map / 3D vision / 3D generation

Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images

JiaKui Hu, Shanshan Zhao, Qing-Guo Chen, Xuerui Qiu, Jialun Liu, Zhao Xu, Weihua Luo, Kaifu Zhang, Yanye Lu

ICLR 2026 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 14 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 generation training (texture module) to understanding model (ablation)Omni-View (BAGEL-7B-FT) · VSI-Bench Appr. Orderaccuracy: 43.1 -> 47.2Improved
add geometry module (depth) on top of texture (ablation)Omni-View · VSI-Bench Rel. Dist.accuracy: 53.2 -> 63.0Improved
add geometry module (depth) (ablation)Omni-View · VSI-Bench Abs. Dist.accuracy: 44.6 -> 44.9No clear effect
separate texture and geometry modules instead of unified architecture (ablation)Omni-View · VSI-Bench Rel. Dist.accuracy: 63.8 -> 65.9Improved
use autoregressive instead of bidirectional generation (ablation)Omni-View · VSI-Bench Abs. Dist.accuracy: 40.6 -> 46.4Improved
use autoregressive instead of bidirectional generation (ablation)Omni-View · SQA3DEM: 57.2 -> 59.2Improved
use dense-to-sparse reference schedule vs dense only (ablation)Omni-View · ScanQA CIDErCIDEr: 94.7 -> 103.0Improved
use dense-to-sparse vs Ross3D random mask (ablation)Omni-View · ScanQA CIDErCIDEr: 98.9 -> 103.0Improved
add dense-only references (ablation)Omni-View · VSI-Bench Obj. Sizeaccuracy: dense 60.1 vs sparse 65.5Mixed
add stage 2 RGBDP fine-tuning (ablation)Omni-View · Re10k NVS single viewLPIPS: 0.265 -> 0.114Improved
compare to Voyager-13B on NVS pixel fidelityOmni-View · Re10k NVS single viewPSNR: 23.12 -> 23.22No clear effect
compare to 3D-input methods on groundingOmni-View · ScanReferAcc@0.25: 62.6 -> 50.8Hurt

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