AI Paper Atlas

Research map / 3D vision / 3D generation

MVGBench: a Comprehensive Benchmark for Multi-view Generation Models

Xianghui Xie, Jan Eric Lessen, Gerard Pons-Moll

ICCV 2025 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 3 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 SV3D on same objects (ablation)SV3D · GSOcPSNR: 26.751 -> 27.708Improved
add RCN camera embedding (ablation)SV3D fine-tuned · GSOcPSNR: 27.708 -> 28.257Improved
add CaP camera embedding (ablation)SV3D fine-tuned · GSOcPSNR: 27.708 -> 27.980Improved
combine RCN and CaP embeddings (ablation)SV3D fine-tuned · GSOcPSNR: 28.257 -> 27.809Hurt
replace CLIP with ConvNextV2 encoder (ablation)SV3D+CaP · GSOcPSNR: 27.980 -> 28.934Improved
replace CLIP with DINOv2 encoder (ablation)SV3D+CaP · GSOcPSNR: 27.980 -> 28.507Improved
add SyncDreamer 3D convolution synchronization (ablation)SV3D+CaP+ConvNextV2 · GSOcPSNR: 28.934 -> 28.881No clear effect
increase training objects from 10k to 150k (ablation)SV3D+CaP+ConvNextV2 · CO3D (real)cPSNR: 24.261 -> 25.994Improved
increase training objects from 50k to 150k (ablation)SV3D+CaP+ConvNextV2 · GSO (synthetic)cPSNR: 28.053 -> 28.934Mixed
pass GT multi-views through SV3D autoencoder (ablation)GT multi-view images · GSO30cPSNR: 31.94 -> 30.29Hurt
use per-object oFID instead of dataset-level FIDimage quality metric · user studyagreement with human rankings: 0.50 -> 0.77Improved
use SV3D-based video model instead of Zero123multi-view generator · GSO (best setup)cPSNR: 17.37 -> 26.75Improved

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