AI Paper Atlas

Research map / 3D vision / 3D generation

Global Pose Control for Generative View Synthesis in Normalized Object Coordinate Space

Zhibing Li, Amogh Gupta, Behnoosh Parsa, Dan Casas

ECCV 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 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 LoRA fine-tuning to off-the-shelf Qwen-Image-Edit with text camera prompts (ablation)Qwen-Image-Edit · Camera conditioning ablationPSNR: 12.48 -> 16.78Improved
Add Plucker camera tokens with global attention (ablation)Baseline + LoRA · Camera conditioning ablationPSNR: 16.78 -> 16.87No clear effect
Replace global attention with regional attention for camera tokens (ablation)Baseline + LoRA + camera tokens · Camera conditioning ablationPSNR: 16.87 -> 20.80Improved
Replace global attention with regional attention for camera tokens (ablation)Baseline + LoRA + camera tokens · Camera conditioning ablationLPIPS: 0.180 -> 0.111Improved
Add front face text definition to training (ablation)Model trained on ABO only · unseen categories (qualitative)qualitativeImproved
Add canonical front view anchoring among generated targets (ablation)Ours · swords and thin objects (qualitative)pose accuracyImproved
Replace detailed captions with category-only captions (ablation)Ours · Toys4k 1 viewPSNR: 18.24 -> 18.18No clear effect
Replace detailed captions with category-only captions (ablation)Ours · Toys4k 5 viewsPSNR: 19.68 -> 19.70No clear effect
Use global NOCS pose control instead of estimated relative input posesOurs vs SEVA · GSO 1 viewPSNR: 15.20 -> 17.25Improved
Use GT input poses for SEVA instead of estimated poses (3 views)SEVA vs Ours · Toys4k 3 viewsPSNR: 21.35 -> 19.31Hurt
Add more input views from 1 to 5Ours · GSOPSNR: 17.25 -> 19.07Improved
Use 2D image-editing NVS instead of image-to-3D generationOurs vs Orientation Matters · Toys4k 1 viewPSNR: 16.94 -> 18.24Improved

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