AI Paper Atlas

Research map / Video / Video generation

GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion

Hanxin Zhu, Cong Wang, Peiyan Tu, Jiayi Luo, Tianyu He, Xin Jin, Zhibo Chen

IJCV 2026 · Video › Video generation · approach: Trajectory-guided motion control · 2 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
use geometry-then-appearance instead of simultaneous appearance and geometry generation (ablation)GTA · DL3DV (20 large-viewpoint scenes)PSNR: 15.03 -> 17.14Improved
use two-stage geometry-then-appearance instead of a single joint RGB-depth diffusion model (ablation)GTA · DL3DV eval (55 scenes)PSNR: 16.62 -> 17.47Improved
use two-stage geometry-then-appearance instead of a single joint RGB-depth diffusion model (ablation)GTA · DL3DV eval (55 scenes)R-err: 0.022 -> 0.013Improved
use two-stage geometry-then-appearance instead of a single joint RGB-depth diffusion model (ablation)GTA · DL3DV (20 large-viewpoint scenes)LPIPS: 0.418 -> 0.367Improved
add Random Latent Shuffle during training (ablation)GTA · DL3DV eval (55 scenes)PSNR: 16.83 -> 17.47Improved
add Random Latent Shuffle during training (ablation)GTA · DL3DV eval (55 scenes)LPIPS: 0.389 -> 0.342Improved
raise shuffle probability from 0.50 to 1.00 (ablation)GTA · DL3DV eval (55 scenes)PSNR: 17.47 -> 17.22Hurt
raise shuffle probability from 0.00 to 0.50 (ablation)GTA · DL3DV eval (55 scenes)LPIPS: 0.389 -> 0.342Improved
shuffle noisy and target latents but not the conditioning latent (inconsistent shuffle) versus no shuffle (ablation)GTA · DL3DV eval (55 scenes)PSNR: 16.83 -> 16.35Hurt
permute conditioning latents consistently with noisy and target latents versus inconsistent shuffle (ablation)GTA · DL3DV eval (55 scenes)PSNR: 16.35 -> 17.47Improved
add test-time scaling with masked-warping (ablation)GTA · DL3DV eval (55 scenes)FID: 38.32 -> 34.54Improved
add test-time scaling with masked-warping (ablation)GTA · DL3DV eval (55 scenes)PSNR: 17.47 -> 17.35Hurt

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