AI Paper Atlas

Research map / 3D vision / 3D generation

Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion

Mutian Xu, Chongjie Ye, Haolin Liu, Yushuang Wu, Jiahao Chang, Xiaoguang Han

ICCV 2025 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 1 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 residual depth generation (instead of direct real depth) (ablation)Stable-Sim2Real · LASA 3D reconstruction, table category, zero-shot ablationmIoU/Chamfer/F-score: 26.4/18.2/22.1 -> 28.5/16.1/24.7Improved
add loss re-weighting in Stage-II (ablation)Stable-Sim2Real · LASA 3D reconstruction, table category, zero-shot ablationmIoU/Chamfer/F-score: 27.1/17.9/23.3 -> 28.5/16.1/24.7Improved
add 3D binary discriminator (instead of difference threshold) (ablation)Stable-Sim2Real · LASA 3D reconstruction, table category, zero-shot ablationmIoU/Chamfer/F-score: 27.3/17.5/23.6 -> 28.5/16.1/24.7Improved
add Stage-III on top of Stage-II (ablation)Stable-Sim2Real · LASA 3D reconstruction, table category, zero-shot ablationmIoU/Chamfer/F-score: 28.5/16.1/24.7 -> 28.6/16.1/24.5No clear effect
add Stage-IV on top of Stage-II (ablation)Stable-Sim2Real · LASA 3D reconstruction, table category, zero-shot ablationmIoU/Chamfer/F-score: 28.5/16.1/24.7 -> 28.0/16.9/24.1Hurt
use patch size 128x128 instead of 32x32 (ablation)Stable-Sim2Real · LASA 3D reconstruction, table category, zero-shot ablationmIoU/Chamfer/F-score: 27.1/16.9/22.6 -> 28.5/16.1/24.7Improved
use classifier width 64 instead of 16 (ablation)Stable-Sim2Real · LASA 3D reconstruction, table category, zero-shot ablationmIoU/Chamfer/F-score: 26.3/17.2/22.8 -> 28.5/16.1/24.7Improved
use classifier width 64 instead of 256 (ablation)Stable-Sim2Real · LASA 3D reconstruction, table category, zero-shot ablationmIoU/Chamfer/F-score: 26.4/18.3/22.5 -> 28.5/16.1/24.7Improved
use fixed weights instead of classifier confidence as soft weight (ablation)Stable-Sim2Real · LASA 3D reconstruction, table category, zero-shot ablationmIoU/Chamfer/F-score: 27.8/15.2/23.9 -> 28.5/16.1/24.7Improved
finetune 2D Stable Diffusion instead of 3D diffusion DiT-3D (ablation)Stable-Sim2Real · LASA 3D reconstruction, table category, zero-shot ablationmIoU/Chamfer/F-score: 26.9/19.1/22.3 -> 28.5/16.1/24.7Improved
add Stage-II enhancement to Stage-I output (ablation)Stable-Sim2Real · 3D binary classifier on simulated patchesclassifier accuracy: 67.8% -> 32.5%Improved
use Cycle-GAN simulated data for pretraining instead of none (ablation)DisCo · LASA 3D reconstruction, few-shot (Chair)mIoU: 24.5 -> 25.1No clear effect

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