Research map / 3D vision / 3D generation
3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
Ze-Xin Yin, Liu Liu, Xinjie Wang, Wei Sui, Zhizhong Su, Jian Yang, Jin Xie
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add coarse-to-fine generation (ablation) | 3D-Fixer · ARSG-110K testset | Scene F-Score: 53.87 -> 54.44 (IoU 44.00 -> 44.52) | Improved |
| add alignment loss (ORFA) (ablation) | 3D-Fixer · ARSG-110K testset | Scene F-Score: 54.44 -> 54.55 (IoU 44.52 -> 45.73) | Improved |
| increase network layers from 6 to 12 to 18 (ablation) | 3D-Fixer · ARSG-110K testset | Scene F-Score: 53.52 -> 54.44 -> 56.40 | Improved |
| add depth-ratio embedding (ablation) | 3D-Fixer · ARSG-110K testset | Scene F-Score: 50.53 -> 50.85 | No clear effect |
| add global feature cross-attention (ablation) | 3D-Fixer · ARSG-110K testset | Scene F-Score: 50.53 -> 50.60 | No clear effect |
| add both depth-ratio embedding and global feature (ablation) | 3D-Fixer · ARSG-110K testset | Scene F-Score: 50.53 -> 54.44 (IoU 36.93 -> 44.52) | Improved |
| mix multiple geometry estimators in training data (ablation) | 3D-Fixer · ARSG-110K testset | Scene F-Score: 54.44 -> 55.20; CDS 0.266 -> 0.272 | Mixed |
| 3D-Fixer vs MIDI on bounding box IoU | 3D-Fixer · MIDI testset | BBox IoU: 0.518 -> 0.492 | Hurt |
| use 3D-Fixer instead of MIDI on out-of-domain complex scenes | 3D-Fixer · ARSG-110K testset | Scene F-Score: 15.35 -> 68.82 | Improved |
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.
- MIDI — MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation (CVPR 2025) · better on 10 of 11 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
- Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors (CVPR 2026 · similarity 0.88)
- Point-based Instance Completion with Scene Constraints (ICLR 2025 · similarity 0.88)
- Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis (NeurIPS 2024 · similarity 0.87)
- SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images (CVPR 2025 · similarity 0.87)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.86)
- World Tracing: Pixel-Aligned Geometry Beyond the Visible (NeurIPS 2026 · similarity 0.86)
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.
