Research map / 3D vision / 3D generation
FaithFusion: Harmonizing Reconstruction and Generation via Pixel-wise Information Gain
YuAn Wang, Xiaofan Li, Chi Huang, Wenhao Zhang, Hao Li, Bosheng Wang, Xun Sun, Jun Wang
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 EIG guidance to DIFIX3D+ (ablation) | DIFIX3D+ · Waymo lane shift 6m | FID: 120.24 -> 119.01 | Improved |
| add EIGent dual-stage fusion (ablation) | EIG Guided DIFIX3D+ · Waymo lane shift 6m | FID: 119.01 -> 113.94 | Improved |
| add EIGent dual-stage fusion (ablation) | EIG Guided DIFIX3D+ · Waymo lane shift 6m | FID-UCR: 143.80 -> 137.58 | Improved |
| add EIGent dual-stage fusion (ablation) | EIG Guided DIFIX3D+ · Waymo lane shift 6m | FID-HPR: 149.82 -> 153.69 | Hurt |
| add EIG-weighted reconstruction (progressive integration) (ablation) | EIGent fusion · Waymo lane shift 6m | FID: 113.94 -> 107.47 | Improved |
| add EIG-weighted reconstruction (progressive integration) (ablation) | EIGent fusion · Waymo lane shift 6m | FID-UCR: 137.58 -> 137.02 | Improved |
| add EIG-weighted reconstruction (progressive integration) (ablation) | EIGent fusion · Waymo lane shift 6m | FID-HPR: 153.69 -> 147.75 | Improved |
| full FaithFusion vs DIFIX3D+ with no extra conditions | DIFIX3D+ · Waymo lane shift 3m | FID: 84.12 -> 71.51 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- ReconDreamer — ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration (CVPR 2025) · better on 11 of 12 shared results
- OmniRe — OmniRe: Omni Urban Scene Reconstruction (ICLR 2025) · better on 6 of 6 shared results
- FreeVS — FreeVS: Generative View Synthesis on Free Driving Trajectory (ICLR 2025) · better on 6 of 6 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
- Generative Novel View Synthesis with 3D-Aware Diffusion Models (ICCV 2023 · similarity 0.88)
- Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion (NeurIPS 2026 · similarity 0.88)
- FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views (NeurIPS 2026 · similarity 0.87)
- Coherent 3D Scene Diffusion From a Single RGB Image (NeurIPS 2024 · similarity 0.87)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.87)
- Decompositional Neural Scene Reconstruction with Generative Diffusion Prior (CVPR 2025 · similarity 0.87)
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.
