Research map / 3D vision / 3D generation
Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction
Hansheng Chen, Jiatao Gu, Anpei Chen, Wei Tian, Zhuowen Tu, Lingjie Liu, Hao Su
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 |
|---|---|---|---|
| train NeRF auto-decoder and diffusion jointly in a single stage instead of two stages (ablation) | SSDNeRF · SRN Cars unconditional generation | KID /10^-3: 6.38 -> 3.47 | Improved |
| single-stage training instead of two-stage (ablation) | SSDNeRF · SRN Cars 1-view reconstruction | FID: 20.97 -> 16.39 | Improved |
| add diffusion loss during test-time finetuning (ablation) | SSDNeRF · SRN Cars 1-view reconstruction | FID: 27.93 -> 16.39 | Improved |
| add rendering-loss test-time finetuning over guided sampling (ablation) | SSDNeRF · SRN Cars 1-view reconstruction | PSNR: 23.07 -> 23.13 | No clear effect |
| longer training schedule for reconstruction of unseen objects | SSDNeRF · SRN sparse-view reconstruction | reconstruction quality | Hurt |
| train on only 3 views per scene (6% of data) | SSDNeRF · SRN Cars single-view reconstruction | LPIPS: 0.106 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- DiffRF — DiffRF: Rendering-Guided 3D Radiance Field Diffusion (CVPR 2023) · better on 2 of 2 shared results
- CodeNeRF — CodeNeRF: Disentangled Neural Radiance Fields for Object Categories (ICCV 2021) · better on 1 of 2 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
- ReconFusion: 3D Reconstruction with Diffusion Priors (CVPR 2024 · similarity 0.91)
- Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views (AAAI 2024 · similarity 0.91)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.91)
- Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning (CVPR 2024 · similarity 0.90)
- FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors (CVPR 2025 · similarity 0.90)
- DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models (CVPR 2025 · similarity 0.90)
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.
