Research map / Image generation / Fast diffusion sampling
Contrastive Diffusion Guidance for Spatial Inverse Problems
Sattwik Basu, Chaitanya Amballa, Zhongweiyang Xu, Jorge Vančo Sampedro, Srihari Nelakuditi, Romit Roy Choudhury
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 intersection penalty (7e-4 vs 0) (ablation) | CoGuide · HouseExpo, dense | F1: 0.91 -> 0.95 | Improved |
| add intersection penalty (7e-4 vs 0) (ablation) | CoGuide · HouseExpo, sparse | IoU: 0.78 -> 0.84 | Improved |
| increase intersection weight from 7e-4 to 1.5e-3 (ablation) | CoGuide · HouseExpo, dense | F1: 0.95 -> 0.94 | Hurt |
| use Adam instead of GD in guidance step (ablation) | CoGuide (DDIM) · HouseExpo | F1: 0.86 -> 0.92 | Improved |
| use Adam instead of GD in guidance step (ablation) | CoGuide (DDPM) · HouseExpo | F1: 0.92 -> 0.94 | Improved |
| CoGuide instead of DPS with differentiable path planners | diffusion inverse solver · HouseExpo, sparse | F1: 0.79 -> 0.91 | Improved |
| CoGuide vs CFG at sparse trajectories | floorplan diffusion · HouseExpo, sparse | F1: 0.86 -> 0.91 | Improved |
| CoGuide vs CFG at dense trajectories | floorplan diffusion · HouseExpo, dense | F1: 0.97 -> 0.95 | Hurt |
| combine CFG prior with CoGuide guidance | CFG · HouseExpo, sparse | F1: 0.86 -> 0.93 | Improved |
| increase measurement noise on trajectories (ablation) | CoGuide · HouseExpo | IoU | Hurt |
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.
- DMPlug — DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models (NeurIPS 2024) · better on 3 of 3 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
- SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems (ICML 2025 · similarity 0.88)
- A Variational Perspective on Solving Inverse Problems with Diffusion Models (ICLR 2024 · similarity 0.87)
- BADGR: Bundle Adjustment Diffusion Conditioned by Gradients for Wide-Baseline Floor Plan Reconstruction (CVPR 2025 · similarity 0.86)
- DEFT: Efficient Fine-tuning of Diffusion Models by Learning the Generalised $h$-transform (NeurIPS 2024 · similarity 0.86)
- Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes (CVPR 2025 · similarity 0.86)
- Solving Video Inverse Problems Using Image Diffusion Models (ICLR 2025 · 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.
