Research map / Point clouds / Point cloud classification
C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 Hilbert sorting to C-Flow for point-cloud modeling (ablation) | C-Flow · ShapeNet image → point cloud | CD: 0.86 -> 0.52 | Helped |
| Add global-feature coupling after sorting (ablation) | C-Flow · ShapeNet image → point cloud | CD: 0.52 -> 0.49 | Helped |
| Use Chamfer distance for cycle consistency (ablation) | C-Flow with sorting and global-feature coupling · ShapeNet image → point cloud | CD: 0.49 -> 0.26 | Helped |
| Add invertible cycle consistency (ablation) | C-Flow · Cityscapes segmentation → street views | SSIM: 0.37 -> 0.42 | Helped |
| Add invertible cycle consistency (ablation) | C-Flow · Cityscapes segmentation → street views | BPD: 3.21 -> 3.17 | Helped |
| Add invertible cycle consistency (ablation) | C-Flow · CMP Facades structure ← facades | BPD: 3.55 -> 3.55 | No clear effect |
| Add invertible cycle consistency (ablation) | C-Flow · CMP Facades structure → facades | IS: 1.92 -> 1.69 | Hurt |
| Add invertible cycle consistency (ablation) | C-Flow · Maps map → aerial photo | SSIM: 0.19 -> 0.17 | Hurt |
| Add invertible cycle consistency (ablation) | C-Flow · Edges → shoes | SSIM: 0.66 -> 0.67 | Helped |
| Add invertible cycle consistency (ablation) | C-Flow across image-to-image mappings · Image-to-image benchmarks | SSIM | Mixed |
Closest papers by meaning
- CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching (NeurIPS 2025 · similarity 0.88)
- Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching (NeurIPS 2024 · similarity 0.87)
- Cross Flow: One-Step Generation Across Latent and Pixel Spaces (NeurIPS 2026 · similarity 0.87)
- Expanding Flow Maps (NeurIPS 2026 · similarity 0.87)
- Text-to-Image Rectified Flow as Plug-and-Play Priors (ICLR 2025 · similarity 0.87)
- Align Your Flow: Scaling Continuous-Time Flow Map Distillation (NeurIPS 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.