Research map / 3D vision / Face and shape
PRIF: Primary Ray-Based Implicit Function
Brandon Y. Feng, Yinda Zhang, Danhang Tang, Ruofei Du, Amitabh Varshney
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 |
|---|---|---|---|
| use reference point f_r instead of Plucker moment vector (ablation) | PRIF · ShapeNetCore Car generative | mean Chamfer distance: 2.397 -> 1.961 | Improved |
| use reference point f_r instead of Plucker moment vector (ablation) | PRIF · ShapeNetCore Chair generative | mean Chamfer distance: 2.603 -> 0.982 | Improved |
| use reference point f_r instead of Plucker moment vector (ablation) | PRIF · ShapeNetCore Lamp generative | mean Chamfer distance: 4.838 -> 3.276 | Improved |
| reparametrize ray with perpendicular foot f_r rather than origin p_r (ablation) | PRIF · single shape and novel rays | Chamfer distance | Improved |
| remove outliers from predicted hit points (ablation) | PRIF · single shape | Chamfer distance | No clear effect |
| reduce MLP width from 2.96M to 1.35M parameters (ablation) | PRIF · ShapeNetCore Car generative | mean Chamfer distance: 1.961 -> 2.055 | Hurt |
| increase noise level from 0.01 to 0.1 (ablation) | PRIF · ShapeNetCore Car denoising | mean Chamfer distance: 1.929 -> 2.842 | Hurt |
| use PRIF instead of SDF | PRIF · Stanford single shape: Buddha | mean Chamfer distance: 6.119 -> 1.443 | Improved |
| use PRIF instead of occupancy function | PRIF · ShapeNetCore Lamp generative | mean Chamfer distance: 143.377 -> 3.276 | Improved |
| use PRIF instead of DeepSDF sphere tracing for rendering | PRIF · 512x512 depth rendering | time (s): 1.01070 -> 0.00578 | Improved |
| use PRIF instead of SDF for Bunny | PRIF · Stanford single shape: Bunny | mean Chamfer distance: 1.717 -> 1.169 | Improved |
Later papers that compared with this method
1 later accepted paper reports PRIF as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency (NeurIPS 2023 · better on 0 of 1 shared result)
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
- RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency (NeurIPS 2023 · similarity 0.88)
- Local Deep Implicit Functions for 3D Shape (CVPR 2020 · similarity 0.87)
- Neural Geometric Level of Detail: Real-Time Rendering With Implicit 3D Shapes (CVPR 2021 · similarity 0.87)
- GIFS: Neural Implicit Function for General Shape Representation (CVPR 2022 · similarity 0.86)
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.85)
- Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance (CVPR 2024 · similarity 0.85)
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.
