Research map / 3D vision / Face and shape
GIFS: Neural Implicit Function for General Shape Representation
Jianglong Ye, Yuntao Chen, Naiyan Wang, Xiaolong Wang
Check 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 GIFS instead of NDF | ShapeNet Car watertight reconstruction · ShapeNet Car watertight | Chamfer distance mean: 0.152 -> 0.146 | Improved |
| Use GIFS instead of NDF | ShapeNet Car watertight reconstruction · ShapeNet Car watertight | F1 at 0.01: 98.32 -> 98.09 | Hurt |
| Use GIFS instead of NDF | ShapeNet Car general-shape reconstruction · ShapeNet Car general shapes | Chamfer distance mean: 0.126 -> 0.128 | Hurt |
| Use GIFS instead of NDF | ShapeNet Car general-shape reconstruction · ShapeNet Car general shapes | F1 at 0.005: 88.09 -> 88.05 | No clear effect |
| Use GIFS instead of NDF for mesh conversion and inference | ShapeNet Car general-shape reconstruction · ShapeNet Car general shapes | runtime: 2593 s -> 53 s | Improved |
| Add the UDF branch (ablation) | GIFS · ShapeNet Car watertight | Chamfer distance mean: 0.227 -> 0.146 | Improved |
| Add the UDF branch (ablation) | GIFS · ShapeNet Car watertight | F1 at 0.005: 73.38 -> 88.75 | Improved |
| Add mesh refinement (ablation) | GIFS · ShapeNet Car watertight | Chamfer distance mean: 0.152 -> 0.146 | Improved |
| Increase the extraction grid from 80^3 to 160^3 (ablation) | GIFS surface extraction · ShapeNet Car general shapes | Chamfer distance mean: 0.445 -> 0.128 | Improved |
| Increase the extraction grid from 160^3 to 320^3 (ablation) | GIFS surface extraction · ShapeNet Car general shapes | Chamfer distance mean: 0.128 -> 0.123 | Improved |
| Replace σ 0.005, 0.01, 0.03 with σ 0.003, 0.01, 0.03 (ablation) | GIFS training data sampling · ShapeNet Car general shapes | Chamfer distance mean: 0.128 -> 0.131 | Hurt |
| Use σ 0.01, 0.03 only (ablation) | GIFS training data sampling · ShapeNet Car general shapes | Chamfer distance mean: 0.128 -> 0.137 | Hurt |
Later papers that compared with this method
4 later accepted papers report GIFS as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularization (TPAMI 2025 · better on 7 of 7 shared results)
- Neural Vector Fields for Implicit Surface Representation and Inference (IJCV 2024 · better on 9 of 9 shared results)
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · better on 3 of 3 shared results)
- Neural Vector Fields: Implicit Representation by Explicit Learning (CVPR 2023 · better on 5 of 5 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
- Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing (ICCV 2021 · similarity 0.89)
- Local Deep Implicit Functions for 3D Shape (CVPR 2020 · similarity 0.88)
- NeAT: Learning Neural Implicit Surfaces With Arbitrary Topologies From Multi-View Images (CVPR 2023 · similarity 0.88)
- Implicit Surface Representations As Layers in Neural Networks (ICCV 2019 · similarity 0.88)
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.87)
- LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions (AAAI 2024 · 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.
