Research map / 3D vision / Face and shape
Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing
Garvita Tiwari, Nikolaos Sarafianos, Tony Tung, Gerard Pons-Moll
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 canonical mapping network (learned blend weights) instead of nearest-neighbour SMPL weights (ablation) | Neural-GIF canonical SDF · DFAUST | Point2Surface (mm): 18.38 -> 3.28 | Improved |
| add canonical mapping network instead of nearest-neighbour SMPL weights (ablation) | Neural-GIF canonical SDF · DFAUST | IoU: 0.806 -> 0.972 | Improved |
| add canonical mapping network instead of nearest-neighbour SMPL weights (ablation) | Neural-GIF canonical SDF · CAPE | Point2Surface (mm): 12.93 -> 7.93 | Improved |
| add canonical mapping network instead of nearest-neighbour SMPL weights (ablation) | Neural-GIF canonical SDF · ClothSeq | Point2Surface (mm): 11.89 -> 9.18 | Improved |
| add displacement field network and normal prediction on top of canonical mapping network (ablation) | Neural-GIF · CAPE | Point2Surface (mm): 7.93 -> 5.86 | Mixed |
| add displacement field network and normal prediction on top of canonical mapping network (ablation) | Neural-GIF · ClothSeq | Point2Surface (mm): 9.18 -> 4.73 | Improved |
| add displacement field network and normal prediction (ablation) | Neural-GIF · DFAUST | Point2Surface (mm): 3.28 -> 3.21 | Improved |
| use Neural-GIF instead of NASA | implicit clothed human model · ClothSeq | IoU: 0.780 -> 0.967 | Improved |
| use Neural-GIF instead of SCANimate | implicit clothed human model · CAPE | Point2Surface (mm): 5.82 -> 5.86 | No clear effect |
| use Neural-GIF instead of SCANimate | implicit clothed human model · ClothSeq | Point2Surface (mm): 7.32 -> 4.73 | Improved |
| use Neural-GIF instead of TailorNet (template with known registration) | clothing model · TailorNet skirt | Point2Surface (mm): 9.82 -> 11.14 | Hurt |
| use Neural-GIF instead of TailorNet | clothing model · TailorNet shirt | Point2Surface (mm): 7.28 -> 10.98 | Hurt |
Later papers that compared with this method
1 later accepted paper reports Neural-GIF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- COAP: Compositional Articulated Occupancy of People (CVPR 2022 · better on 4 of 4 shared results)
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.
- SCANimate — SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks (CVPR 2021) · better on 7 of 9 shared results
- TailorNet — TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style (CVPR 2020) · better on 0 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
- SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements (CVPR 2021 · similarity 0.90)
- TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style (CVPR 2020 · similarity 0.90)
- GIFS: Neural Implicit Function for General Shape Representation (CVPR 2022 · similarity 0.89)
- NPMs: Neural Parametric Models for 3D Deformable Shapes (ICCV 2021 · similarity 0.88)
- CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition (CVPR 2023 · similarity 0.88)
- The Power of Points for Modeling Humans in Clothing (ICCV 2021 · similarity 0.88)
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.
