Research map / 3D vision / Face and shape
Neuralangelo: High-Fidelity Neural Surface Reconstruction
Read the paperCheck 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 |
|---|---|---|---|
| Use numerical gradients and progressively activate hash-grid resolutions instead of analytical gradients (ablation) | Neuralangelo · DTU | Chamfer distance (mm): 0.88 -> 0.61 | Helped |
| Use numerical gradients and progressively activate hash-grid resolutions instead of analytical gradients (ablation) | Neuralangelo · DTU | PSNR: 30.55 -> 33.84 | Helped |
| Use numerical gradients and progressively activate hash-grid resolutions instead of analytical gradients (ablation) | Neuralangelo · Tanks and Temples | F1 score: 0.27 -> 0.50 | Helped |
| Use numerical gradients and progressively activate hash-grid resolutions instead of analytical gradients (ablation) | Neuralangelo · Tanks and Temples | PSNR: 25.51 -> 27.24 | Helped |
| Add progressive hash-grid activation to numerical gradients (ablation) | Neuralangelo · DTU | Chamfer distance (mm): 0.65 -> 0.61 | Helped |
| Add progressive hash-grid activation to numerical gradients (ablation) | Neuralangelo · DTU | PSNR: 31.47 -> 33.84 | Helped |
| Add progressive hash-grid activation to numerical gradients (ablation) | Neuralangelo · Tanks and Temples | F1 score: 0.45 -> 0.50 | Helped |
| Add progressive hash-grid activation to numerical gradients (ablation) | Neuralangelo · Tanks and Temples | PSNR: 25.26 -> 27.24 | Helped |
| Add numerical gradients to analytical gradients with progressive activation (ablation) | Neuralangelo · DTU | Chamfer distance (mm): 0.73 -> 0.61 | Helped |
| Add numerical gradients to analytical gradients with progressive activation (ablation) | Neuralangelo · Tanks and Temples | F1 score: 0.30 -> 0.50 | Helped |
| Add curvature regularization (ablation) | Neuralangelo · Surface reconstruction | surface smoothness | Helped |
| Warm up curvature regularization strength instead of applying it from the start (ablation) | Neuralangelo · Concave regions | concave shape formation | Helped |
Closest papers by meaning
- NeAT: Learning Neural Implicit Surfaces With Arbitrary Topologies From Multi-View Images (CVPR 2023 · similarity 0.88)
- Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction (ICLR 2023 · similarity 0.88)
- Iso-Points: Optimizing Neural Implicit Surfaces With Hybrid Representations (CVPR 2021 · similarity 0.87)
- MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video (CVPR 2024 · similarity 0.87)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · similarity 0.86)
- SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration (CVPR 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.