Paper · ≈ 1 min read

HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields

Also known as: arXiv:2106.13228 · Source: examples/demo-corpus/data/research/papers/arxiv-2106-13228/abstract.md

Outgoing relations

• part_of → 3D/4D Vision and Reconstruction (ResearchField)
• uses_metric → LPIPS (Metric)

Connected node types

• Metric: 1
• ResearchField: 1

Mentions in the corpus

• part_of Evidence: We show that our method, which we dub HyperNeRF, outperforms existing m…
• part_of Evidence: Compared to Nerfies, HyperNeRF reduces average error rates by 4.1% for…
• part_of Evidence: On a benchmark of casually captured topology-changing clips, HyperNeRF…
• summarizes Project Pulse
• summarizes Field Overview — 3D/4D Vision and Reconstruction

Related

Paper

Nerfies: Deformable Neural Radiance Fields

score 12.79

Paper

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

score 4.98

Paper

Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields

score 4.58

Paper

MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes

score 4.58

Cross-references in raw data

• examples/demo-corpus/data/research/papers/arxiv-2106-13228/paper.md

Source provenance

examples/demo-corpus/data/research/papers/arxiv-2106-13228/abstract.md

Activity