Paper · ≈ 1 min read
UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction
Outgoing relations
- addresses → Novel View Synthesis (Task)
- evaluated_on → DTU (Benchmark)
- part_of → 3D/4D Vision and Reconstruction (ResearchField)
- part_of → Research Literature (ResearchField)
- uses_metric → LPIPS (Metric)
- uses_metric → PSNR (Metric)
- uses_metric → SSIM (Metric)
Connected node types
- Metric: 3
- ResearchField: 2
- Benchmark: 1
- Task: 1
Mentions in the corpus
- part_of Evidence: At the same time, neural radiance fields have revolutionized novel view…
- mentioned_in Claim: At the same time, neural radiance fields have revolutionized novel view synthesis.
- part_of Evidence: Our experiments demonstrate that we outperform NeRF in terms of reconst…
- part_of Evidence: Experiments on DTU, BlendedMVS, and an internal synthetic indoor datase…
- summarizes Project Pulse
- summarizes Field Overview — 3D/4D Vision and Reconstruction
- summarizes Field Overview — Research Literature
Cross-references in raw data
Source provenance
examples/demo-corpus/data/research/papers/arxiv-2104-10078/abstract.md