Research map / Point clouds / Point cloud classification
Neural Point Light Fields
Check 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 |
|---|---|---|---|
| Represent the light field using sparse point features and one radiance evaluation per ray instead of volumetric sampling | Neural Point Light Fields · Waymo Open Dataset, novel view synthesis | PSNR: 26.15 -> 29.96 | Helped |
| Represent the light field using sparse point features and one radiance evaluation per ray instead of volumetric sampling | Neural Point Light Fields · Waymo Open Dataset, novel view synthesis | LPIPS: 0.310 -> 0.119 | Helped |
| Use learned self-attention to aggregate local point features rather than heuristic inverse-distance weighting (ablation) | Neural Point Light Fields · Waymo Open Dataset, scene reconstruction | reconstruction quality | Helped |
| Use heuristic inverse-distance weighting instead of learned attention (ablation) | Neural Point Light Fields · Waymo Open Dataset, scene reconstruction | reconstruction quality | Hurt |
| Sum selected point features without learned attention (ablation) | Neural Point Light Fields · Waymo Open Dataset, scene reconstruction | trainability | Hurt |
| Use a set of nearby points to condition each ray rather than parameterizing the ray alone (ablation) | Neural Point Light Fields · Waymo Open Dataset, large-scene light fields | reconstruction quality | Helped |
Closest papers by meaning
- Learning Neural Light Fields With Ray-Space Embedding (CVPR 2022 · similarity 0.92)
- NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis (CVPR 2024 · similarity 0.88)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.88)
- GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis (CVPR 2025 · similarity 0.87)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 2024 · similarity 0.87)
- HashPoint: Accelerated Point Searching and Sampling for Neural Rendering (CVPR 2024 · similarity 0.87)
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.