Research map / 3D vision / NeRF and radiance fields
ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes ACRF, a framework that compresses explicit NeRF representations by reformulating them as 3D point-cloud data and applying attribute compression after pruning.
Problem
Compressing explicit neural radiance field (NeRF) models, which store large numbers of per-point attributes and are costly to store and transmit.
Approach
Treats explicit NeRF compression as 3D data compression: the neural 3D structure is pruned and converted to a point cloud, then its attributes are compressed with an attribute compression scheme.
Closest papers by meaning
- Neural NeRF Compression (ICML 2024 · similarity 0.94)
- NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation (CVPR 2024 · similarity 0.93)
- CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis (AAAI 2025 · similarity 0.90)
- How Far Can We Compress Instant-NGP-Based NeRF? (CVPR 2024 · similarity 0.89)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 2024 · similarity 0.89)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · 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.