<p>Neural Radiance Fields (NeRF) have been widely adopted as practical and versatile representations for 3D scenes. However, architectures such as plain MLPs, Tensors, low-rank Tensors, and Hashtables each involve distinct trade-offs, making it difficult for a single model to meet diverse task requirements. For example, Hashtables offer fast rendering but lack clear geometric meaning, complicating spatial-relation-aware editing. To overcome these limitations and maximize the potential of each architecture, we propose Progressive Volume Distillation with Active Learning (PVD-AL), a systematic distillation method that enables any-to-any conversion between diverse architectures, which shifts the relationship between these architectures from competition to collaboration. PVD-AL decomposes each structure into two parts and progressively performs distillation from shallower to deeper volume representation, leveraging effective information retrieved from the rendering process. Additionally, a three-level active learning technique provides continuous feedback from teacher to student, achieving high-performance outcomes. Experimental evidence showcases the effectiveness of our method across benchmarks. For instance, PVD-AL distills an MLP-based model from a Hashtables-based model 10<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\times \)</EquationSource> <EquationSource Format="MATHML"><math> <mo>×</mo> </math></EquationSource> </InlineEquation> <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\sim \)</EquationSource> <EquationSource Format="MATHML"><math> <mo>∼</mo> </math></EquationSource> </InlineEquation>20<InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\times \)</EquationSource> <EquationSource Format="MATHML"><math> <mo>×</mo> </math></EquationSource> </InlineEquation> faster with a 0.8dB<InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(\sim \)</EquationSource> <EquationSource Format="MATHML"><math> <mo>∼</mo> </math></EquationSource> </InlineEquation>2dB higher PSNR than training the MLP-based model from scratch. Moreover, PVD-AL permits the fusion of diverse features among distinct structures, enabling models with enhanced editing capabilities and improved hardware adaptability. PVD-AL also exhibits broad adaptability and sustainable evolvability, facilitating efficient conversion between NeRF and 3D Gaussian Splatting (3DGS), with experiments confirming significant performance benefits.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Progressive Volume Distillation with Active Learning for Efficient NeRF Architecture Conversion

  • Shuangkang Fang,
  • Yufeng Wang,
  • Yi Yang,
  • Weixin Xu,
  • Heng Wang,
  • Wenrui Ding,
  • Shuchang Zhou

摘要

Neural Radiance Fields (NeRF) have been widely adopted as practical and versatile representations for 3D scenes. However, architectures such as plain MLPs, Tensors, low-rank Tensors, and Hashtables each involve distinct trade-offs, making it difficult for a single model to meet diverse task requirements. For example, Hashtables offer fast rendering but lack clear geometric meaning, complicating spatial-relation-aware editing. To overcome these limitations and maximize the potential of each architecture, we propose Progressive Volume Distillation with Active Learning (PVD-AL), a systematic distillation method that enables any-to-any conversion between diverse architectures, which shifts the relationship between these architectures from competition to collaboration. PVD-AL decomposes each structure into two parts and progressively performs distillation from shallower to deeper volume representation, leveraging effective information retrieved from the rendering process. Additionally, a three-level active learning technique provides continuous feedback from teacher to student, achieving high-performance outcomes. Experimental evidence showcases the effectiveness of our method across benchmarks. For instance, PVD-AL distills an MLP-based model from a Hashtables-based model 10 \(\times \) × \(\sim \) 20 \(\times \) × faster with a 0.8dB \(\sim \) 2dB higher PSNR than training the MLP-based model from scratch. Moreover, PVD-AL permits the fusion of diverse features among distinct structures, enabling models with enhanced editing capabilities and improved hardware adaptability. PVD-AL also exhibits broad adaptability and sustainable evolvability, facilitating efficient conversion between NeRF and 3D Gaussian Splatting (3DGS), with experiments confirming significant performance benefits.