MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes
Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time rendering or require too much memory to scale to large scenes. We present a Memory-Efficient Radiance Field (MERF) representation that achieves real-time rendering of large-scale scenes in a browser. MERF reduces the memory consumption of prior sparse volumetric radiance fields using a combination of a sparse feature grid and high-resolution 2D feature planes. To support large-scale unbounded scenes, we introduce a novel contraction function that maps scene coordinates into a bounded volume while still allowing for efficient ray-box intersection. We design a lossless procedure for baking the parameterization used during training into a model that achieves real-time rendering while still preserving the photorealistic view synthesis quality of a volumetric radiance field.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration
Recent techniques for real-time view synthesis have rapidly advanced in fidelity and speed, and modern methods are capable of rendering near-photorealistic scenes at interactive frame rates. At the same time, a tension h…
Novel View SynthesisSlimmeRF: Slimmable Radiance Fields
Neural Radiance Field (NeRF) and its variants have recently emerged as successful methods for novel view synthesis and 3D scene reconstruction. However, most current NeRF models either achieve high accuracy using large m…
3D Scene ReconstructionNeRFNovel View SynthesisOblique-MERF: Revisiting and Improving MERF for Oblique Photography
Neural implicit fields have established a new paradigm for scene representation, with subsequent work achieving high-quality real-time rendering. However, reconstructing 3D scenes from oblique aerial photography presents…
Compressing Volumetric Radiance Fields to 1 MB
Approximating radiance fields with volumetric grids is one of promising directions for improving NeRF, represented by methods like Plenoxels and DVGO, which achieve super-fast training convergence and real-time rendering…
Model CompressionNeRFNeural RenderingQuantizationTransformerFAM: Feedback attention is working memory
While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architec…