Anti-Aliased Neural Implicit Surfaces with Encoding Level of Detail
DescriptionWe present LoD-NeuS, an efficient neural representation for high-frequency geometry detail recovery and anti-aliased novel view rendering. Drawing inspiration from voxel-based representations with the level of detail (LoD), we introduce a multi-scale tri-plane-based scene representation that is capable of capturing the LoD of the signed distance function (SDF) and the space radiance. Our representation aggregates space features from a multi-level convolved featurization within a conical frustum along a ray and optimizes the LoD feature volume through differentiable rendering. Additionally, we propose an error-guided sampling strategy to guide the growth of the SDF during the optimization. Both qualitative and quantitative evaluations demonstrate that our method achieves superior surface reconstructions and photorealistic view synthesis compared to state-of-the-art approaches.
Event Type
Technical Papers
TimeTuesday, 12 December 20239:30am - 12:45pm
LocationDarling Harbour Theatre, Level 2 (Convention Centre)
