GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction
We present GO-Surf, a direct feature grid optimization method for accurate and fast surface reconstruction from RGB-D sequences. We model the underlying scene with a learned hierarchical feature voxel grid that encapsulates multi-level geometric and appearance local information. Feature vectors are directly optimized such that after being tri-linearly interpolated, decoded by two shallow MLPs into signed distance and radiance values, and rendered via surface volume rendering, the discrepancy between synthesized and observed RGB/depth values is minimized. Our supervision signals -- RGB, depth and approximate SDF -- can be obtained directly from input images without any need for fusion or post-processing. We formulate a novel SDF gradient regularization term that encourages surface smoothness and hole filling while maintaining high frequency details. GO-Surf can optimize sequences of $1$-$2$K frames in $15$-$45$ minutes, a speedup of $\times60$ over NeuralRGB-D, the most related approach based on an MLP representation, while maintaining on par performance on standard benchmarks. Project page: https://jingwenwang95.github.io/go_surf/
Code (1)
Tasks
Surface ReconstructionSimilar Papers 제목 키워드 기반
Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction
Direct optimization of interpolated features on multi-resolution voxel grids has emerged as a more efficient alternative to MLP-like modules. However, this approach is constrained by higher memory expenses and limited re…
Computational EfficiencySurface ReconstructionFrom Point Clouds to Mesh Using Regression
Surface reconstruction from a point cloud is a standard subproblem in many algorithms for dense 3D reconstruction from RGB images or depth maps. Methods, performing only local operations in the vicinity of individual poi…
3D Reconstructionglobal-optimizationGPUregression+1Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences
Temporally consistent surface reconstruction of dynamic 3D objects from unstructured point cloud data remains challenging, especially for very long sequences. Existing methods either optimize deformations incrementally, …
GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Clouds
Learning implicit representations has been a widely used solution for surface reconstruction from 3D point clouds. The latest methods infer a distance or occupancy field by overfitting a neural network on a single point …
Surface ReconstructionDirect Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
We present a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses. This task, which is often applied to novel view synthesis, is rece…
GPUNeRFNovel View Synthesis