Hybrid Latents: Geometry-Appearance-Aware Surfel Splatting
We introduce a hybrid Gaussian-hash-grid radiance representation for reconstructing 2D Gaussian scene models from multi-view images. Similar to NeST splatting, our approach reduces the entanglement between geometry and appearance common in NeRF-based models, but adds per-Gaussian latent features alongside hash-grid features to bias the optimizer toward a separation of low- and high-frequency scene components. This explicit frequency-based decomposition reduces the tendency of high-frequency texture to compensate for geometric errors. Encouraging Gaussians with hard opacity falloffs further strengthens the separation between geometry and appearance, improving both geometry reconstruction and rendering efficiency. Finally, probabilistic pruning combined with a sparsity-inducing BCE opacity loss allows redundant Gaussians to be turned off, yielding a minimal set of Gaussians sufficient to represent the scene. Using both synthetic and real-world datasets, we compare against the state of the art in Gaussian-based novel-view synthesis and demonstrate superior reconstruction fidelity with an order of magnitude fewer primitives.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DeepSurfels: Learning Online Appearance Fusion
We present DeepSurfels, a novel hybrid scene representation for geometry and appearance information. DeepSurfels combines explicit and neural building blocks to jointly encode geometry and appearance information. In cont…
Point-Based 3D Reconstruction from Sparse Views under Known Illumination
Sparse view 3D reconstruction is commonly addressed with neural implicit surfaces or dense point-based representations such as Gaussian splatting. Surface-aware splatting methods improve extracted geometry through orient…
3D ReconstructionTopoSurfel: Closing the Loop between Gaussian Surfels and Meshes for Surface Reconstruction
3D Gaussian Splatting has achieved remarkable success in novel view synthesis. However, extracting high-fidelity surfaces directly from 3DGS remains challenging due to its discrete and unstructured nature. Existing 3DGS-…
Novel View SynthesisObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction
Autonomous high-fidelity object reconstruction is fundamental for creating digital assets and bridging the simulation-to-reality gap in robotics. We present ObjSplat, an active reconstruction framework that leverages Gau…
Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries
Though Gaussian splatting has achieved impressive results in novel view synthesis, it requires millions of primitives to model highly textured scenes, even when the geometry of the scene is simple. We propose a represent…
Novel View Synthesis