SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration
We present SuperNormal, a fast, high-fidelity approach to multi-view 3D reconstruction using surface normal maps. With a few minutes, SuperNormal produces detailed surfaces on par with 3D scanners. We harness volume rendering to optimize a neural signed distance function (SDF) powered by multi-resolution hash encoding. To accelerate training, we propose directional finite difference and patch-based ray marching to approximate the SDF gradients numerically. While not compromising reconstruction quality, this strategy is nearly twice as efficient as analytical gradients and about three times faster than axis-aligned finite difference. Experiments on the benchmark dataset demonstrate the superiority of SuperNormal in efficiency and accuracy compared to existing multi-view photometric stereo methods. On our captured objects, SuperNormal produces more fine-grained geometry than recent neural 3D reconstruction methods.
Code (1)
Tasks
3D ReconstructionMulti-View 3D ReconstructionSurface ReconstructionSimilar Papers 제목 키워드 기반
NPLMV-PS: Neural Point-Light Multi-View Photometric Stereo
In this work we present a novel multi-view photometric stereo (MVPS) method. Like many works in 3D reconstruction we are leveraging neural shape representations and learnt renderers. However, our work differs from the st…
3D ReconstructionNeRFNeural RenderingPMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction
Reflective and textureless surfaces remain a challenge in multi-view 3D reconstruction.Both camera pose calibration and shape reconstruction often fail due to insufficient or unreliable cross-view visual features. To add…
Surface ReconstructionLearning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
The increasing size of large language models (LLMs) traditionally requires low-precision integer formats to meet strict latency and power demands. Yet recently, alternative formats such as Normal Float (NF4) have increas…
QuantizationMulti-view Normal and Distance Guidance Gaussian Splatting for Surface Reconstruction
3D Gaussian Splatting (3DGS) achieves remarkable results in the field of surface reconstruction. However, when Gaussian normal vectors are aligned within the single-view projection plane, while the geometry appears reaso…
Just Look at the Image: Viewpoint-Specific Surface Normal Prediction for Improved Multi-View Reconstruction
We present a multi-view reconstruction method that combines conventional multi-view stereo (MVS) with appearance-based normal prediction, to obtain dense and accurate 3D surface models. Reliable surface normals reconstru…