Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
In this work we address the challenging problem of multiview 3D surface reconstruction. We introduce a neural network architecture that simultaneously learns the unknown geometry, camera parameters, and a neural renderer that approximates the light reflected from the surface towards the camera. The geometry is represented as a zero level-set of a neural network, while the neural renderer, derived from the rendering equation, is capable of (implicitly) modeling a wide set of lighting conditions and materials. We trained our network on real world 2D images of objects with different material properties, lighting conditions, and noisy camera initializations from the DTU MVS dataset. We found our model to produce state of the art 3D surface reconstructions with high fidelity, resolution and detail.
Code (3)
Tasks
3D Reconstruction3D Shape RepresentationSurface ReconstructionSimilar Papers 제목 키워드 기반
Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction
Photometric stereo (PS) is an established technique for high-detail reconstruction of 3D geometry and appearance. To correct for surface integration errors, PS is often combined with multiview stereo (MVS). With dynamic …
3D geometry3D ReconstructionOptical Flow EstimationVocal Bursts Intensity Prediction4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video
4D reconstruction of equine family (e.g. horses) from monocular video is important for animal welfare. Previous mainstream 4D animal reconstruction methods require joint optimization of motion and appearance over a whole…
NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images
We present NeRSP, a Neural 3D reconstruction technique for Reflective surfaces with Sparse Polarized images. Reflective surface reconstruction is extremely challenging as specular reflections are view-dependent and thus …
3D ReconstructionSurface ReconstructionSIRA: Relightable Avatars from a Single Image
Recovering the geometry of a human head from a single image, while factorizing the materials and illumination is a severely ill-posed problem that requires prior information to be solved. Methods based on 3D Morphable Mo…
Surface ReconstructionTexture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editing
3D Gaussian splatting, emerging as a groundbreaking approach, has drawn increasing attention for its capabilities of high-fidelity reconstruction and real-time rendering. However, it couples the appearance and geometry o…
DisentanglementGPU