arXiv Computer Vision By Magnus Kaufmann Gjerde, Joakim Bruslund Haurum, Jeppe Revall Frisvad, Markus Worchel, J. Andreas B{\ae}rentzen, Thomas B. Moeslund

Point-Based 3D Reconstruction from Sparse Views under Known Illumination

Read the original on arXiv Computer Vision →

arXiv:2608. 20000v1 Announce Type: new Abstract: Sparse view 3D reconstruction is commonly addressed with neural implicit surfaces or dense point-based representations such as Gaussian splatting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Hugging Face Trending Papers
3d ago

CoMVS-GS: Collaborative Multi-View Stereo and 3D Gaussian Splatting for Surface Reconstruction

3D Gaussian Splatting enables efficient novel view synthesis, but accurate mesh reconstruction remains difficult in weakly observed and occluded regions, where Gaussian primitives may grow into unstable or geometrically inconsistent structures. We propose CoMVS-GS, a general surface reconstruction framework that combines Multi-View Stereo with Gaussian splatting.

arXiv AI
Jul 1

Intrinsic decomposition and editing of 3D Gaussian splats

arXiv:2606. 31637v1 Announce Type: cross Abstract: Intrinsic decomposition which expresses image colors as the product of diffuse albedo and shading, possibly augmented with view-dependent residuals has a long history in image editing as it enables the modification of object colors and textures without altering lighting.

By Alexandre Lanvin, Jeffrey Hu, Simon Lucas, Adrien Bousseau, George Drettakis