Let There Be Color! Large-Scale Texturing of 3D Reconstructions

By Michael Waechter, Nils Moehrle, Michael Goesele. European Conference on Computer Vision, 2014

395 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b8f1ea118487d8500d45e5fbf95ab80eedd7fa92

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

SceneNet: An annotated model generator for indoor scene understanding (2016, methodology): “RGB reconstruction from images of a SceneNet synthetic bedroom and living-room using VisualSfM [3] and [32]. data and we leave it as future work.”
Gibson Env: Real-World Perception for Embodied Agents (2018, background): “Further, when multiple images in the input are available, a smart selection mechanism (often referred to as Image Based Rendering) can help with lighting inconsistencies and handling more difficult and non lambertian surfaces [40, 60, 90], compared to rendering from a textured mesh or as such entire”
NeRF-: Neural Radiance Fields Without Known Camera Parameters (2021, background): “One group aims to explicitly reconstruct the surface geometry and the appearance on the surface from the observed sparse views [Chaurasia et al. 2013; Debevec et al. 1996; Hedman et al. 2017; Waechter et al. 2014; Wiles et al. 2020; Zitnick et al. 2004].”
Pixelwise View Selection for Unstructured Multi-View Stereo (2016, methodology): “, [58]) for visualization purposes and, since the points already have normals, we can directly apply meshing algorithms (e.”
Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction (2021, background): “Mesh-based representations [8, 54, 58, 63] can run in real-time but have a hard time with gradient-based optimization without template meshes provided.”
KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs (2021, methodology): “Mesh-based methods, including classical [5, 9, 65, 69] and learning-based [45, 46, 61] ones, typically require a preprocessing step, e.”
PlenOctrees for Real-time Rendering of Neural Radiance Fields (2021, methodology): “Mesh based methods represent the scene with surfaces, and have been used to model Lambertian (diffuse) [54] and nonLambertian scenes [58, 5, 3].”
Colored Point Cloud Registration Revisited (2017, background): “Multi-view stereo pipelines reconstruct colored point clouds from image collections [8, 13, 39].”