Главная
Study mode:
on
1
Intro
2
Geometry + Material
3
Image-based appearance acquisition
4
RGBD reconstructions
5
Projective texture mapping
6
Previous works
7
Our approach
8
Observations
9
Similarity: coherence
10
Similarity: completeness + coherence
11
Consistency
12
Patch-base energy function
13
Multi-scale optimization
14
Comparison against single-view selection
15
Acquisition setup
16
Learning-based multi-view stereo
17
SVBRDF prediction
18
Geometry reconstruction
19
Volumetric representations
20
Relightable reconstructions
21
Joint view synthesis and relighting
22
Mobile phone captures with flashlight
23
Discretized volume rendering
24
Learning deep reflectance volumes
25
Loss functions
26
Comparison to mesh-based methods
27
Comparison on synthetic data
28
Environment map rendering
29
Physically-accurate volume rendering
30
More results
31
Integration with a physically-based rendere
32
Sparse geometry and BRDF acquisition
33
Neural representations for scenes
34
Generalizable neural representations
35
Integration with traditional rendering
Description:
Explore cutting-edge techniques for appearance acquisition in digital 3D content creation through this seminar talk by Sai Bi from UC San Diego. Delve into methods for recovering high-quality texture maps, reconstructing meshes with per-vertex BRDFs, and learning volumetric representations for joint view synthesis and relighting. Gain insights into RGB-D reconstructions, multi-view stereo, SVBRDF prediction, and mobile phone captures with flashlight. Discover the latest advancements in volumetric rendering, neural representations for scenes, and integration with physically-based renderers. Understand the challenges and solutions in reproducing the appearance of real-world objects and scenes for virtual and augmented reality applications.

Appearance Acquisition for Digital 3D Content Creation

Andreas Geiger
Add to list
0:00 / 0:00