Professional Documents
Culture Documents
It eats, a lot!
Joint Embeddings of Shapes and Images
via CNN Image Purification
128 dim space visualized by t-SNE
Image based Shape Retrieval
Shape based Image Retrieval
Cross-View Image Retrieval
Text Images Shapes
Text based Shape Retrieval
Text based Shape Retrieval
Shape Embedding
𝑆𝑖𝑚𝑖𝑙𝑎𝑟𝑖𝑡𝑦(𝑆𝑖 ,𝑆𝑗 ) = 𝒫𝑖 − 𝒫𝑗
Many choices for 𝒫𝑖 :
Shape Histograms, Spin Images, Spherical
Harmonics, Shape Distributions, etc.
LFD-HoG
Very Strong!
… … … …
HoG HoG HoG HoG HoG
… … … …
Concatenate
𝑆𝟏 𝑆𝟏
𝑆𝟐 𝑆𝟐
𝑆𝟑 𝑆𝟑
. .
. .
. .
. .
.
PCA
.
. .
. .
. .
𝑆𝒌 𝑆𝒌
. .
. .
𝑆𝒏 𝑆𝒏
203,760 128
chairs
planes
cars
𝑆𝒌 𝑆𝒌
. .
. .
𝑆𝒏 𝑆𝒏
Sammon
Num of neighbors by original distance
PCA
200 LLE
NPE
Optimal
150
100
50
0
0 50 100 150 200 250
Neighborhood size in embedding space
Shape Embedding
𝑆𝑖𝑚𝑖𝑙𝑎𝑟𝑖𝑡𝑦(𝑆𝑖 ,𝑆𝑗 ) = 𝒫𝑖 − 𝒫𝑗
Our choice of embedding point 𝒫𝑖 :
1. Extract Light Field HoG Descriptors
2. Compute Distance Matrix
3. MDS with Sammon’s Error
Image Embedding
via CNN Image Purification
Deep learning, yay or nay?
𝒫𝑖 = 𝑓(𝐼𝑖 )
A piece of cake, What the hell is
elementary math…
𝒫2 − 𝒫3 < 𝒫1 − 𝒫2 the 𝑓?
http://shapenet.org
Shape Embedding Image Synthesis
Training Phase
Testing Phase 𝒫𝑖 = 𝑓(𝐼𝑆𝑖 ), the hell function
Quantitative Evaluation
Class Embedding
Label Point