@@ -168,20 +168,36 @@ <h2 class="title is-3" style="white-space: nowrap;">Reconstruct images from feat
168168
169169 < div class ="columns is-centered has-text-centered ">
170170 < div class ="column is-four-fifths ">
171- < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations</ h2 >
171+ < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Q matrix Calculation and Application. </ h2 >
172172 < div class ="content has-text-justified ">
173+ < img src ="./static/images/features_reconstruction_manipulation_train_Q.drawio.png " alt ="features_reconstruction_manipulation_train_Q " width ="900 ">
174+ < p class ="caption " style ="width: 100%; text-align: center; ">
175+ < b > Figure 3. Feature-space transformations. Q matrix Calculation.</ b > We then calculate Q matrix for feature-space manupulation.
176+ </ p >
173177 < div style ="text-align: center; ">
174- < img src ="./static/images/features_reconstruction_manipulation .drawio.png " alt ="features_reconstruction_manipulation " width ="900 ">
178+ < img src ="./static/images/features_reconstruction_manipulation_eval_Q .drawio.png " alt ="features_reconstruction_manipulation_eval_Q " width ="900 ">
175179 < p class ="caption " style ="width: 100%; text-align: center; ">
176- < b > Figure 3 . Feature-space transformations.</ b > We then calculate Q matrix for feature- space manupulation .
180+ < b > Figure 4 . Feature-space transformations. Q matrix Application. </ b > After Q matrix is calculated, we apply it to the feature space. For each patch embedding .
177181 </ p >
182+ </ div >
183+ </ div >
184+ < br > < br >
185+ </ div >
186+ </ div >
187+
188+
189+ < div class ="columns is-centered has-text-centered ">
190+ < div class ="column is-four-fifths ">
191+ < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Color Swap Examples.</ h2 >
192+ < div class ="content has-text-justified ">
193+
178194 < img src ="./static/images/rb_swap.png " alt ="rb_swap " width ="900 ">
179195 < p class ="caption " style ="width: 100%; text-align: center; ">
180- < b > Figure 4 . Red-blue channel swap samples.</ b > We then calculate Q matrix for feature-space manupulation.
196+ < b > Figure 5 . Red-blue channel swap samples.</ b >
181197 </ p >
182198 < img src ="./static/images/rb_swap_eigenvalues.png " alt ="rb_swap_eigenvalues " width ="900 ">
183199 < p class ="caption " style ="width: 100%; text-align: center; ">
184- < b > Figure 5 . Eigenvalues for red-blue channel swap matrix.</ b > Majority of eigenvalues are close to 1, which means that the transformation is close to an identity matrix. While the other cluster of eigenvalues are close to -1, which means that for these channels direction is changed to the opposite.
200+ < b > Figure 6 . Eigenvalues for red-blue channel swap matrix.</ b > Majority of eigenvalues are close to 1, which means that the transformation is close to an identity matrix. While the other cluster of eigenvalues are close to -1, which means that for these channels direction is changed to the opposite.
185201 </ p >
186202 </ div >
187203 </ div >
@@ -190,6 +206,42 @@ <h2 class="title is-3" style="white-space: nowrap;">Feature-space transformation
190206 </ div >
191207
192208
209+ < div class ="columns is-centered has-text-centered ">
210+ < div class ="column is-four-fifths ">
211+ < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Blue Channel Suppression.</ h2 >
212+ < div class ="content has-text-justified ">
213+
214+ < img src ="./static/images/b_suppression_all_transformations.png " alt ="b_suppression_all_transformations " width ="900 ">
215+ < p class ="caption " style ="width: 100%; text-align: center; ">
216+ < b > Figure 7. Blue channel suppression samples.</ b >
217+ </ p >
218+ < img src ="./static/images/b_suppression_all_eigen_values.png " alt ="b_suppression_all_eigen_values " width ="900 ">
219+ < p class ="caption " style ="width: 100%; text-align: center; ">
220+ < b > Figure 8. Eigenvalues for blue channel suppression matrix.</ b >
221+ </ p >
222+ </ div >
223+ </ div >
224+ < br > < br >
225+ </ div >
226+ </ div >
227+
228+
229+ < div class ="columns is-centered has-text-centered ">
230+ < div class ="column is-four-fifths ">
231+ < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Colorization.</ h2 >
232+ < div class ="content has-text-justified ">
233+
234+ < img src ="./static/images/colorized_examples.png " alt ="colorization_all_transformations " width ="900 ">
235+ < p class ="caption " style ="width: 100%; text-align: center; ">
236+ < b > Figure 9. Colorization samples.</ b >
237+ </ p >
238+ </ div >
239+ </ div >
240+ < br > < br >
241+ </ div >
242+ </ div >
243+
244+
193245
194246 <!-- TODO: add citation -->
195247 <!--BibTex citation -->
0 commit comments