@@ -170,95 +170,68 @@ <h2 class="title is-3" style="white-space: nowrap;">Reconstruct images from feat
170170
171171 < div class ="columns is-centered has-text-centered ">
172172 < div class ="column is-four-fifths ">
173- < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Q matrix Calculation and
174- Application.</ h2 >
173+ < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Q matrix Calculation and Application.</ h2 >
175174 < div class ="content has-text-justified ">
176- < div class ="columns is-centered ">
177- < div class ="column is-half ">
178- < img src ="./static/images/features_reconstruction_manipulation_train_Q.drawio.png "
179- alt ="features_reconstruction_manipulation_train_Q " width ="70% ">
180- < p class ="caption " style ="width: 70%; text-align: center; ">
181- < b > Figure 3. Feature-space transformations. Q matrix Calculation.</ b > We then calculate Q matrix for
182- feature-space manupulation.
183- </ p >
184- </ div >
185- < div class ="column is-half ">
186- < img src ="./static/images/features_reconstruction_manipulation_eval_Q.drawio.png "
187- alt ="features_reconstruction_manipulation_eval_Q " width ="70% ">
188- < p class ="caption " style ="width: 70%; text-align: center; ">
189- < b > Figure 4. Feature-space transformations. Q matrix Application.</ b > After Q matrix is calculated, we
190- apply it to the feature space. For each patch embedding.
191- </ p >
192- </ div >
175+ < div style ="text-align: center; ">
176+ < img src ="./static/images/features_reconstruction_manipulation_train_Q.drawio.png " alt ="features_reconstruction_manipulation_train_Q " width ="70% ">
177+ < p class ="caption " style ="width: 70%; text-align: center; ">
178+ < b > Figure 3. Feature-space transformations. Q matrix Calculation.</ b > We then calculate Q matrix for feature-space manupulation.
179+ </ p >
180+ < br > < br >
181+ < img src ="./static/images/features_reconstruction_manipulation_eval_Q.drawio.png " alt ="features_reconstruction_manipulation_eval_Q " width ="70% ">
182+ < p class ="caption " style ="width: 70%; text-align: center; ">
183+ < 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.
184+ </ p >
193185 </ div >
194186 </ div >
195187 < br > < br >
196188 </ div >
197189 </ div >
198190
199-
200191 < div class ="columns is-centered has-text-centered ">
201192 < div class ="column is-four-fifths ">
202193 < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Color Swap Examples.</ h2 >
203194 < div class ="content has-text-justified ">
204- < div class ="columns is-centered ">
205- < div class ="column is-half ">
206- < div style ="text-align: center; ">
207- < img src ="./static/images/rb_swap.png " alt ="rb_swap " width ="100% ">
208- < p class ="caption " style ="width: 100%; text-align: center; ">
209- < b > Figure 5. Red-blue channel swap samples.</ b >
210- </ p >
211- </ div >
212- </ div >
213- < div class ="column is-half ">
214- < div style ="text-align: center; ">
215- < img src ="./static/images/color_swap_all_eigen_values.png " alt ="color_swap_all_eigen_values " width ="100% ">
216- < p class ="caption " style ="width: 100%; text-align: center; ">
217- < b > Figure 6. Eigenvalues for red-blue channel swap matrix.</ b > Majority of eigenvalues are close to 1, which
218- means that the transformation is close to an identity matrix. While the other cluster of eigenvalues are
219- close to -1, which means that for these channels direction is changed to the opposite.
220- </ p >
221- </ div >
222- </ div >
195+ < div style ="text-align: center; ">
196+ < img src ="./static/images/rb_swap.png " alt ="rb_swap " width ="70% ">
197+ < p class ="caption " style ="width: 70%; text-align: center; ">
198+ < b > Figure 5. Red-blue channel swap samples.</ b >
199+ </ p >
200+ < br > < br >
201+ < img src ="./static/images/color_swap_all_eigen_values.png " alt ="color_swap_all_eigen_values " width ="70% ">
202+ < p class ="caption " style ="width: 70%; text-align: center; ">
203+ < 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.
204+ </ p >
223205 </ div >
224206 </ div >
207+ < br > < br >
225208 </ div >
226- < br > < br >
227- </ div >
228209 </ div >
229210
230-
231211 < div class ="columns is-centered has-text-centered ">
232212 < div class ="column is-four-fifths ">
233213 < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Blue Channel Suppression.</ h2 >
234214 < div class ="content has-text-justified ">
235-
236215 < div style ="text-align: center; ">
237- < img src ="./static/images/b_suppression_all_transformations.png " alt ="b_suppression_all_transformations "
238- width ="900 ">
239- < p class ="caption " style ="width: 100%; text-align: center; ">
216+ < img src ="./static/images/b_suppression_all_transformations.png " alt ="b_suppression_all_transformations " width ="70% ">
217+ < p class ="caption " style ="width: 70%; text-align: center; ">
240218 < b > Figure 7. Blue channel suppression samples.</ b >
241219 </ p >
242- </ div >
243- < div style ="text-align: center; ">
244- < img src ="./static/images/b_suppression_all_eigen_values.png " alt ="b_suppression_all_eigen_values "
245- width ="900 ">
246- < p class ="caption " style ="width: 100%; text-align: center; ">
220+ < br > < br >
221+ < img src ="./static/images/b_suppression_all_eigen_values.png " alt ="b_suppression_all_eigen_values " width ="70% ">
222+ < p class ="caption " style ="width: 70%; text-align: center; ">
247223 < b > Figure 8. Eigenvalues for blue channel suppression matrix.</ b >
248224 </ p >
249225 </ div >
250226 </ div >
227+ < br > < br >
251228 </ div >
252- < br > < br >
253229 </ div >
254- </ div >
255-
256230
257231 < div class ="columns is-centered has-text-centered ">
258232 < div class ="column is-four-fifths ">
259233 < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Colorization.</ h2 >
260234 < div class ="content has-text-justified ">
261-
262235 < div style ="text-align: center; ">
263236 < img src ="./static/images/colorized_examples.png " alt ="colorization_all_transformations " width ="900 ">
264237 < p class ="caption " style ="width: 100%; text-align: center; ">
0 commit comments