@@ -124,6 +124,7 @@ <h2 class="title is-3">Abstract</h2>
124124 changes in reconstructed images, revealing that orthogonal rotations — rather than spatial transformations
125125 — control color encoding. Our approach can be applied to any vision encoder, shedding light on the inner
126126 structure of its feature space.
127+ </ p >
127128 </ div >
128129 </ div >
129130 </ div >
@@ -139,26 +140,33 @@ <h2 class="title is-3">Abstract</h2>
139140 <!-- Нужно четко подчеркнуть какие различия между модельками -->
140141 <!-- И как это влияет на реконструкцию -->
141142
142- < div class ="columns is-centered has-text-centered ">
143- < div class ="column is-four-fifths ">
144- < h2 class ="title is-3 " style ="white-space: nowrap; "> Reconstruct images from feature space</ h2 >
145- < div class ="content has-text-justified ">
146- < div style ="text-align: center; ">
147- < img src ="./static/images/features_reconstruction.drawio.png " alt ="features_reconstruction " width ="900 ">
148- < p class ="caption " style ="width: 100%; text-align: center; ">
149- < b > Figure 1. Image reconstructor training.</ b > For pretrained model we train a reconstructor model that
150- restores the image from the feature space.
151- </ p >
152- < img src ="./static/images/reconstruction_metrics.jpg " alt ="reconstruction_metrics " width ="900 ">
153- < p class ="caption " style ="width: 100%; text-align: center; ">
154- < b > Figure 2. Reconstruction Metrics.</ b > We show the results of the reconstruction for SigLip and SigLip2
155- for different image resultions.
156- </ p >
143+ < section class ="section ">
144+ < div class ="container is-max-desktop ">
145+ < div class ="columns is-centered ">
146+ < div class ="column is-four-fifths ">
147+ < h2 class ="title is-3 has-text-centered "> Reconstruct images from feature space</ h2 >
148+ < div class ="content ">
149+ < div class ="has-text-centered ">
150+ < figure class ="image is-16by9 mb-6 ">
151+ < img src ="./static/images/features_reconstruction.drawio.png " alt ="features_reconstruction " class ="is-rounded ">
152+ </ figure >
153+ < p class ="caption has-text-centered mb-6 ">
154+ < b > Figure 1. Image reconstructor training.</ b > For pretrained model we train a reconstructor model that
155+ restores the image from the feature space.
156+ </ p >
157+ < figure class ="image is-16by9 mb-6 ">
158+ < img src ="./static/images/reconstruction_metrics.jpg " alt ="reconstruction_metrics " class ="is-rounded ">
159+ </ figure >
160+ < p class ="caption has-text-centered mb-6 ">
161+ < b > Figure 2. Reconstruction Metrics.</ b > We show the results of the reconstruction for SigLip and SigLip2
162+ for different image resultions.
163+ </ p >
164+ </ div >
165+ </ div >
157166 </ div >
158167 </ div >
159- < br > < br >
160168 </ div >
161- </ div >
169+ </ section >
162170
163171 <!-- (2) Feature-space transformations -->
164172 <!-- Текстовое объяснение -->
@@ -168,81 +176,115 @@ <h2 class="title is-3" style="white-space: nowrap;">Reconstruct images from feat
168176 <!-- Примеры Спектра такой м-цы, показать, что только небольшое кол-во каналов меняется -->
169177 <!-- -->
170178
171- < div class ="columns is-centered has-text-centered ">
172- < div class ="column is-four-fifths ">
173- < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Q matrix Calculation and Application.</ h2 >
174- < div class ="content has-text-justified ">
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 >
179+ < section class ="section ">
180+ < div class ="container is-max-desktop ">
181+ < div class ="columns is-centered ">
182+ < div class ="column is-four-fifths ">
183+ < h2 class ="title is-3 has-text-centered "> Feature-space transformations. Q matrix Calculation and Application.</ h2 >
184+ < div class ="content ">
185+ < div class ="columns is-centered ">
186+ < div class ="column is-half ">
187+ < figure class ="image is-16by9 mb-6 ">
188+ < img src ="./static/images/features_reconstruction_manipulation_train_Q.drawio.png " alt ="features_reconstruction_manipulation_train_Q " class ="is-rounded ">
189+ </ figure >
190+ < p class ="caption has-text-centered mb-6 ">
191+ < b > Figure 3. Feature-space transformations. Q matrix Calculation.</ b > We then calculate Q matrix for feature-space manupulation.
192+ </ p >
193+ </ div >
194+ < div class ="column is-half ">
195+ < figure class ="image is-16by9 mb-6 ">
196+ < img src ="./static/images/features_reconstruction_manipulation_eval_Q.drawio.png " alt ="features_reconstruction_manipulation_eval_Q " class ="is-rounded ">
197+ </ figure >
198+ < p class ="caption has-text-centered mb-6 ">
199+ < 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.
200+ </ p >
201+ </ div >
202+ </ div >
203+ </ div >
185204 </ div >
186205 </ div >
187- < br > < br >
188206 </ div >
189- </ div >
207+ </ section >
190208
191- < div class ="columns is-centered has-text-centered ">
192- < div class ="column is-four-fifths ">
193- < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Color Swap Examples.</ h2 >
194- < div class ="content has-text-justified ">
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 >
209+ < section class ="section ">
210+ < div class ="container is-max-desktop ">
211+ < div class ="columns is-centered ">
212+ < div class ="column is-four-fifths ">
213+ < h2 class ="title is-3 has-text-centered "> Feature-space transformations. Color Swap Examples.</ h2 >
214+ < div class ="content ">
215+ < div class ="columns is-centered ">
216+ < div class ="column is-half ">
217+ < figure class ="image is-16by9 mb-6 ">
218+ < img src ="./static/images/rb_swap.png " alt ="rb_swap " class ="is-rounded ">
219+ </ figure >
220+ < p class ="caption has-text-centered mb-6 ">
221+ < b > Figure 5. Red-blue channel swap samples.</ b >
222+ </ p >
223+ </ div >
224+ < div class ="column is-half ">
225+ < figure class ="image is-16by9 mb-6 ">
226+ < img src ="./static/images/color_swap_all_eigen_values.png " alt ="color_swap_all_eigen_values " class ="is-rounded ">
227+ </ figure >
228+ < p class ="caption has-text-centered mb-6 ">
229+ < 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.
230+ </ p >
231+ </ div >
232+ </ div >
233+ </ div >
205234 </ div >
206235 </ div >
207- < br > < br >
208236 </ div >
209- </ div >
237+ </ section >
210238
211- < div class ="columns is-centered has-text-centered ">
212- < div class ="column is-four-fifths ">
213- < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Blue Channel Suppression.</ h2 >
214- < div class ="content has-text-justified ">
215- < div style ="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; ">
218- < b > Figure 7. Blue channel suppression samples.</ b >
219- </ p >
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; ">
223- < b > Figure 8. Eigenvalues for blue channel suppression matrix.</ b >
224- </ p >
239+ < section class ="section ">
240+ < div class ="container is-max-desktop ">
241+ < div class ="columns is-centered ">
242+ < div class ="column is-four-fifths ">
243+ < h2 class ="title is-3 has-text-centered "> Feature-space transformations. Blue Channel Suppression.</ h2 >
244+ < div class ="content ">
245+ < div class ="columns is-centered ">
246+ < div class ="column is-half ">
247+ < figure class ="image is-16by9 mb-6 ">
248+ < img src ="./static/images/b_suppression_all_transformations.png " alt ="b_suppression_all_transformations " class ="is-rounded ">
249+ </ figure >
250+ < p class ="caption has-text-centered mb-6 ">
251+ < b > Figure 7. Blue channel suppression samples.</ b >
252+ </ p >
253+ </ div >
254+ < div class ="column is-half ">
255+ < figure class ="image is-16by9 mb-6 ">
256+ < img src ="./static/images/b_suppression_all_eigen_values.png " alt ="b_suppression_all_eigen_values " class ="is-rounded ">
257+ </ figure >
258+ < p class ="caption has-text-centered mb-6 ">
259+ < b > Figure 8. Eigenvalues for blue channel suppression matrix.</ b >
260+ </ p >
261+ </ div >
262+ </ div >
263+ </ div >
225264 </ div >
226265 </ div >
227- < br > < br >
228266 </ div >
229- </ div >
267+ </ section >
230268
231- < div class ="columns is-centered has-text-centered ">
232- < div class ="column is-four-fifths ">
233- < h2 class ="title is-3 " style ="white-space: nowrap; "> Feature-space transformations. Colorization.</ h2 >
234- < div class ="content has-text-justified ">
235- < div style ="text-align: center; ">
236- < img src ="./static/images/colorized_examples.png " alt ="colorization_all_transformations " width ="900 ">
237- < p class ="caption " style ="width: 100%; text-align: center; ">
238- < b > Figure 9. Colorization samples.</ b >
239- </ p >
269+ < section class ="section ">
270+ < div class ="container is-max-desktop ">
271+ < div class ="columns is-centered ">
272+ < div class ="column is-four-fifths ">
273+ < h2 class ="title is-3 has-text-centered "> Feature-space transformations. Colorization.</ h2 >
274+ < div class ="content ">
275+ < div class ="has-text-centered ">
276+ < figure class ="image is-16by9 mb-6 ">
277+ < img src ="./static/images/colorized_examples.png " alt ="colorization_all_transformations " class ="is-rounded ">
278+ </ figure >
279+ < p class ="caption has-text-centered mb-6 ">
280+ < b > Figure 9. Colorization samples.</ b >
281+ </ p >
282+ </ div >
283+ </ div >
240284 </ div >
241285 </ div >
242286 </ div >
243- < br > < br >
244- </ div >
245- </ div >
287+ </ section >
246288
247289
248290
@@ -290,6 +332,46 @@ <h2 class="title">BibTeX</h2>
290332
291333 <!-- End of Statcounter Code -->
292334
335+ <!-- Add modal HTML structure -->
336+ < div id ="imageModal " class ="modal ">
337+ < span class ="modal-close "> ×</ span >
338+ < img class ="modal-content " id ="modalImage ">
339+ </ div >
340+
341+ < script >
342+ // Get the modal
343+ const modal = document . getElementById ( "imageModal" ) ;
344+ const modalImg = document . getElementById ( "modalImage" ) ;
345+ const closeBtn = document . getElementsByClassName ( "modal-close" ) [ 0 ] ;
346+
347+ // Add click event to all images
348+ document . querySelectorAll ( '.image.is-16by9 img' ) . forEach ( img => {
349+ img . onclick = function ( ) {
350+ modal . style . display = "block" ;
351+ modalImg . src = this . src ;
352+ }
353+ } ) ;
354+
355+ // Close modal when clicking the close button
356+ closeBtn . onclick = function ( ) {
357+ modal . style . display = "none" ;
358+ }
359+
360+ // Close modal when clicking outside the image
361+ window . onclick = function ( event ) {
362+ if ( event . target == modal ) {
363+ modal . style . display = "none" ;
364+ }
365+ }
366+
367+ // Close modal with Escape key
368+ document . addEventListener ( 'keydown' , function ( event ) {
369+ if ( event . key === "Escape" ) {
370+ modal . style . display = "none" ;
371+ }
372+ } ) ;
373+ </ script >
374+
293375</ body >
294376
295377</ html >
0 commit comments