Update index.html

index.html

@@ -208,9 +208,21 @@
             <section class="section">
                 <div class="container is-max-desktop">
                     <div class="columns is-centered has-text-centered">
-                        <img src="static/images/ledits_teaser.jpg"
+                        <img src="static/images/removal.png"
                              class="interpolation-image"
-                             style="max-height:800px; max-width:1200px"
+                             style="max-height:800px; max-width:800px"
+                             alt="examples"/>
+                    </div>
+                    <div class="columns is-centered has-text-centered">
+                        <img src="static/images/replacement.png"
+                             class="interpolation-image"
+                             style="max-height:800px; max-width:800px"
+                             alt="examples"/>
+                    </div>
+                    <div class="columns is-centered has-text-centered">
+                        <img src="static/images/style_transfer.png"
+                             class="interpolation-image"
+                             style="max-height:800px; max-width:800px"
                              alt="examples"/>
                     </div>
                 </div>
@@ -221,13 +233,12 @@
             </div>
             <p>
                 The methodology of LEDITS++ can be broken down into three components: (1) efficient image
-                inversion, (2) versatile textual editing, and (3) semantic grounding of image changes. More in-depth
-                details and mathematical derivations of each component can be found in App
+                inversion, (2) versatile textual editing, and (3) semantic grounding of image changes.
             </p>
 
             <div class="columns is-centered has-text-centered">
-                <img src="static/images/diagram.jpg"
-                     style="max-height:620px; max-width:700px"
+                <img src="static/images/ledits_teaser.jpg"
+                     style="max-height:620px; max-width:1000px"
                      alt="diagram"/>
             </div>
 
@@ -250,6 +261,18 @@
                     <div class="content">
                         <h2 class="title is-4">Component 1: Perfect Inversion</h2>
                         <p>
+                            Utilizing text-to-image models for editing real images is usually done by inverting the sampling process to
+                            identify a noisy xT that will be denoised to the input image x0.
+                            We propose an efficient inversion method that greatly reduces the required number
+                            of steps while maintaining no reconstruction error.
+                            First, DDPM can be viewed as a first-order
+                            stochastic differential
+                            equation
+                            (SDE) solver when
+                            formulating the reverse diffusion process as an SDE. This
+                            SDE can be solved more efficiently—in fewer steps—
+                            using a higher-order differential equation solver, hence we present here dpm-solver++
+                            Inversion.
 
                         </p>
 
@@ -262,6 +285,13 @@
                     <div class="columns is-centered">
                         <div class="column content">
                             <p>
+                                After creating our re-construction sequence, we can edit the image by manipulating
+                                the noise estimate εθ based on a set of edit instructions. We devise a dedicated
+                                guidance term for each concept based on conditioned and unconditioned estimate. We
+                                define LEDITS++ guidance such that it both reflects the direction of the edit (if we
+                                want
+                                to push away from/towards the edit concept) and maximizes fine-grained control over
+                                the effect of the desired edit
 
                             </p>
 
@@ -275,6 +305,12 @@
                     <div class="columns is-centered">
                         <div class="column content">
                             <p>
+                                With LEDITS++, we empirically demonstrate that these maps can also capture regions 290
+                                of an image relevant to an editing concept that is not already present.
+                                Specifically for multiple edits, calculating a
+                                dedicated mask for each edit prompt ensures that the corresponding
+                                guidance terms remain largely isolated, limiting
+                                interference between them.
 
                             </p>