Update index.html

Signed-off-by: hg-chung <107260735+hg-chung@users.noreply.github.com>

index.html

@@ -118,7 +118,12 @@ <h1 class="title is-1 publication-title">Differentiable Point-based
         <h2 class="title is-3">Abstract</h2>
         <div class="content has-text-justified">
           <p>
-            We present differentiable point-based inverse rendering, DPIR, an analysis-by-synthesis method that processes images captured under diverse illuminations to estimate shape and spatially-varying BRDF. To this end, we adopt point-based rendering, eliminating the need for multiple samplings per ray, typical of volumetric rendering, thus significantly enhancing the speed of inverse rendering. To realize this idea, we devise a hybrid point-volumetric representation for geometry and a regularized basis-BRDF representation for reflectance. The hybrid geometric representation enables fast rendering through point-based splatting while retaining the geometric details and stability inherent to SDF-based representations. The regularized basis-BRDF mitigates the ill-posedness of inverse rendering stemming from limited light-view angular samples. We also propose an efficient shadow detection method using point-based shadow map rendering. Our extensive evaluations demonstrate that DPIR outperforms prior works in terms of reconstruction accuracy, computational efficiency, and memory footprint. Furthermore, our explicit point-based representation and rendering enables intuitive geometry and reflectance editing.
+            We present differentiable point-based inverse rendering, DPIR, an analysis-by-synthesis method that processes images captured under diverse illuminations to estimate shape and spatially-varying BRDF. 
+            To this end, we adopt point-based rendering, eliminating the need for multiple samplings per ray, typical of volumetric rendering, thus significantly enhancing the speed of inverse rendering. 
+            To realize this idea, we devise a hybrid point-volumetric representation for geometry and a regularized basis-BRDF representation for reflectance. 
+            The hybrid geometric representation enables fast rendering through point-based splatting while retaining the geometric details and stability inherent to SDF-based representations. 
+            The regularized basis-BRDF mitigates the ill-posedness of inverse rendering stemming from limited light-view angular samples. We also propose an efficient shadow detection method using point-based shadow map rendering. 
+            Our extensive evaluations demonstrate that DPIR outperforms prior works in terms of reconstruction accuracy, computational efficiency, and memory footprint. Furthermore, our explicit point-based representation and rendering enables intuitive geometry and reflectance editing.
           </p>
         </div>
       </div>
@@ -136,33 +141,13 @@ <h2 class="title is-3">Abstract</h2>
         <h2 class="title is-3">Method</h2>
         <img src="static/images/intro.png" alt="MY ALT TEXT"/>
         <h2 class="subtitle has-text-centered">
-          Overview of Differentiable forward rendering in DPIR    
-        </div>
-      </div>
-    </div>
-  </div>
-</section>
-
-<section class="section">
-  <div class="container is-max-desktop">   
-      <div class="columns is-centered">      
-        <div class="column is-full-width">
-          <h2 class="title is-3">Neural Spectro-polarimetric Field (NeSpoF)</h2>
-          <div class="column is-centered has-text-centered"><p>$\mathbf{s}, \sigma = F_\Theta(x,y,z,\theta, \phi, \lambda)$</p></div>
-
-          <img src="./static/images/intro.PNG"
-                 class="interpolation-image"
-                 alt="Network architecture."
-                 width="100%"/> 
-          <p>
             (a) For each 3D point, its position is used as a query for the diffuse-albedo MLP $\Theta_d$, SDF MLP $\Theta_\text{SDF}$, and specular-basis coefficient MLP $\Theta_c$. 
             The specular-basis BRDF MLP $\Theta_s$ models specular-basis reflectance, given the incident and outgoing directions $\boldsymbol{\omega_{i}}$ and $\boldsymbol{\omega_{o}}$. 
             The point-based shadow renderer estimates the point visibility from a light source per each image. By using the diffuse albedo, normals, specular reflectance, and visibility, we compute the radiance for each point. 
-            (b) The radiance is then projected onto a camera plane to render the pixel color through splatting-based differentiable forward rendering.
-          </p>
+            (b) The radiance is then projected onto a camera plane to render the pixel color through splatting-based differentiable forward rendering. 
         </div>
       </div>
-    <!--/ Method. -->
+    </div>
   </div>
 </section>