Merge branch 'main' of https://github.com/AIGCResearch/custyle

index.html

@@ -522,7 +522,7 @@ <h2 class="title is-3">Qualitative Comparisons</h2>
         </figure>
         <div class="content has-text-justified">
           <p>
-            <strong>Qualitative Comparisons:</strong> We compare our method against other state-of-the-art (SOTA) approaches: <em>StyleGaussian</em> (<a href="#liu2024stylegaussian">Liu et al., 2024</a>), <em>IGS2GS</em> (<a href="#igs2gs">IGS2GS Reference</a>), and <em>Ref-NPR</em> (<a href="#zhang2023ref">Zhang et al., 2023</a>) on three datasets (<em>Chair</em>, <em>Hotdog</em>, and <em>Mic</em>) using three styles: <em>Cartoon</em>, <em>Sky Painting</em>, and <em>Fire</em>.
+            <strong>Qualitative Comparisons:</strong> We compare our method against other state-of-the-art (SOTA) approaches: <em>StyleGaussian</em> (<a href="https://kunhao-liu.github.io/StyleGaussian/">Liu et al., 2024</a>), <em>IGS2GS</em> (<a href="https://instruct-gs2gs.github.io/">IGS2GS Reference</a>), and <em>Ref-NPR</em> (<a href="https://ref-npr.github.io/">Zhang et al., 2023</a>) on three datasets (<em>Chair</em>, <em>Hotdog</em>, and <em>Mic</em>) using three styles: <em>Cartoon</em>, <em>Sky Painting</em>, and <em>Fire</em>.
           </p>
           <p>
             The horizontal axis represents the compared methods, while the vertical axis displays different datasets. Our method effectively preserves the original model details, including:
@@ -650,6 +650,41 @@ <h2 class="title is-4">Ablation: Gaussian Refine</h2>
 
 
 
+<section class="section">
+  <div class="container is-max-desktop">
+    <!-- Related Work. -->
+    <div class="columns is-centered">
+      <div class="column is-full-width">
+        <h2 class="title is-3">Related Work</h2>
+
+        <div class="content has-text-justified">
+          <p>
+            Below are some related works that were introduced around the same time as ours.
+          </p>
+          <p>
+            <a href="https://arxiv.org/abs/2403.07807">StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting</a> (Liu et al., 2024) introduces an approach for fast 3D style transfer using Gaussian splatting techniques.
+          </p>
+          <p>
+            <a href="https://instruct-gs2gs.github.io/">Instruct-GS2GS: Editing 3D Gaussian Splats with Instructions</a> (Vachha & Haque, 2024) presents a framework for editing 3D Gaussian splats through natural language instructions.
+          </p>
+          <p>
+            <a href="https://arxiv.org/abs/2407.01414">Styleshot: A Snapshot on Any Style</a> (Gao et al., 2024) explores the ability to apply arbitrary styles to 3D objects using a snapshot-based approach.
+          </p>
+          <p>
+            <a href="https://arxiv.org/abs/2308.06721">Ip-adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models</a> (Ye et al., 2023) introduces an image prompt adapter for enhancing text-to-image models.
+          </p>
+          <p>
+            <a href="https://arxiv.org/abs/2404.02733">Instantstyle: Free Lunch Towards Style-Preserving in Text-to-Image Generation</a> (Wang et al., 2024) proposes a method for maintaining style consistency in text-to-image generation.
+          </p>
+          <p>
+            <a href="https://dl.acm.org/doi/10.1145/3588432.3591486">3D Gaussian Splatting for Real-Time Radiance Field Rendering</a> (Kerbl et al., 2023) investigates real-time rendering techniques for 3D Gaussian splatting in radiance fields.
+          </p>
+        </div>
+      </div>
+    </div>
+    <!--/ Related Work. -->
+  </div>
+</section>