added docs

saandeepa93 · Jul 7, 2024 · fcaeac0 · fcaeac0
1 parent 45231a6
commit fcaeac0
Show file tree

Hide file tree

Showing 25 changed files with 13 additions and 81 deletions.
diff --git a/docs/index.html b/docs/index.html
@@ -138,27 +138,19 @@ <h2 class="title is-3">Abstract</h2>
             deforming scene using photos/videos captured casually from mobile phones.
           </p>
           <p>
-            Our approach augments neural radiance fields
-            (NeRF) by optimizing an
-            additional continuous volumetric deformation field that warps each observed point into a
-            canonical 5D NeRF.
-            We observe that these NeRF-like deformation fields are prone to local minima, and
-            propose a coarse-to-fine optimization method for coordinate-based models that allows for
-            more robust optimization.
-            By adapting principles from geometry processing and physical simulation to NeRF-like
-            models, we propose an elastic regularization of the deformation field that further
-            improves robustness.
-          </p>
-          <p>
-            We show that <span class="dnerf">Nerfies</span> can turn casually captured selfie
-            photos/videos into deformable NeRF
-            models that allow for photorealistic renderings of the subject from arbitrary
-            viewpoints, which we dub <i>"nerfies"</i>. We evaluate our method by collecting data
-            using a
-            rig with two mobile phones that take time-synchronized photos, yielding train/validation
-            images of the same pose at different viewpoints. We show that our method faithfully
-            reconstructs non-rigidly deforming scenes and reproduces unseen views with high
-            fidelity.
+            Identifying Out-of-distribution (OOD) data is becoming increasingly critical as the real-world applications 
+            of deep learning methods expand. Post-hoc methods modify softmax scores fine-tuned on outlier data or leverage
+            intermediate feature layers to identify distinctive patterns between In-Distribution (ID) and OOD samples. 
+            Other methods focus on employing diverse OOD samples to learn discrepancies between ID and OOD. 
+            These techniques, however, are typically dependent on the quality of the outlier samples assumed. 
+            Density-based methods explicitly model class-conditioned distributions but this requires long training 
+            time or retraining the classifier. To tackle these issues, we introduce \textit{FlowCon}, a new density-based 
+            OOD detection technique. Our main innovation lies in efficiently combining the properties of normalizing 
+            flow with supervised contrastive learning, ensuring robust representation learning with tractable density estimation. 
+            Empirical evaluation shows the enhanced performance of our method across common vision datasets such as 
+            CIFAR-10 and CIFAR-100 pretrained on ResNet18 and WideResNet classifiers. We also perform quantitative 
+            analysis using likelihood plots and qualitative visualization using UMAP embeddings and demonstrate the 
+            robustness of the proposed method under various OOD contexts. Code will be open-sourced post decision.
           </p>
         </div>
       </div>
@@ -186,66 +178,6 @@ <h2 class="title is-3">Abstract</h2>
     <!--/ Matting. -->
 
     <!-- Animation. -->
-    <div class="columns is-centered">
-      <div class="column is-full-width">
-        <h2 class="title is-3">Animation</h2>
-
-        <!-- Interpolating. -->
-        <h3 class="title is-4">Interpolating states</h3>
-        <div class="content has-text-justified">
-          <p>
-            We can also animate the scene by interpolating the deformation latent codes of two input
-            frames. Use the slider here to linearly interpolate between the left frame and the right
-            frame.
-          </p>
-        </div>
-        <div class="columns is-vcentered interpolation-panel">
-          <div class="column is-3 has-text-centered">
-            <img src="./static/images/interpolate_start.jpg"
-                 class="interpolation-image"
-                 alt="Interpolate start reference image."/>
-            <p>Start Frame</p>
-          </div>
-          <div class="column interpolation-video-column">
-            <div id="interpolation-image-wrapper">
-              Loading...
-            </div>
-            <input class="slider is-fullwidth is-large is-info"
-                   id="interpolation-slider"
-                   step="1" min="0" max="100" value="0" type="range">
-          </div>
-          <div class="column is-3 has-text-centered">
-            <img src="./static/images/interpolate_end.jpg"
-                 class="interpolation-image"
-                 alt="Interpolation end reference image."/>
-            <p class="is-bold">End Frame</p>
-          </div>
-        </div>
-        <br/>
-        <!--/ Interpolating. -->
-
-        <!-- Re-rendering. -->
-        <h3 class="title is-4">Re-rendering the input video</h3>
-        <div class="content has-text-justified">
-          <p>
-            Using <span class="dnerf">Nerfies</span>, you can re-render a video from a novel
-            viewpoint such as a stabilized camera by playing back the training deformations.
-          </p>
-        </div>
-        <div class="content has-text-centered">
-          <video id="replay-video"
-                 controls
-                 muted
-                 preload
-                 playsinline
-                 width="75%">
-            <source src="./static/videos/replay.mp4"
-                    type="video/mp4">
-          </video>
-        </div>
-        <!--/ Re-rendering. -->
-
-      </div>
     </div>
     <!--/ Animation. -->
 

diff --git a/docs/static/images/figures/far_near.png b/docs/static/images/figures/far_near.png
diff --git a/docs/static/images/figures/ll_cifar10.png b/docs/static/images/figures/ll_cifar10.png
diff --git a/docs/static/images/figures/ll_cifar100.png b/docs/static/images/figures/ll_cifar100.png
diff --git a/docs/static/images/figures/main_res.png b/docs/static/images/figures/main_res.png
diff --git a/docs/static/images/figures/near.png b/docs/static/images/figures/near.png
diff --git a/docs/static/images/figures/umap.png b/docs/static/images/figures/umap.png
diff --git a/docs/static/videos/._Icon b/docs/static/videos/._Icon
diff --git a/docs/static/videos/blueshirt.mp4 b/docs/static/videos/blueshirt.mp4
diff --git a/docs/static/videos/book.mp4 b/docs/static/videos/book.mp4
diff --git a/docs/static/videos/chair-tp.mp4 b/docs/static/videos/chair-tp.mp4
diff --git a/docs/static/videos/coffee.mp4 b/docs/static/videos/coffee.mp4
diff --git a/docs/static/videos/dollyzoom-depth.mp4 b/docs/static/videos/dollyzoom-depth.mp4
diff --git a/docs/static/videos/dollyzoom-stacked.mp4 b/docs/static/videos/dollyzoom-stacked.mp4
diff --git a/docs/static/videos/dollyzoom.mp4 b/docs/static/videos/dollyzoom.mp4
diff --git a/docs/static/videos/fullbody.mp4 b/docs/static/videos/fullbody.mp4
diff --git a/docs/static/videos/mask-nobg.mp4 b/docs/static/videos/mask-nobg.mp4
diff --git a/docs/static/videos/mask.mp4 b/docs/static/videos/mask.mp4
diff --git a/docs/static/videos/matting.mp4 b/docs/static/videos/matting.mp4
diff --git a/docs/static/videos/replay.mp4 b/docs/static/videos/replay.mp4
diff --git a/docs/static/videos/shiba.mp4 b/docs/static/videos/shiba.mp4
diff --git a/docs/static/videos/steve.mp4 b/docs/static/videos/steve.mp4
diff --git a/docs/static/videos/teaser.mp4 b/docs/static/videos/teaser.mp4
diff --git a/docs/static/videos/toby.mp4 b/docs/static/videos/toby.mp4
diff --git a/docs/static/videos/toby2.mp4 b/docs/static/videos/toby2.mp4