From e9e78318c8283b0770bb88c54446ec625608c288 Mon Sep 17 00:00:00 2001 From: Hannah_Haensen Date: Mon, 8 Jan 2024 16:10:32 +0100 Subject: [PATCH] Update index.html --- docs/index.html | 174 +++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 151 insertions(+), 23 deletions(-) diff --git a/docs/index.html b/docs/index.html index d6c6bd2..229a770 100644 --- a/docs/index.html +++ b/docs/index.html @@ -16,36 +16,140 @@ + +
+
+


DynaMoN: Motion-Aware Fast And Robust Camera -Localization for Dynamic NeRF

+ Localization for Dynamic NeRF
-
-
-

-
- -
- - -

arixv

+
+
+
+
COLMAP + HexPlane
+
-
- - -

Code (coming soon)

+
+
DynaMoN
+ +
+
+
Compare
+
+
+ +
+
+ +
+
+ +
+
Mert Asim Karaoglu (1,3), Hannah Schieber (2,4), Nicolas Schischka (1), Melih Gorgulu(1), @@ -85,6 +189,22 @@
+
+
+ +
+ + +

arixv

+
+
+ + +

Code (coming soon)

+
+

@@ -92,16 +212,22 @@

Abstract

-
+
-
+

- Dynamic reconstruction with neural radiance fields (NeRF) requires accurate camera poses. These are often hard to retrieve with existing structure-from-motion (SfM) pipelines as both camera and scene content can change. We -propose DynaMoN that leverages simultaneous localization and mapping (SLAM) jointly with motion masking to handle dynamic scene content. Our robust SLAM-based tracking module -significantly accelerates the training process of the dynamic NeRF while improving the quality of synthesized views at the same time. Extensive experimental validation on TUM RGB-D, BONN RGB-D Dynamic and the DyCheck’s iPhone dataset, three real-world datasets, shows the advantages of DynaMoN both for camera pose estimation and novel view synthesis. + Dynamic reconstruction with neural radiance fields (NeRF) requires accurate camera poses. These are + often hard to retrieve with existing structure-from-motion (SfM) pipelines as both camera and scene + content can change. We + propose DynaMoN that leverages simultaneous localization and mapping (SLAM) jointly with motion masking + to handle dynamic scene content. Our robust SLAM-based tracking module + significantly accelerates the training process of the dynamic NeRF while improving the quality of + synthesized views at the same time. Extensive experimental validation on TUM RGB-D, BONN RGB-D Dynamic + and the DyCheck’s iPhone dataset, three real-world datasets, shows the advantages of DynaMoN both for + camera pose estimation and novel view synthesis.

@@ -149,8 +275,10 @@

Citation

-
- +