diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..2df7cd6 --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +.DS_store +.idea diff --git a/README.md b/README.md index e69de29..4a374ff 100644 --- a/README.md +++ b/README.md @@ -0,0 +1,9 @@ +# NEO Project Website + +This branch contains the static project page for: + +**NEO: NeRF It Once, Edit It Many Times for Continuous Object Manipulation** + +The site is based on the Nerfies project page template and has been adapted with selected figures from the ICRA 2026 paper materials. + +Open `index.html` in a browser to preview the page. diff --git a/index.html b/index.html new file mode 100644 index 0000000..fda2519 --- /dev/null +++ b/index.html @@ -0,0 +1,281 @@ + + +
+ + + + ++ NEO is a unified framework for language-guided NeRF editing in robotic manipulation. + Given a prompt and a planned object motion, NEO removes the target object, reconstructs + newly revealed regions with multiview-consistent progressive inpainting, and reinserts + the object through direct NeRF weight editing with teacher-student knowledge distillation. +
++ The resulting representation remains persistent across consecutive edits, enabling a robot + to anticipate scene changes before execution. The paper also introduces the NEO-Dataset, + a benchmark of registered tabletop scenes captured before and after object manipulation + for quantitative evaluation of NeRF scene editing methods. +
+
+ + NEO builds an initial NeRF and language field from camera images, localizes the prompted + object, then updates the scene before motion execution. The system combines object + removal, multi-view inpainting, and object reconfiguration modules so the edited neural + field can be reused for the next manipulation. +
++ Progressive inpainting reconstructs surfaces that were hidden by removed objects while + maintaining cross-view consistency for NeRF training. +
+
+ + Teacher-student distillation composes the edited and original fields so moved objects are + preserved directly in the updated representation. +
+
+ + The NEO-Dataset contains twelve registered tabletop scenes captured before and after + object removal or manipulation. Scenes are recorded with fixed robot arms and camera + trajectories, then aligned with ArUco markers so rendered edited views can be compared + against real post-manipulation images. +
++ The dataset is collected in two different setups utilizing two different manipulators: + the Franka Emika Panda and UR5. These provide background variability across scenes in + addition to scene content variation. +
++ Scenes are scanned in an automated manner with controlled camera motion along a fixed + trajectory to ensure little-to-no variation in scene coverage. The camera poses from this + process provide broad scan coverage for training and evaluating edited scene renderings. +
+
+ @article{zielinski2026neo,
+ author={Zielinski, Mikolaj and Hall, David and Belter, Dominik and Moghadam, Peyman},
+ journal={IEEE Robotics and Automation Letters},
+ title={NEO: NeRF It Once, Edit It Many Times for Continuous Object Manipulation},
+ year={2026},
+ volume={},
+ number={},
+ pages={},
+}
+