NeRF-Aug both creates more photorealistic data and runs 63% faster than existing methods. We demonstrate the effectiveness of our method on 5 tasks with 9 novel objects that are not …

Nov 4, 2024 · To solve this problem, we present NeRF-Aug, a novel method that is capable of teaching a policy to interact with objects that are not present in the dataset. This approach …

Jul 4, 2022 · Extensive results demonstrate that Aug-NeRF effectively boosts NeRF performance in both novel view synthesis (up to 1.5dB PSNR gain) and underlying geometry reconstruction.

Extensive results demonstrate that Aug-NeRF effectively boosts NeRF performance in both novel view synthesis (up to 1.5 dB PSNR gain) and underlying geometry reconstruction. …

Mar 7, 2025 · We introduce NeRF-Aug, a data augmentation framework for gripper-camera robotic systems. Our method leverages the photorealism of NeRFs to replace training objects …

• To address such limitation of NeRF, we propose Aug-NeRF, a triple-level, physically-grounded augmented training pipeline, by leveraging worst-case perturba-tions to implicated regularize …

NeRF-Aug is a novel method that is capable of teaching a policy to interact with objects that are not present in the dataset, and differs from existing approaches by leveraging the speed and …

To solve this problem, we present NeRF-Aug, a novel method that is capable of teaching a policy to interact with objects that are not present in the dataset. This approach differs from existing …

Extensive results demonstrate that Aug-NeRF effectively boosts NeRF performance in both novel view synthesis (up to 1.5 dB PSNR gain) and underlying geometry reconstruction. …

NeRF-Aug leverages NeRFs to generate synthetic training data for robotics tasks like object grasping and navigation. The authors demonstrate that NeRF-Aug can improve the …