English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Implicit representations such as Neural Radiance Fields (NeRF) have beenshown to be very effective at novel view synthesis. However, these modelstypically require manual and careful human data collection for training. Inthis paper, we present AutoNeRF, a method to collect data required to trainNeRFs using autonomous embodied agents. Our method allows an agent to explorean unseen environment efficiently and use the experience to build an implicitmap representation autonomously. We compare the impact of different explorationstrategies including handcrafted frontier-based exploration, end-to-end andmodular approaches composed of trained high-level planners and classicallow-level path followers. We train these models with different reward functionstailored to this problem and evaluate the quality of the learnedrepresentations on four different downstream tasks: classical viewpointrendering, map reconstruction, planning, and pose refinement. Empirical resultsshow that NeRFs can be trained on actively collected data using just a singleepisode of experience in an unseen environment, and can be used for severaldownstream robotic tasks, and that modular trained exploration modelsoutperform other classical and end-to-end baselines. Finally, we show thatAutoNeRF can reconstruct large-scale scenes, and is thus a useful tool toperform scene-specific adaptation as the produced 3D environment models can beloaded into a simulator to fine-tune a policy of interest.

AutoNeRF: Training Implicit Scene Representations with Autonomous Agents