AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning

Dongseok Shim, Seungjae Lee, H. Jin Kim

ICML 2023 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 1 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use SNeRL encoder instead of DrQ-v2, CURL, CURL-multiview, CNN-AE, NeRF-RLSNeRL with SAC · Window-open, Hammer, Drawer-open, Soccer (Meta-world, 4 seeds)episode returnImproved
Pre-train with plain CNN autoencoder reconstruction (CNN-AE)CNN-AE · Meta-world visual control tasksepisode returnHurt
RGB-only NeRF autoencoder (NeRF-RL) versus multi-view contrastive CURL-multiviewNeRF-RL · Meta-world visual control tasksepisode returnNo clear effect
Remove semantic supervision or distilled feature supervision (ablation)SNeRL · Window-open and Soccerepisode returnHurt
Use only semantic labels in the simple Window environment (ablation)SNeRL · Window-openepisode returnNo clear effect
Add multi-view self-predictive auxiliary loss (ablation)SNeRL · Meta-world tasksepisode returnMixed
Use SNeRL encoder in Dreamer instead of NeRF-RL or CNN-AE weightsDreamer · Meta-world tasks, model-basedepisode returnImproved
Add semantic and feature supervision to NeRF decoderNeRF decoder · Image reconstruction in 3 camera viewsrendering fidelityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy