NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields

• URL: http://arxiv.org/abs/2404.01300v3
• Date: Thu, 18 Jul 2024 17:59:48 GMT
• Title: NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields
• Authors: Muhammad Zubair Irshad, Sergey Zakharov, Vitor Guizilini, Adrien Gaidon, Zsolt Kira, Rares Ambrus,
• Abstract summary: We show how to generate effective 3D representations from posed RGB images. We pretrain this representation at scale on our proposed curated posed-RGB data, totaling over 1.8 million images. Our novel self-supervised pretraining for NeRFs, NeRF-MAE, scales remarkably well and improves performance on various challenging 3D tasks.
• Score: 57.617972778377215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural fields excel in computer vision and robotics due to their ability to understand the 3D visual world such as inferring semantics, geometry, and dynamics. Given the capabilities of neural fields in densely representing a 3D scene from 2D images, we ask the question: Can we scale their self-supervised pretraining, specifically using masked autoencoders, to generate effective 3D representations from posed RGB images. Owing to the astounding success of extending transformers to novel data modalities, we employ standard 3D Vision Transformers to suit the unique formulation of NeRFs. We leverage NeRF's volumetric grid as a dense input to the transformer, contrasting it with other 3D representations such as pointclouds where the information density can be uneven, and the representation is irregular. Due to the difficulty of applying masked autoencoders to an implicit representation, such as NeRF, we opt for extracting an explicit representation that canonicalizes scenes across domains by employing the camera trajectory for sampling. Our goal is made possible by masking random patches from NeRF's radiance and density grid and employing a standard 3D Swin Transformer to reconstruct the masked patches. In doing so, the model can learn the semantic and spatial structure of complete scenes. We pretrain this representation at scale on our proposed curated posed-RGB data, totaling over 1.8 million images. Once pretrained, the encoder is used for effective 3D transfer learning. Our novel self-supervised pretraining for NeRFs, NeRF-MAE, scales remarkably well and improves performance on various challenging 3D tasks. Utilizing unlabeled posed 2D data for pretraining, NeRF-MAE significantly outperforms self-supervised 3D pretraining and NeRF scene understanding baselines on Front3D and ScanNet datasets with an absolute performance improvement of over 20% AP50 and 8% AP25 for 3D object detection.

Related papers

• DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features [65.8738034806085]
  DistillNeRF is a self-supervised learning framework for understanding 3D environments in autonomous driving scenes. Our method is a generalizable feedforward model that predicts a rich neural scene representation from sparse, single-frame multi-view camera inputs.
  arXiv  Detail & Related papers  (2024-06-17T21:15:13Z)
• PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm [114.47216525866435]
  We introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation. For the first time, PonderV2 achieves state-of-the-art performance on 11 indoor and outdoor benchmarks, implying its effectiveness.
  arXiv  Detail & Related papers  (2023-10-12T17:59:57Z)
• Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders [52.91248611338202]
  We propose an alternative to obtain superior 3D representations from 2D pre-trained models via Image-to-Point Masked Autoencoders, named as I2P-MAE. By self-supervised pre-training, we leverage the well learned 2D knowledge to guide 3D masked autoencoding. I2P-MAE attains the state-of-the-art 90.11% accuracy, +3.68% to the second-best, demonstrating superior transferable capacity.
  arXiv  Detail & Related papers  (2022-12-13T17:59:20Z)
• Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations [92.88108411154255]
  We present a method that improves dense 2D image feature extractors when the latter are applied to the analysis of multiple images reconstructible as a 3D scene. We show that our method not only enables semantic understanding in the context of scene-specific neural fields without the use of manual labels, but also consistently improves over the self-supervised 2D baselines.
  arXiv  Detail & Related papers  (2022-09-07T23:24:09Z)
• DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars [92.37436369781692]
  We present DRaCoN, a framework for learning full-body volumetric avatars. It exploits the advantages of both the 2D and 3D neural rendering techniques. Experiments on the challenging ZJU-MoCap and Human3.6M datasets indicate that DRaCoN outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-03-29T17:59:15Z)
• Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation [26.868351498722884]
  We present ObSuRF, a method which turns a single image of a scene into a 3D model represented as a set of Neural Radiance Fields (NeRFs) We make learning more computationally efficient by deriving a novel loss, which allows training NeRFs on RGB-D inputs without explicit ray marching.
  arXiv  Detail & Related papers  (2021-04-02T16:59:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.