DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields
- URL: http://arxiv.org/abs/2311.12063v3
- Date: Mon, 19 Aug 2024 12:34:28 GMT
- Title: DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields
- Authors: Yu Chi, Fangneng Zhan, Sibo Wu, Christian Theobalt, Adam Kortylewski,
- Abstract summary: This paper introduces a novel approach capable of generating infinite, high-quality 3D-consistent 2D annotations alongside 3D point cloud segmentations.
We leverage the strong semantic prior within a 3D generative model to train a semantic decoder.
Once trained, the decoder efficiently generalizes across the latent space, enabling the generation of infinite data.
- Score: 68.94868475824575
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Progress in 3D computer vision tasks demands a huge amount of data, yet annotating multi-view images with 3D-consistent annotations, or point clouds with part segmentation is both time-consuming and challenging. This paper introduces DatasetNeRF, a novel approach capable of generating infinite, high-quality 3D-consistent 2D annotations alongside 3D point cloud segmentations, while utilizing minimal 2D human-labeled annotations. Specifically, we leverage the strong semantic prior within a 3D generative model to train a semantic decoder, requiring only a handful of fine-grained labeled samples. Once trained, the decoder efficiently generalizes across the latent space, enabling the generation of infinite data. The generated data is applicable across various computer vision tasks, including video segmentation and 3D point cloud segmentation. Our approach not only surpasses baseline models in segmentation quality, achieving superior 3D consistency and segmentation precision on individual images, but also demonstrates versatility by being applicable to both articulated and non-articulated generative models. Furthermore, we explore applications stemming from our approach, such as 3D-aware semantic editing and 3D inversion.
Related papers
- 3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features [70.50665869806188]
3DiffTection is a state-of-the-art method for 3D object detection from single images.
We fine-tune a diffusion model to perform novel view synthesis conditioned on a single image.
We further train the model on target data with detection supervision.
arXiv Detail & Related papers (2023-11-07T23:46:41Z) - Leveraging Large-Scale Pretrained Vision Foundation Models for
Label-Efficient 3D Point Cloud Segmentation [67.07112533415116]
We present a novel framework that adapts various foundational models for the 3D point cloud segmentation task.
Our approach involves making initial predictions of 2D semantic masks using different large vision models.
To generate robust 3D semantic pseudo labels, we introduce a semantic label fusion strategy that effectively combines all the results via voting.
arXiv Detail & Related papers (2023-11-03T15:41:15Z) - AutoDecoding Latent 3D Diffusion Models [95.7279510847827]
We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core.
The 3D autodecoder framework embeds properties learned from the target dataset in the latent space.
We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations.
arXiv Detail & Related papers (2023-07-07T17:59:14Z) - Lightweight integration of 3D features to improve 2D image segmentation [1.3799488979862027]
We show that image segmentation can benefit from 3D geometric information without requiring a 3D groundtruth.
Our method can be applied to many 2D segmentation networks, improving significantly their performance.
arXiv Detail & Related papers (2022-12-16T08:22:55Z) - PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained
Image-Language Models [56.324516906160234]
Generalizable 3D part segmentation is important but challenging in vision and robotics.
This paper explores an alternative way for low-shot part segmentation of 3D point clouds by leveraging a pretrained image-language model, GLIP.
We transfer the rich knowledge from 2D to 3D through GLIP-based part detection on point cloud rendering and a novel 2D-to-3D label lifting algorithm.
arXiv Detail & Related papers (2022-12-03T06:59:01Z) - Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based
Perception [122.53774221136193]
State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution.
A natural remedy is to utilize the 3D voxelization and 3D convolution network.
We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
arXiv Detail & Related papers (2021-09-12T06:25:11Z) - Pointwise Attention-Based Atrous Convolutional Neural Networks [15.499267533387039]
A pointwise attention-based atrous convolutional neural network architecture is proposed to efficiently deal with a large number of points.
The proposed model has been evaluated on the two most important 3D point cloud datasets for the 3D semantic segmentation task.
It achieves a reasonable performance compared to state-of-the-art models in terms of accuracy, with a much smaller number of parameters.
arXiv Detail & Related papers (2019-12-27T13:12:58Z)
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.