GCA-3D: Towards Generalized and Consistent Domain Adaptation of 3D Generators
- URL: http://arxiv.org/abs/2412.15491v1
- Date: Fri, 20 Dec 2024 02:13:11 GMT
- Title: GCA-3D: Towards Generalized and Consistent Domain Adaptation of 3D Generators
- Authors: Hengjia Li, Yang Liu, Yibo Zhao, Haoran Cheng, Yang Yang, Linxuan Xia, Zekai Luo, Qibo Qiu, Boxi Wu, Tu Zheng, Zheng Yang, Deng Cai,
- Abstract summary: GCA-3D is a generalized and consistent 3D domain adaptation method without the intricate pipeline of data generation.
We introduce multi-modal depth-aware score distillation sampling loss to efficiently adapt 3D generative models in a non-adversarial manner.
Experiments demonstrate that GCA-3D outperforms previous methods in terms of efficiency, generalization, pose accuracy, and identity consistency.
- Score: 24.67369444661137
- License:
- Abstract: Recently, 3D generative domain adaptation has emerged to adapt the pre-trained generator to other domains without collecting massive datasets and camera pose distributions. Typically, they leverage large-scale pre-trained text-to-image diffusion models to synthesize images for the target domain and then fine-tune the 3D model. However, they suffer from the tedious pipeline of data generation, which inevitably introduces pose bias between the source domain and synthetic dataset. Furthermore, they are not generalized to support one-shot image-guided domain adaptation, which is more challenging due to the more severe pose bias and additional identity bias introduced by the single image reference. To address these issues, we propose GCA-3D, a generalized and consistent 3D domain adaptation method without the intricate pipeline of data generation. Different from previous pipeline methods, we introduce multi-modal depth-aware score distillation sampling loss to efficiently adapt 3D generative models in a non-adversarial manner. This multi-modal loss enables GCA-3D in both text prompt and one-shot image prompt adaptation. Besides, it leverages per-instance depth maps from the volume rendering module to mitigate the overfitting problem and retain the diversity of results. To enhance the pose and identity consistency, we further propose a hierarchical spatial consistency loss to align the spatial structure between the generated images in the source and target domain. Experiments demonstrate that GCA-3D outperforms previous methods in terms of efficiency, generalization, pose accuracy, and identity consistency.
Related papers
- Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation [66.75243908044538]
We introduce Zero-1-to-G, a novel approach to direct 3D generation on Gaussian splats using pretrained 2D diffusion models.
To incorporate 3D awareness, we introduce cross-view and cross-attribute attention layers, which capture complex correlations and enforce 3D consistency across generated splats.
This makes Zero-1-to-G the first direct image-to-3D generative model to effectively utilize pretrained 2D diffusion priors, enabling efficient training and improved generalization to unseen objects.
arXiv Detail & Related papers (2025-01-09T18:37:35Z) - DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models [67.50989119438508]
We introduce DSplats, a novel method that directly denoises multiview images using Gaussian-based Reconstructors to produce realistic 3D assets.
Our experiments demonstrate that DSplats not only produces high-quality, spatially consistent outputs, but also sets a new standard in single-image to 3D reconstruction.
arXiv Detail & Related papers (2024-12-11T07:32:17Z) - GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image [94.56927147492738]
We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes from single images.
We show that leveraging diffusion priors can markedly improve generalization, detail preservation, and efficiency in resource usage.
We propose a simple yet effective strategy to segregate the complex data distribution of various scenes into distinct sub-distributions.
arXiv Detail & Related papers (2024-03-18T17:50:41Z) - Source-Free and Image-Only Unsupervised Domain Adaptation for Category
Level Object Pose Estimation [18.011044932979143]
3DUDA is a method capable of adapting to a nuisance-ridden target domain without 3D or depth data.
We represent object categories as simple cuboid meshes, and harness a generative model of neural feature activations.
We show that our method simulates fine-tuning on a global pseudo-labeled dataset under mild assumptions.
arXiv Detail & Related papers (2024-01-19T17:48:05Z) - PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain
Gap Using Pose-Preserved Text-to-Image Diffusion [15.543034329968465]
We propose PODIA-3D, which uses pose-preserved text-to-image diffusion-based domain adaptation for 3D generative models.
We also propose specialized-to-general sampling strategies to improve the details of the generated samples.
Our approach outperforms existing 3D text-guided domain adaptation methods in terms of text-image correspondence, realism, diversity of rendered images, and sense of depth of 3D shapes in the generated samples.
arXiv Detail & Related papers (2023-04-04T15:49:01Z) - NeRF-GAN Distillation for Efficient 3D-Aware Generation with
Convolutions [97.27105725738016]
integration of Neural Radiance Fields (NeRFs) and generative models, such as Generative Adversarial Networks (GANs) has transformed 3D-aware generation from single-view images.
We propose a simple and effective method, based on re-using the well-disentangled latent space of a pre-trained NeRF-GAN in a pose-conditioned convolutional network to directly generate 3D-consistent images corresponding to the underlying 3D representations.
arXiv Detail & Related papers (2023-03-22T18:59:48Z) - DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image
Diffusion for 3D Generative Model [18.362036050304987]
3D generative models have achieved remarkable performance in synthesizing high resolution photorealistic images with view consistency and detailed 3D shapes.
Text-guided domain adaptation methods have shown impressive performance on converting the 2D generative model on one domain into the models on other domains with different styles.
Here we propose DATID-3D, a domain adaptation method tailored for 3D generative models using text-to-image diffusion models.
arXiv Detail & Related papers (2022-11-29T16:54:34Z) - Towards Model Generalization for Monocular 3D Object Detection [57.25828870799331]
We present an effective unified camera-generalized paradigm (CGP) for Mono3D object detection.
We also propose the 2D-3D geometry-consistent object scaling strategy (GCOS) to bridge the gap via an instance-level augment.
Our method called DGMono3D achieves remarkable performance on all evaluated datasets and surpasses the SoTA unsupervised domain adaptation scheme.
arXiv Detail & Related papers (2022-05-23T23:05:07Z) - Unsupervised Geodesic-preserved Generative Adversarial Networks for
Unconstrained 3D Pose Transfer [84.04540436494011]
We present an unsupervised approach to conduct the pose transfer between any arbitrated given 3D meshes.
Specifically, a novel Intrinsic-Extrinsic Preserved Generative Adrative Network (IEP-GAN) is presented for both intrinsic (i.e., shape) and extrinsic (i.e., pose) information preservation.
Our proposed model produces better results and is substantially more efficient compared to recent state-of-the-art methods.
arXiv Detail & Related papers (2021-08-17T09:08:21Z)
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.