GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Space
- URL: http://arxiv.org/abs/2412.16717v1
- Date: Sat, 21 Dec 2024 17:59:17 GMT
- Title: GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Space
- Authors: Souhaib Attaiki, Paul Guerrero, Duygu Ceylan, Niloy J. Mitra, Maks Ovsjanikov,
- Abstract summary: We train a feed-forward text-to-3D diffusion generator for human characters using only single-view 2D data for supervision.
GANFusion starts by generating unconditional triplane features for 3D data using a GAN architecture trained with only single-view 2D data.
- Score: 64.82017974849697
- License:
- Abstract: We train a feed-forward text-to-3D diffusion generator for human characters using only single-view 2D data for supervision. Existing 3D generative models cannot yet match the fidelity of image or video generative models. State-of-the-art 3D generators are either trained with explicit 3D supervision and are thus limited by the volume and diversity of existing 3D data. Meanwhile, generators that can be trained with only 2D data as supervision typically produce coarser results, cannot be text-conditioned, or must revert to test-time optimization. We observe that GAN- and diffusion-based generators have complementary qualities: GANs can be trained efficiently with 2D supervision to produce high-quality 3D objects but are hard to condition on text. In contrast, denoising diffusion models can be conditioned efficiently but tend to be hard to train with only 2D supervision. We introduce GANFusion, which starts by generating unconditional triplane features for 3D data using a GAN architecture trained with only single-view 2D data. We then generate random samples from the GAN, caption them, and train a text-conditioned diffusion model that directly learns to sample from the space of good triplane features that can be decoded into 3D objects.
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) - Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior [57.986512832738704]
We present a new framework Sculpt3D that equips the current pipeline with explicit injection of 3D priors from retrieved reference objects without re-training the 2D diffusion model.
Specifically, we demonstrate that high-quality and diverse 3D geometry can be guaranteed by keypoints supervision through a sparse ray sampling approach.
These two decoupled designs effectively harness 3D information from reference objects to generate 3D objects while preserving the generation quality of the 2D diffusion model.
arXiv Detail & Related papers (2024-03-14T07:39:59Z) - 3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors [85.11117452560882]
We present a two-stage text-to-3D generation system, namely 3DTopia, which generates high-quality general 3D assets within 5 minutes using hybrid diffusion priors.
The first stage samples from a 3D diffusion prior directly learned from 3D data. Specifically, it is powered by a text-conditioned tri-plane latent diffusion model, which quickly generates coarse 3D samples for fast prototyping.
The second stage utilizes 2D diffusion priors to further refine the texture of coarse 3D models from the first stage. The refinement consists of both latent and pixel space optimization for high-quality texture generation
arXiv Detail & Related papers (2024-03-04T17:26:28Z) - GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models [102.22388340738536]
2D and 3D diffusion models can generate decent 3D objects based on prompts.
3D diffusion models have good 3D consistency, but their quality and generalization are limited as trainable 3D data is expensive and hard to obtain.
This paper attempts to bridge the power from the two types of diffusion models via the recent explicit and efficient 3D Gaussian splatting representation.
arXiv Detail & Related papers (2023-10-12T17:22:24Z) - Control3Diff: Learning Controllable 3D Diffusion Models from Single-view
Images [70.17085345196583]
Control3Diff is a 3D diffusion model that combines the strengths of diffusion models and 3D GANs for versatile, controllable 3D-aware image synthesis.
We validate the efficacy of Control3Diff on standard image generation benchmarks, including FFHQ, AFHQ, and ShapeNet.
arXiv Detail & Related papers (2023-04-13T17:52:29Z)
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.