CAD: Photorealistic 3D Generation via Adversarial Distillation
- URL: http://arxiv.org/abs/2312.06663v1
- Date: Mon, 11 Dec 2023 18:59:58 GMT
- Title: CAD: Photorealistic 3D Generation via Adversarial Distillation
- Authors: Ziyu Wan, Despoina Paschalidou, Ian Huang, Hongyu Liu, Bokui Shen,
Xiaoyu Xiang, Jing Liao, Leonidas Guibas
- Abstract summary: We propose a novel learning paradigm for 3D synthesis that utilizes pre-trained diffusion models.
Our method unlocks the generation of high-fidelity and photorealistic 3D content conditioned on a single image and prompt.
- Score: 28.07049413820128
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The increased demand for 3D data in AR/VR, robotics and gaming applications,
gave rise to powerful generative pipelines capable of synthesizing high-quality
3D objects. Most of these models rely on the Score Distillation Sampling (SDS)
algorithm to optimize a 3D representation such that the rendered image
maintains a high likelihood as evaluated by a pre-trained diffusion model.
However, finding a correct mode in the high-dimensional distribution produced
by the diffusion model is challenging and often leads to issues such as
over-saturation, over-smoothing, and Janus-like artifacts. In this paper, we
propose a novel learning paradigm for 3D synthesis that utilizes pre-trained
diffusion models. Instead of focusing on mode-seeking, our method directly
models the distribution discrepancy between multi-view renderings and diffusion
priors in an adversarial manner, which unlocks the generation of high-fidelity
and photorealistic 3D content, conditioned on a single image and prompt.
Moreover, by harnessing the latent space of GANs and expressive diffusion model
priors, our method facilitates a wide variety of 3D applications including
single-view reconstruction, high diversity generation and continuous 3D
interpolation in the open domain. The experiments demonstrate the superiority
of our pipeline compared to previous works in terms of generation quality and
diversity.
Related papers
- DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation [33.62074896816882]
DiffSplat is a novel 3D generative framework that generates 3D Gaussian splats by taming large-scale text-to-image diffusion models.
It differs from previous 3D generative models by effectively utilizing web-scale 2D priors while maintaining 3D consistency in a unified model.
In conjunction with the regular diffusion loss on these grids, a 3D rendering loss is introduced to facilitate 3D coherence across arbitrary views.
arXiv Detail & Related papers (2025-01-28T07:38:59Z) - 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) - Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion [63.81544586407943]
Single-image 3D portrait generation methods typically employ 2D diffusion models to provide multi-view knowledge, which is then distilled into 3D representations.
We propose a Hybrid Priors Diffsion model, which explicitly and implicitly incorporates multi-view priors as conditions to enhance the status consistency of the generated multi-view portraits.
Experiments demonstrate that our method can produce 3D portraits with accurate geometry and rich details from a single image.
arXiv Detail & Related papers (2024-11-15T17:19:18Z) - 4Diffusion: Multi-view Video Diffusion Model for 4D Generation [55.82208863521353]
Current 4D generation methods have achieved noteworthy efficacy with the aid of advanced diffusion generative models.
We propose a novel 4D generation pipeline, namely 4Diffusion, aimed at generating spatial-temporally consistent 4D content from a monocular video.
arXiv Detail & Related papers (2024-05-31T08:18:39Z) - LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation [73.36690511083894]
This paper introduces a novel framework called LN3Diff to address a unified 3D diffusion pipeline.
Our approach harnesses a 3D-aware architecture and variational autoencoder to encode the input image into a structured, compact, and 3D latent space.
It achieves state-of-the-art performance on ShapeNet for 3D generation and demonstrates superior performance in monocular 3D reconstruction and conditional 3D generation.
arXiv Detail & Related papers (2024-03-18T17:54:34Z) - Sparse3D: Distilling Multiview-Consistent Diffusion for Object
Reconstruction from Sparse Views [47.215089338101066]
We present Sparse3D, a novel 3D reconstruction method tailored for sparse view inputs.
Our approach distills robust priors from a multiview-consistent diffusion model to refine a neural radiance field.
By tapping into 2D priors from powerful image diffusion models, our integrated model consistently delivers high-quality results.
arXiv Detail & Related papers (2023-08-27T11:52:00Z) - IT3D: Improved Text-to-3D Generation with Explicit View Synthesis [71.68595192524843]
This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues.
Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images.
For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data.
arXiv Detail & Related papers (2023-08-22T14:39:17Z) - 3D Neural Field Generation using Triplane Diffusion [37.46688195622667]
We present an efficient diffusion-based model for 3D-aware generation of neural fields.
Our approach pre-processes training data, such as ShapeNet meshes, by converting them to continuous occupancy fields.
We demonstrate state-of-the-art results on 3D generation on several object classes from ShapeNet.
arXiv Detail & Related papers (2022-11-30T01:55:52Z)
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.