Text-to-3D - Paper Copilot

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation

Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, Gang Zeng

Peking University; Nanyang Technological University; Baidu

Portals

Abstract

Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their practical usage. In this paper, we propose DreamGaussian, a novel 3D content generation framework that achieves both efficiency and quality simultaneously. Our key insight is to design a generative 3D Gaussian Splatting model with companioned mesh extraction and texture refinement in UV space. In contrast to the occupancy pruning used in Neural Radiance Fields, we demonstrate that the progressive densification of 3D Gaussians converges significantly faster for 3D generative tasks. To further enhance the texture quality and facilitate downstream applications, we introduce an efficient algorithm to convert 3D Gaussians into textured meshes and apply a fine-tuning stage to refine the details. Extensive experiments demonstrate the superior efficiency and competitive generation quality of our proposed approach. Notably, DreamGaussian produces high-quality textured meshes in just 2 minutes from a single-view image, achieving approximately 10 times acceleration compared to existing methods.

Related Works

3D REPRESENTATIONS; TEXT-TO-3D GENERATION; IMAGE-TO-3D GENERATION

Comparisons

Zero-1-to-3, One-2-3-45, Shap-E, DreamFusion, Point-E

Magic3D: High-Resolution Text-to-3D Content Creation

Chen-Hsuan Lin, Jun Gao, Luming Tang, Towaki Takikawa, Xiaohui Zeng, Xun Huang, Karsten Kreis, Sanja Fidler, Ming-Yu Liu, Tsung-Yi Lin

NVIDIA

Portals

Abstract

DreamFusion has recently demonstrated the utility of a pre-trained text-to-image diffusion model to optimize Neural Radiance Fields (NeRF), achieving remarkable text-to-3D synthesis results. However, the method has two inherent limitations: (a) extremely slow optimization of NeRF and (b) low-resolution image space supervision on NeRF, leading to low-quality 3D models with a long processing time. In this paper, we address these limitations by utilizing a two-stage optimization framework. First, we obtain a coarse model using a low-resolution diffusion prior and accelerate with a sparse 3D hash grid structure. Using the coarse representation as the initialization, we further optimize a textured 3D mesh model with an efficient differentiable renderer interacting with a high-resolution latent diffusion model. Our method, dubbed Magic3D, can create high quality 3D mesh models in 40 minutes, which is 2× faster than DreamFusion (reportedly taking 1.5 hours on average), while also achieving higher resolution. User studies show 61.7% raters to prefer our approach over DreamFusion. Together with the image-conditioned generation capabilities, we provide users with new ways to control 3D synthesis, opening up new avenues to various creative applications.

Related Works

Text-to-image generation; 3D generative models; Text-to-3D generation

Comparisons

DreamFusion

Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation

Haochen Wang, Xiaodan Du, Jiahao Li, Raymond A. Yeh, Greg Shakhnarovich

TTI-Chicago; Purdue University

Portals

Abstract

A diffusion model learns to predict a vector field of gradients. We propose to apply chain rule on the learned gradients, and back-propagate the score of a diffusion model through the Jacobian of a differentiable renderer, which we instantiate to be a voxel radiance field. This setup aggregates 2D scores at multiple camera viewpoints into a 3D score, and repurposes a pretrained 2D model for 3D data generation. We identify a technical challenge of distribution mismatch that arises in this application, and propose a novel estimation mechanism to resolve it. We run our algorithm on several off-the-shelf diffusion image generative models, including the recently released Stable Diffusion trained on the large-scale LAION dataset.

Related Works

Neural radiance fields (NeRF); 2D-supervised 3D GANs; CLIP-guided, optimization-based 3D generative models; DreamFusion

Comparisons

DreamFusion

D-SDS: Debiasing Scores and Prompts of 2D Diffusionfor View-consistent Text-to-3D Generation

Susung Hong, Donghoon Ahn, Seungryong Kim

Korea University

Portals

Abstract

Existing score-distilling text-to-3D generation techniques, despite their consider able promise, often encounter the view inconsistency problem. One of the most notable issues is the Janus problem, where the most canonical view of an object (e.g., face or head) appears in other views. In this work, we explore existing frameworks for score-distilling text-to-3D generation and identify the main causes of the view inconsistency problem—the embedded bias of 2D diffusion models. Based on these findings, we propose two approaches to debias the score-distillation frameworks for view-consistent text-to-3D generation. Our first approach, called score debiasing, involves cutting off the score estimated by 2D diffusion models and gradually increasing the truncation value throughout the optimization process. Our second approach, called prompt debiasing, identifies conflicting words be tween user prompts and view prompts using a language model, and adjusts the discrepancy between view prompts and the viewing direction of an object. Our experimental results show that our methods improve the realism of the generated 3D objects by significantly reducing artifacts and achieve a good trade-off between faithfulness to the 2D diffusion models and 3D consistency with little overhead.

Related Works

Diffusion models; Score distillation for text-to-3D generation

Comparisons

SJC, DreamFusion

ATT3D: Amortized Text-to-3D Object Synthesis

Jonathan Lorraine, Kevin Xie, Xiaohui Zeng, Chen-Hsuan Lin, Towaki Takikawa, Nicholas Sharp, Tsung-Yi Lin, Ming-Yu Liu, Sanja Fidler, James Lucas

NVIDIA; University of Toronto; Vector Institute

Portals

Abstract

Text-to-3D modeling has seen exciting progress by combining generative text-to-image models with image-to-3D methods like Neural Radiance Fields. DreamFusion recently achieved high-quality results but requires a lengthy, per-prompt optimization to create 3D objects. To address this, we amortize optimization over text prompts by training on many prompts simultaneously with a unified model, instead of separately. With this, we share computation across a prompt set, training in less time than per-prompt optimization. Our framework - Amortized Text-to-3D (ATT3D) - enables sharing of knowledge between prompts to generalize to unseen setups and smooth interpolations between text for novel assets and simple animations.

Related Works

NeRFs for Image-to-3D; Text-to-Image Generation; Text-to-3D (TT3D) Generation; Amortized Optimization; Image-to-3D Models; Text-to-3D Animation

Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

Zibo Zhao, Wen Liu, Xin Chen, Xianfang Zeng, Rui Wang, Pei Cheng, Bin Fu, Tao Chen, Gang Yu, Shenghua Gao

ShanghaiTech University; Tencent PCG; Fudan University

Portals

Abstract

We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts. Directly learning a conditional generative model from images or texts to 3D shapes is prone to producing inconsistent results with the conditions because 3D shapes have an additional dimension whose distribution significantly differs from that of 2D images and texts. To bridge the domain gap among the three modalities and facilitate multi-modal-conditioned 3D shape generation, we explore representing 3D shapes in a shape-image-text-aligned space. Our framework comprises two models: a Shape-Image-Text-Aligned Variational Auto-Encoder (SITA-VAE) and a conditional Aligned Shape Latent Diffusion Model (ASLDM). The former model encodes the 3D shapes into the shape latent space aligned to the image and text and reconstructs the fine-grained 3D neural fields corresponding to given shape embeddings via the transformer-based decoder. The latter model learns a probabilistic mapping function from the image or text space to the latent shape space. Our extensive experiments demonstrate that our proposed approach can generate higher-quality and more diverse 3D shapes that better semantically conform to the visual or textural conditional inputs, validating the effectiveness of the shape-image-text-aligned space for cross-modality 3D shape generation.

Related Works

Neural 3D Shape Representation; Conditional 3D Shape Generation; Contrastive Learning in 3D

Comparisons

Occ, ConvOcc, IFNet, 3DILG, 3DS2V

SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, Wenping Wang

The University of Hong Kong; Tencent Games; University of Pennsylvania; Texas A&M University

Portals

Abstract

In this paper, we present a novel diffusion model called that generates multiview-consistent images from a single-view image. Using pretrained large-scale 2D diffusion models, recent work Zero123 demonstrates the ability to generate plausible novel views from a single-view image of an object. However, maintaining consistency in geometry and colors for the generated images remains a challenge. To address this issue, we propose a synchronized multiview diffusion model that models the joint probability distribution of multiview images, enabling the generation of multiview-consistent images in a single reverse process. SyncDreamer synchronizes the intermediate states of all the generated images at every step of the reverse process through a 3D-aware feature attention mechanism that correlates the corresponding features across different views. Experiments show that SyncDreamer generates images with high consistency across different views, thus making it well-suited for various 3D generation tasks such as novel-view-synthesis, text-to-3D, and image-to-3D.

Related Works

Diffusion models; Using 2D diffusion models for 3D; Other single-view reconstruction methods

Comparisons

Zero-1-to-3, RealFusion, Magic123, One-2-3-45, Point-E, Shap-E

Zero-1-to-3: Zero-shot One Image to 3D Object

Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, Carl Vondrick

Columbia University; Toyota Research Institute

Portals

Abstract

We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image. To perform novel view synthesis in this under-constrained setting, we capitalize on the geometric priors that large-scale diffusion models learn about natural images. Our conditional diffusion model uses a synthetic dataset to learn controls of the relative camera viewpoint, which allow new images to be generated of the same object under a specified camera transformation. Even though it is trained on a synthetic dataset, our model retains a strong zero-shot generalization ability to out-of-distribution datasets as well as in-the-wild images, including impressionist paintings. Our viewpoint-conditioned diffusion approach can further be used for the task of 3D reconstruction from a single image. Qualitative and quantitative experiments show that our method significantly outperforms state-of-the-art single-view 3D reconstruction and novel view synthesis models by leveraging Internet-scale pre-training.

Related Works

3D generative models; Single-view object reconstruction

Comparisons

DietNeRF, Image Variations, SJC

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, Jun Zhu

Tsinghua University; Renmin University of China; ShengShu

Portals

Abstract

Score distillation sampling (SDS) has shown great promise in text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models, but suffers from over-saturation, over-smoothing, and low-diversity problems. In this work, we propose to model the 3D parameter as a random variable instead of a constant as in SDS and present variational score distillation (VSD), a principled particle-based variational framework to explain and address the aforementioned issues in text-to-3D generation. We show that SDS is a special case of VSD and leads to poor samples with both small and large CFG weights. In comparison, VSD works well with various CFG weights as ancestral sampling from diffusion models and simultaneously improves the diversity and sample quality with a common CFG weight (i.e., 7.5). We further present various improvements in the design space for text-to-3D such as distillation time schedule and density initialization, which are orthogonal to the distillation algorithm yet not well explored. Our overall approach, dubbed ProlificDreamer, can generate high rendering resolution (i.e., 512x512) and high-fidelity NeRF with rich structure and complex effects (e.g., smoke and drops). Further, initialized from NeRF, meshes fine-tuned by VSD are meticulously detailed and photo-realistic.

Related Works

Diffusion models; Text-to-3D generation by score distillation sampling (SDS); 3D representations

Comparisons

DreamFusion, Magic3D, Fantasia3D

DreamFusion: Text-to-3D using 2D Diffusion

Ben Poole, Ajay Jain, Jonathan T. Barron, Ben Mildenhall

Google Research; UC Berkeley

Portals

Abstract

Recent breakthroughs in text-to-image synthesis have been driven by diffusion models trained on billions of image-text pairs. Adapting this approach to 3D synthesis would require large-scale datasets of labeled 3D data and efficient architectures for denoising 3D data, neither of which currently exist. In this work, we circumvent these limitations by using a pretrained 2D text-to-image diffusion model to perform text-to-3D synthesis. We introduce a loss based on probability density distillation that enables the use of a 2D diffusion model as a prior for optimization of a parametric image generator. Using this loss in a DeepDream-like procedure, we optimize a randomly-initialized 3D model (a Neural Radiance Field, or NeRF) via gradient descent such that its 2D renderings from random angles achieve a low loss. The resulting 3D model of the given text can be viewed from any angle, relit by arbitrary illumination, or composited into any 3D environment. Our approach requires no 3D training data and no modifications to the image diffusion model, demonstrating the effectiveness of pretrained image diffusion models as priors.

Comparisons

Dream Fields, CLIP-Mesh

Category: Text-to-3D

Portals

Abstract

Related Works

Comparisons

Portals

Abstract

Related Works

Comparisons

Portals

Abstract

Related Works

Comparisons

Portals

Abstract

Related Works

Comparisons

Portals

Abstract

Related Works

Portals

Abstract

Related Works

Comparisons

Portals

Abstract

Related Works

Comparisons

Portals

Abstract

Related Works

Comparisons

Portals

Abstract

Related Works

Comparisons

Portals

Abstract

Comparisons