We introduce GRM, a large-scale reconstructor capable of recovering a 3D asset from sparse-view images in around 0.1s. GRM is a feed-forward transformer-based model that efficiently incorporates multi-view information to translate the input pixels into pixel-aligned Gaussians, which are unprojected to create a set of densely distributed 3D Gaussians representing a scene. Together, our transformer architecture and the use of 3D Gaussians unlock a scalable and efficient reconstruction framework. Extensive experimental results demonstrate the superiority of our method over alternatives regarding both reconstruction quality and efficiency. We also showcase the potential of GRM in generative tasks, i.e., text-to-3D and image-to-3D, by integrating it with existing multi-view diffusion models. Our project website is at: https://justimyhxu.github.io/projects/grm/.
Open-domain 3D object synthesis has been lagging behind image synthesis due to limited data and higher computational complexity. To bridge this gap, recent works have investigated multi-view diffusion but often fall short in either 3D consistency, visual quality, or efficiency. This paper proposes MVEdit, which functions as a 3D counterpart of SDEdit, employing ancestral sampling to jointly denoise multi-view images and output high-quality textured meshes. Built on off-the-shelf 2D diffusion models, MVEdit achieves 3D consistency through a training-free 3D Adapter, which lifts the 2D views of the last timestep into a coherent 3D representation, then conditions the 2D views of the next timestep using rendered views, without uncompromising visual quality. With an inference time of only 2-5 minutes, this framework achieves better trade-off between quality and speed than score distillation. MVEdit is highly versatile and extendable, with a wide range of applications including text/image-to-3D generation, 3D-to-3D editing, and high-quality texture synthesis. In particular, evaluations demonstrate state-of-the-art performance in both image-to-3D and text-guided texture generation tasks. Additionally, we introduce a method for fine-tuning 2D latent diffusion models on small 3D datasets with limited resources, enabling fast low-resolution text-to-3D initialization.
This work presents 3DPE, a practical tool that can efficiently edit a face image following given prompts, like reference images or text descriptions, in the 3D-aware manner. To this end, a lightweight module is distilled from a 3D portrait generator and a text-to-image model, which provide prior knowledge of face geometry and open-vocabulary editing capability, respectively. Such a design brings two compelling advantages over existing approaches. First, our system achieves real-time editing with a feedforward network (i.e., ~0.04s per image), over 100x faster than the second competitor. Second, thanks to the powerful priors, our module could focus on the learning of editing-related variations, such that it manages to handle various types of editing simultaneously in the training phase and further supports fast adaptation to user-specified novel types of editing during inference (e.g., with ~5min fine-tuning per case). The code, the model, and the interface will be made publicly available to facilitate future research.
Multimodal large language models (LMMs) excel in world knowledge and problem-solving abilities. Through the use of a world-facing camera and contextual AI, emerging smart accessories aim to provide a seamless interface between humans and LMMs. Yet, these wearable computing systems lack an understanding of the user's attention. We introduce GazeGPT as a new user interaction paradigm for contextual AI. GazeGPT uses eye tracking to help the LMM understand which object in the world-facing camera view a user is paying attention to. Using extensive user evaluations, we show that this gaze-contingent mechanism is a faster and more accurate pointing mechanism than alternatives; that it augments human capabilities by significantly improving their accuracy in a dog-breed classification task; and that it is consistently ranked as more natural than head- or body-driven selection mechanisms for contextual AI. Moreover, we prototype a variety of application scenarios that suggest GazeGPT could be of significant value to users as part of future AI-driven personal assistants.
Despite recent advances in text-to-3D generative methods, there is a notable absence of reliable evaluation metrics. Existing metrics usually focus on a single criterion each, such as how well the asset aligned with the input text. These metrics lack the flexibility to generalize to different evaluation criteria and might not align well with human preferences. Conducting user preference studies is an alternative that offers both adaptability and human-aligned results. User studies, however, can be very expensive to scale. This paper presents an automatic, versatile, and human-aligned evaluation metric for text-to-3D generative models. To this end, we first develop a prompt generator using GPT-4V to generate evaluating prompts, which serve as input to compare text-to-3D models. We further design a method instructing GPT-4V to compare two 3D assets according to user-defined criteria. Finally, we use these pairwise comparison results to assign these models Elo ratings. Experimental results suggest our metric strongly align with human preference across different evaluation criteria.
X-ray free-electron lasers (XFELs) offer unique capabilities for measuring the structure and dynamics of biomolecules, helping us understand the basic building blocks of life. Notably, high-repetition-rate XFELs enable single particle imaging (X-ray SPI) where individual, weakly scattering biomolecules are imaged under near-physiological conditions with the opportunity to access fleeting states that cannot be captured in cryogenic or crystallized conditions. Existing X-ray SPI reconstruction algorithms, which estimate the unknown orientation of a particle in each captured image as well as its shared 3D structure, are inadequate in handling the massive datasets generated by these emerging XFELs. Here, we introduce X-RAI, an online reconstruction framework that estimates the structure of a 3D macromolecule from large X-ray SPI datasets. X-RAI consists of a convolutional encoder, which amortizes pose estimation over large datasets, as well as a physics-based decoder, which employs an implicit neural representation to enable high-quality 3D reconstruction in an end-to-end, self-supervised manner. We demonstrate that X-RAI achieves state-of-the-art performance for small-scale datasets in simulation and challenging experimental settings and demonstrate its unprecedented ability to process large datasets containing millions of diffraction images in an online fashion. These abilities signify a paradigm shift in X-ray SPI towards real-time capture and reconstruction.
Customization techniques for text-to-image models have paved the way for a wide range of previously unattainable applications, enabling the generation of specific concepts across diverse contexts and styles. While existing methods facilitate high-fidelity customization for individual concepts or a limited, pre-defined set of them, they fall short of achieving scalability, where a single model can seamlessly render countless concepts. In this paper, we address a new problem called Modular Customization, with the goal of efficiently merging customized models that were fine-tuned independently for individual concepts. This allows the merged model to jointly synthesize concepts in one image without compromising fidelity or incurring any additional computational costs. To address this problem, we introduce Orthogonal Adaptation, a method designed to encourage the customized models, which do not have access to each other during fine-tuning, to have orthogonal residual weights. This ensures that during inference time, the customized models can be summed with minimal interference. Our proposed method is both simple and versatile, applicable to nearly all optimizable weights in the model architecture. Through an extensive set of quantitative and qualitative evaluations, our method consistently outperforms relevant baselines in terms of efficiency and identity preservation, demonstrating a significant leap toward scalable customization of diffusion models.
Traditional 3D content creation tools empower users to bring their imagination to life by giving them direct control over a scene's geometry, appearance, motion, and camera path. Creating computer-generated videos, however, is a tedious manual process, which can be automated by emerging text-to-video diffusion models. Despite great promise, video diffusion models are difficult to control, hindering a user to apply their own creativity rather than amplifying it. To address this challenge, we present a novel approach that combines the controllability of dynamic 3D meshes with the expressivity and editability of emerging diffusion models. For this purpose, our approach takes an animated, low-fidelity rendered mesh as input and injects the ground truth correspondence information obtained from the dynamic mesh into various stages of a pre-trained text-to-image generation model to output high-quality and temporally consistent frames. We demonstrate our approach on various examples where motion can be obtained by animating rigged assets or changing the camera path.
Recent breakthroughs in text-to-4D generation rely on pre-trained text-to-image and text-to-video models to generate dynamic 3D scenes. However, current text-to-4D methods face a three-way tradeoff between the quality of scene appearance, 3D structure, and motion. For example, text-to-image models and their 3D-aware variants are trained on internet-scale image datasets and can be used to produce scenes with realistic appearance and 3D structure -- but no motion. Text-to-video models are trained on relatively smaller video datasets and can produce scenes with motion, but poorer appearance and 3D structure. While these models have complementary strengths, they also have opposing weaknesses, making it difficult to combine them in a way that alleviates this three-way tradeoff. Here, we introduce hybrid score distillation sampling, an alternating optimization procedure that blends supervision signals from multiple pre-trained diffusion models and incorporates benefits of each for high-fidelity text-to-4D generation. Using hybrid SDS, we demonstrate synthesis of 4D scenes with compelling appearance, 3D structure, and motion.
Efficient generation of 3D digital humans is important in several industries, including virtual reality, social media, and cinematic production. 3D generative adversarial networks (GANs) have demonstrated state-of-the-art (SOTA) quality and diversity for generated assets. Current 3D GAN architectures, however, typically rely on volume representations, which are slow to render, thereby hampering the GAN training and requiring multi-view-inconsistent 2D upsamplers. Here, we introduce Gaussian Shell Maps (GSMs) as a framework that connects SOTA generator network architectures with emerging 3D Gaussian rendering primitives using an articulable multi shell--based scaffold. In this setting, a CNN generates a 3D texture stack with features that are mapped to the shells. The latter represent inflated and deflated versions of a template surface of a digital human in a canonical body pose. Instead of rasterizing the shells directly, we sample 3D Gaussians on the shells whose attributes are encoded in the texture features. These Gaussians are efficiently and differentiably rendered. The ability to articulate the shells is important during GAN training and, at inference time, to deform a body into arbitrary user-defined poses. Our efficient rendering scheme bypasses the need for view-inconsistent upsamplers and achieves high-quality multi-view consistent renderings at a native resolution of $512 \times 512$ pixels. We demonstrate that GSMs successfully generate 3D humans when trained on single-view datasets, including SHHQ and DeepFashion.