MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

We present MoGe, a powerful model for recovering 3D geometry from monocular open-domain images. Given a single image, our model directly predicts a 3D point map of the captured scene with an affine-invariant representation, which is agnostic to true global scale and shift. This new representation precludes ambiguous supervision in training and facilitate effective geometry learning. Furthermore, we propose a set of novel global and local geometry supervisions that empower the model to learn high-quality geometry. These include a robust, optimal, and efficient point cloud alignment solver for accurate global shape learning, and a multi-scale local geometry loss promoting precise local geometry supervision. We train our model on a large, mixed dataset and demonstrate its strong generalizability and high accuracy. In our comprehensive evaluation on diverse unseen datasets, our model significantly outperforms state-of-the-art methods across all tasks, including monocular estimation of 3D point map, depth map, and camera field of view. Code and models will be released on our project page.

l_inf-approximation of localized distributions

Distributions in spatial model often exhibit localized features. Intuitively, this locality implies a low intrinsic dimensionality, which can be exploited for efficient approximation and computation of complex distributions. However, existing approximation theory mainly considers the joint distributions, which does not guarantee that the marginal errors are small. In this work, we establish a dimension independent error bound for the marginals of approximate distributions. This $\ell_\infty$-approximation error is obtained using Stein's method, and we propose a $\delta$-locality condition that quantifies the degree of localization in a distribution. We also show how $\delta$-locality can be derived from different conditions that characterize the distribution's locality. Our $\ell_\infty$ bound motivates the localization of existing approximation methods to respect the locality. As examples, we show how to use localized likelihood-informed subspace method and localized score matching, which not only avoid dimension dependence in the approximation error, but also significantly reduce the computational cost due to the local and parallel implementation based on the localized structure.

Data-Driven Fire Modeling: Learning First Arrival Times and Model Parameters with Neural Networks

Data-driven techniques are being increasingly applied to complement physics-based models in fire science. However, the lack of sufficiently large datasets continues to hinder the application of certain machine learning techniques. In this paper, we use simulated data to investigate the ability of neural networks to parameterize dynamics in fire science. In particular, we investigate neural networks that map five key parameters in fire spread to the first arrival time, and the corresponding inverse problem. By using simulated data, we are able to characterize the error, the required dataset size, and the convergence properties of these neural networks. For the inverse problem, we quantify the network's sensitivity in estimating each of the key parameters. The findings demonstrate the potential of machine learning in fire science, highlight the challenges associated with limited dataset sizes, and quantify the sensitivity of neural networks to estimate key parameters governing fire spread dynamics.

Evaluation of Missing Data Analytical Techniques in Longitudinal Research: Traditional and Machine Learning Approaches

Missing Not at Random (MNAR) and nonnormal data are challenging to handle. Traditional missing data analytical techniques such as full information maximum likelihood estimation (FIML) may fail with nonnormal data as they are built on normal distribution assumptions. Two-Stage Robust Estimation (TSRE) does manage nonnormal data, but both FIML and TSRE are less explored in longitudinal studies under MNAR conditions with nonnormal distributions. Unlike traditional statistical approaches, machine learning approaches do not require distributional assumptions about the data. More importantly, they have shown promise for MNAR data; however, their application in longitudinal studies, addressing both Missing at Random (MAR) and MNAR scenarios, is also underexplored. This study utilizes Monte Carlo simulations to assess and compare the effectiveness of six analytical techniques for missing data within the growth curve modeling framework. These techniques include traditional approaches like FIML and TSRE, machine learning approaches by single imputation (K-Nearest Neighbors and missForest), and machine learning approaches by multiple imputation (micecart and miceForest). We investigate the influence of sample size, missing data rate, missing data mechanism, and data distribution on the accuracy and efficiency of model estimation. Our findings indicate that FIML is most effective for MNAR data among the tested approaches. TSRE excels in handling MAR data, while missForest is only advantageous in limited conditions with a combination of very skewed distributions, very large sample sizes (e.g., n larger than 1000), and low missing data rates.

ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models

In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, there are additional attributes which are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes is insufficiently sampled by existing training scheme of diffusion generative models, causing degraded test time performance. We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc. Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, ComboStoc enables a new way of test time generation which uses insynchronized time steps for different dimensions and attributes, thus allowing for varying degrees of control over them.

Structured Conformal Inference for Matrix Completion with Applications to Group Recommender Systems

We develop a conformal inference method to construct joint confidence regions for structured groups of missing entries within a sparsely observed matrix. This method is useful to provide reliable uncertainty estimation for group-level collaborative filtering; for example, it can be applied to help suggest a movie for a group of friends to watch together. Unlike standard conformal techniques, which make inferences for one individual at a time, our method achieves stronger group-level guarantees by carefully assembling a structured calibration data set mimicking the patterns expected among the test group of interest. We propose a generalized weighted conformalization framework to deal with the lack of exchangeability arising from such structured calibration, and in this process we introduce several innovations to overcome computational challenges. The practicality and effectiveness of our method are demonstrated through extensive numerical experiments and an analysis of the MovieLens 100K data set.

VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time

We introduce VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) given a single static image and a speech audio clip. Our premiere model, VASA-1, is capable of not only producing lip movements that are exquisitely synchronized with the audio, but also capturing a large spectrum of facial nuances and natural head motions that contribute to the perception of authenticity and liveliness. The core innovations include a holistic facial dynamics and head movement generation model that works in a face latent space, and the development of such an expressive and disentangled face latent space using videos. Through extensive experiments including evaluation on a set of new metrics, we show that our method significantly outperforms previous methods along various dimensions comprehensively. Our method not only delivers high video quality with realistic facial and head dynamics but also supports the online generation of 512x512 videos at up to 40 FPS with negligible starting latency. It paves the way for real-time engagements with lifelike avatars that emulate human conversational behaviors.

Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors

We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typically rely on synthetic multi-view datasets for training specialized models, thus constraining their effectiveness on open-domain images featuring significantly more varied layouts and styles. In contrast, our method directly leverages powerful image diffusion models trained on a broad spectrum of text-image pairs and thus retain their exceptional generalization abilities. This objective is realized through the development of an iterative novel view synthesis and geometry alignment algorithm. The algorithm harnesses diffusion models for dual purposes: they provide appearance prior by predicting novel views of the selected object using estimated depth maps, and they act as a geometry critic by correcting misalignments in 3D shapes across the sampled views. Our method can generate high-quality 3D-aware image edits with large viewpoint transformations and high appearance and shape consistency with the input image, pushing the boundaries of what is possible with single-image 3D-aware editing.

MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion

As a promising 3D generation technique, multiview diffusion (MVD) has received a lot of attention due to its advantages in terms of generalizability, quality, and efficiency. By finetuning pretrained large image diffusion models with 3D data, the MVD methods first generate multiple views of a 3D object based on an image or text prompt and then reconstruct 3D shapes with multiview 3D reconstruction. However, the sparse views and inconsistent details in the generated images make 3D reconstruction challenging. We present MVD$^2$, an efficient 3D reconstruction method for multiview diffusion (MVD) images. MVD$^2$ aggregates image features into a 3D feature volume by projection and convolution and then decodes volumetric features into a 3D mesh. We train MVD$^2$ with 3D shape collections and MVD images prompted by rendered views of 3D shapes. To address the discrepancy between the generated multiview images and ground-truth views of the 3D shapes, we design a simple-yet-efficient view-dependent training scheme. MVD$^2$ improves the 3D generation quality of MVD and is fast and robust to various MVD methods. After training, it can efficiently decode 3D meshes from multiview images within one second. We train MVD$^2$ with Zero-123++ and ObjectVerse-LVIS 3D dataset and demonstrate its superior performance in generating 3D models from multiview images generated by different MVD methods, using both synthetic and real images as prompts.

DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation

This paper presents a novel method for exerting fine-grained lighting control during text-driven diffusion-based image generation. While existing diffusion models already have the ability to generate images under any lighting condition, without additional guidance these models tend to correlate image content and lighting. Moreover, text prompts lack the necessary expressional power to describe detailed lighting setups. To provide the content creator with fine-grained control over the lighting during image generation, we augment the text-prompt with detailed lighting information in the form of radiance hints, i.e., visualizations of the scene geometry with a homogeneous canonical material under the target lighting. However, the scene geometry needed to produce the radiance hints is unknown. Our key observation is that we only need to guide the diffusion process, hence exact radiance hints are not necessary; we only need to point the diffusion model in the right direction. Based on this observation, we introduce a three stage method for controlling the lighting during image generation. In the first stage, we leverage a standard pretrained diffusion model to generate a provisional image under uncontrolled lighting. Next, in the second stage, we resynthesize and refine the foreground object in the generated image by passing the target lighting to a refined diffusion model, named DiLightNet, using radiance hints computed on a coarse shape of the foreground object inferred from the provisional image. To retain the texture details, we multiply the radiance hints with a neural encoding of the provisional synthesized image before passing it to DiLightNet. Finally, in the third stage, we resynthesize the background to be consistent with the lighting on the foreground object. We demonstrate and validate our lighting controlled diffusion model on a variety of text prompts and lighting conditions.