Sreyas Mohan

Adria Marcos-Morales, Matan Leibovich, Sreyas Mohan et al.

Unsupervised denoising is a crucial challenge in real-world imaging applications. Unsupervised deep-learning methods have demonstrated impressive performance on benchmarks based on synthetic noise. However, no metrics are available to evaluate these methods in an unsupervised fashion. This is highly problematic for the many practical applications where ground-truth clean images are not available. In this work, we propose two novel metrics: the unsupervised mean squared error (MSE) and the unsupervised peak signal-to-noise ratio (PSNR), which are computed using only noisy data. We provide a theoretical analysis of these metrics, showing that they are asymptotically consistent estimators of the supervised MSE and PSNR. Controlled numerical experiments with synthetic noise confirm that they provide accurate approximations in practice. We validate our approach on real-world data from two imaging modalities: videos in raw format and transmission electron microscopy. Our results demonstrate that the proposed metrics enable unsupervised evaluation of denoising methods based exclusively on noisy data.

Dmytro Kotovenko, Olga Grebenkova, Nikolaos Sarafianos et al.

While style transfer techniques have been well-developed for 2D image stylization, the extension of these methods to 3D scenes remains relatively unexplored. Existing approaches demonstrate proficiency in transferring colors and textures but often struggle with replicating the geometry of the scenes. In our work, we leverage an explicit Gaussian Splatting (GS) representation and directly match the distributions of Gaussians between style and content scenes using the Earth Mover's Distance (EMD). By employing the entropy-regularized Wasserstein-2 distance, we ensure that the transformation maintains spatial smoothness. Additionally, we decompose the scene stylization problem into smaller chunks to enhance efficiency. This paradigm shift reframes stylization from a pure generative process driven by latent space losses to an explicit matching of distributions between two Gaussian representations. Our method achieves high-resolution 3D stylization by faithfully transferring details from 3D style scenes onto the content scene. Furthermore, WaSt-3D consistently delivers results across diverse content and style scenes without necessitating any training, as it relies solely on optimization-based techniques. See our project page for additional results and source code: $\href{https://compvis.github.io/wast3d/}{https://compvis.github.io/wast3d/}$.

Xinyu Gong, Sreyas Mohan, Naina Dhingra et al.

In this paper, we study a novel problem in egocentric action recognition, which we term as "Multimodal Generalization" (MMG). MMG aims to study how systems can generalize when data from certain modalities is limited or even completely missing. We thoroughly investigate MMG in the context of standard supervised action recognition and the more challenging few-shot setting for learning new action categories. MMG consists of two novel scenarios, designed to support security, and efficiency considerations in real-world applications: (1) missing modality generalization where some modalities that were present during the train time are missing during the inference time, and (2) cross-modal zero-shot generalization, where the modalities present during the inference time and the training time are disjoint. To enable this investigation, we construct a new dataset MMG-Ego4D containing data points with video, audio, and inertial motion sensor (IMU) modalities. Our dataset is derived from Ego4D dataset, but processed and thoroughly re-annotated by human experts to facilitate research in the MMG problem. We evaluate a diverse array of models on MMG-Ego4D and propose new methods with improved generalization ability. In particular, we introduce a new fusion module with modality dropout training, contrastive-based alignment training, and a novel cross-modal prototypical loss for better few-shot performance. We hope this study will serve as a benchmark and guide future research in multimodal generalization problems. The benchmark and code will be available at https://github.com/facebookresearch/MMG_Ego4D.

Alejandra Duarte, Chaitra V. Hegde, Aakash Kaku et al.

The integrity of articular cartilage is a crucial aspect in the early diagnosis of osteoarthritis (OA). Many novel MRI techniques have the potential to assess compositional changes of the cartilage extracellular matrix. Among these techniques, diffusion tensor imaging (DTI) of cartilage provides a simultaneous assessment of the two principal components of the solid matrix: collagen structure and proteoglycan concentration. DTI, as for any other compositional MRI technique, require a human expert to perform segmentation manually. The manual segmentation is error-prone and time-consuming ($\sim$ few hours per subject). We use an ensemble of modified U-Nets to automate this segmentation task. We benchmark our model against a human expert test-retest segmentation and conclude that our model is superior for Patellar and Tibial cartilage using dice score as the comparison metric. In the end, we do a perturbation analysis to understand the sensitivity of our model to the different components of our input. We also provide confidence maps for the predictions so that radiologists can tweak the model predictions as required. The model has been deployed in practice. In conclusion, cartilage segmentation on DW-MRI images with modified U-Nets achieves accuracy that outperforms the human segmenter. Code is available at https://github.com/aakashrkaku/knee-cartilage-segmentation

Peihao Wang, Dejia Xu, Zhiwen Fan et al.

Despite the remarkable performance of score distillation in text-to-3D generation, such techniques notoriously suffer from view inconsistency issues, also known as "Janus" artifact, where the generated objects fake each view with multiple front faces. Although empirically effective methods have approached this problem via score debiasing or prompt engineering, a more rigorous perspective to explain and tackle this problem remains elusive. In this paper, we reveal that the existing score distillation-based text-to-3D generation frameworks degenerate to maximal likelihood seeking on each view independently and thus suffer from the mode collapse problem, manifesting as the Janus artifact in practice. To tame mode collapse, we improve score distillation by re-establishing the entropy term in the corresponding variational objective, which is applied to the distribution of rendered images. Maximizing the entropy encourages diversity among different views in generated 3D assets, thereby mitigating the Janus problem. Based on this new objective, we derive a new update rule for 3D score distillation, dubbed Entropic Score Distillation (ESD). We theoretically reveal that ESD can be simplified and implemented by just adopting the classifier-free guidance trick upon variational score distillation. Although embarrassingly straightforward, our extensive experiments successfully demonstrate that ESD can be an effective treatment for Janus artifacts in score distillation.

Peihao Wang, Zhiwen Fan, Dejia Xu et al.

Score distillation has emerged as one of the most prevalent approaches for text-to-3D asset synthesis. Essentially, score distillation updates 3D parameters by lifting and back-propagating scores averaged over different views. In this paper, we reveal that the gradient estimation in score distillation is inherent to high variance. Through the lens of variance reduction, the effectiveness of SDS and VSD can be interpreted as applications of various control variates to the Monte Carlo estimator of the distilled score. Motivated by this rethinking and based on Stein's identity, we propose a more general solution to reduce variance for score distillation, termed Stein Score Distillation (SSD). SSD incorporates control variates constructed by Stein identity, allowing for arbitrary baseline functions. This enables us to include flexible guidance priors and network architectures to explicitly optimize for variance reduction. In our experiments, the overall pipeline, dubbed SteinDreamer, is implemented by instantiating the control variate with a monocular depth estimator. The results suggest that SSD can effectively reduce the distillation variance and consistently improve visual quality for both object- and scene-level generation. Moreover, we demonstrate that SteinDreamer achieves faster convergence than existing methods due to more stable gradient updates.

Peihao Wang, Yuehao Wang, Dilin Wang et al.

3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time, high-resolution novel view synthesis. By representing scenes as a mixture of Gaussian primitives, 3DGS leverages GPU rasterization pipelines for efficient rendering and reconstruction. To optimize scene coverage and capture fine details, 3DGS employs a densification algorithm to generate additional points. However, this process often leads to redundant point clouds, resulting in excessive memory usage, slower performance, and substantial storage demands - posing significant challenges for deployment on resource-constrained devices. To address this limitation, we propose a theoretical framework that demystifies and improves density control in 3DGS. Our analysis reveals that splitting is crucial for escaping saddle points. Through an optimization-theoretic approach, we establish the necessary conditions for densification, determine the minimal number of offspring Gaussians, identify the optimal parameter update direction, and provide an analytical solution for normalizing off-spring opacity. Building on these insights, we introduce SteepGS, incorporating steepest density control, a principled strategy that minimizes loss while maintaining a compact point cloud. SteepGS achieves a ~50% reduction in Gaussian points without compromising rendering quality, significantly enhancing both efficiency and scalability.

Vasu Agrawal, Akinniyi Akinyemi, Kathryn Alvero et al.

Human communication involves a complex interplay of verbal and nonverbal signals, essential for conveying meaning and achieving interpersonal goals. To develop socially intelligent AI technologies, it is crucial to develop models that can both comprehend and generate dyadic behavioral dynamics. To this end, we introduce the Seamless Interaction Dataset, a large-scale collection of over 4,000 hours of face-to-face interaction footage from over 4,000 participants in diverse contexts. This dataset enables the development of AI technologies that understand dyadic embodied dynamics, unlocking breakthroughs in virtual agents, telepresence experiences, and multimodal content analysis tools. We also develop a suite of models that utilize the dataset to generate dyadic motion gestures and facial expressions aligned with human speech. These models can take as input both the speech and visual behavior of their interlocutors. We present a variant with speech from an LLM model and integrations with 2D and 3D rendering methods, bringing us closer to interactive virtual agents. Additionally, we describe controllable variants of our motion models that can adapt emotional responses and expressivity levels, as well as generating more semantically-relevant gestures. Finally, we discuss methods for assessing the quality of these dyadic motion models, which are demonstrating the potential for more intuitive and responsive human-AI interactions.

Kefan Chen, Sergiu Oprea, Justin Theiss et al.

With the rising interest from the community in digital avatars coupled with the importance of expressions and gestures in communication, modeling natural avatar behavior remains an important challenge across many industries such as teleconferencing, gaming, and AR/VR. Human hands are the primary tool for interacting with the environment and essential for realistic human behavior modeling, yet existing 3D hand and head avatar models often overlook the crucial aspect of hand-body interactions, such as between hand and face. We present InteracttAvatar, the first model to faithfully capture the photorealistic appearance of dynamic hand and non-rigid hand-face interactions. Our novel Dynamic Gaussian Hand model, combining template model and 3D Gaussian Splatting as well as a dynamic refinement module, captures pose-dependent change, e.g. the fine wrinkles and complex shadows that occur during articulation. Importantly, our hand-face interaction module models the subtle geometry and appearance dynamics that underlie common gestures. Through experiments of novel view synthesis, self reenactment and cross-identity reenactment, we demonstrate that InteracttAvatar can reconstruct hand and hand-face interactions from monocular or multiview videos with high-fidelity details and be animated with novel poses.

Sheng Liu, Aakash Kaku, Weicheng Zhu et al.

Reliable probability estimation is of crucial importance in many real-world applications where there is inherent (aleatoric) uncertainty. Probability-estimation models are trained on observed outcomes (e.g. whether it has rained or not, or whether a patient has died or not), because the ground-truth probabilities of the events of interest are typically unknown. The problem is therefore analogous to binary classification, with the difference that the objective is to estimate probabilities rather than predicting the specific outcome. This work investigates probability estimation from high-dimensional data using deep neural networks. There exist several methods to improve the probabilities generated by these models but they mostly focus on model (epistemic) uncertainty. For problems with inherent uncertainty, it is challenging to evaluate performance without access to ground-truth probabilities. To address this, we build a synthetic dataset to study and compare different computable metrics. We evaluate existing methods on the synthetic data as well as on three real-world probability estimation tasks, all of which involve inherent uncertainty: precipitation forecasting from radar images, predicting cancer patient survival from histopathology images, and predicting car crashes from dashcam videos. We also give a theoretical analysis of a model for high-dimensional probability estimation which reproduces several of the phenomena evinced in our experiments. Finally, we propose a new method for probability estimation using neural networks, which modifies the training process to promote output probabilities that are consistent with empirical probabilities computed from the data. The method outperforms existing approaches on most metrics on the simulated as well as real-world data.

Ananya B. Sai, Tanay Dixit, Dev Yashpal Sheth et al.

Natural Language Generation (NLG) evaluation is a multifaceted task requiring assessment of multiple desirable criteria, e.g., fluency, coherency, coverage, relevance, adequacy, overall quality, etc. Across existing datasets for 6 NLG tasks, we observe that the human evaluation scores on these multiple criteria are often not correlated. For example, there is a very low correlation between human scores on fluency and data coverage for the task of structured data to text generation. This suggests that the current recipe of proposing new automatic evaluation metrics for NLG by showing that they correlate well with scores assigned by humans for a single criteria (overall quality) alone is inadequate. Indeed, our extensive study involving 25 automatic evaluation metrics across 6 different tasks and 18 different evaluation criteria shows that there is no single metric which correlates well with human scores on all desirable criteria, for most NLG tasks. Given this situation, we propose CheckLists for better design and evaluation of automatic metrics. We design templates which target a specific criteria (e.g., coverage) and perturb the output such that the quality gets affected only along this specific criteria (e.g., the coverage drops). We show that existing evaluation metrics are not robust against even such simple perturbations and disagree with scores assigned by humans to the perturbed output. The proposed templates thus allow for a fine-grained assessment of automatic evaluation metrics exposing their limitations and will facilitate better design, analysis and evaluation of such metrics.

Sreyas Mohan, Joshua L. Vincent, Ramon Manzorro et al.

Deep convolutional neural networks (CNNs) for image denoising are usually trained on large datasets. These models achieve the current state of the art, but they have difficulties generalizing when applied to data that deviate from the training distribution. Recent work has shown that it is possible to train denoisers on a single noisy image. These models adapt to the features of the test image, but their performance is limited by the small amount of information used to train them. Here we propose "GainTuning", in which CNN models pre-trained on large datasets are adaptively and selectively adjusted for individual test images. To avoid overfitting, GainTuning optimizes a single multiplicative scaling parameter (the "Gain") of each channel in the convolutional layers of the CNN. We show that GainTuning improves state-of-the-art CNNs on standard image-denoising benchmarks, boosting their denoising performance on nearly every image in a held-out test set. These adaptive improvements are even more substantial for test images differing systematically from the training data, either in noise level or image type. We illustrate the potential of adaptive denoising in a scientific application, in which a CNN is trained on synthetic data, and tested on real transmission-electron-microscope images. In contrast to the existing methodology, GainTuning is able to faithfully reconstruct the structure of catalytic nanoparticles from these data at extremely low signal-to-noise ratios.

Dev Yashpal Sheth, Sreyas Mohan, Joshua L. Vincent et al.

Deep convolutional neural networks (CNNs) for video denoising are typically trained with supervision, assuming the availability of clean videos. However, in many applications, such as microscopy, noiseless videos are not available. To address this, we propose an Unsupervised Deep Video Denoiser (UDVD), a CNN architecture designed to be trained exclusively with noisy data. The performance of UDVD is comparable to the supervised state-of-the-art, even when trained only on a single short noisy video. We demonstrate the promise of our approach in real-world imaging applications by denoising raw video, fluorescence-microscopy and electron-microscopy data. In contrast to many current approaches to video denoising, UDVD does not require explicit motion compensation. This is advantageous because motion compensation is computationally expensive, and can be unreliable when the input data are noisy. A gradient-based analysis reveals that UDVD automatically adapts to local motion in the input noisy videos. Thus, the network learns to perform implicit motion compensation, even though it is only trained for denoising.

Sreyas Mohan, Ramon Manzorro, Joshua L. Vincent et al.

Denoising is a fundamental challenge in scientific imaging. Deep convolutional neural networks (CNNs) provide the current state of the art in denoising natural images, where they produce impressive results. However, their potential has barely been explored in the context of scientific imaging. Denoising CNNs are typically trained on real natural images artificially corrupted with simulated noise. In contrast, in scientific applications, noiseless ground-truth images are usually not available. To address this issue, we propose a simulation-based denoising (SBD) framework, in which CNNs are trained on simulated images. We test the framework on data obtained from transmission electron microscopy (TEM), an imaging technique with widespread applications in material science, biology, and medicine. SBD outperforms existing techniques by a wide margin on a simulated benchmark dataset, as well as on real data. Apart from the denoised images, SBD generates likelihood maps to visualize the agreement between the structure of the denoised image and the observed data. Our results reveal shortcomings of state-of-the-art denoising architectures, such as their small field-of-view: substantially increasing the field-of-view of the CNNs allows them to exploit non-local periodic patterns in the data, which is crucial at high noise levels. In addition, we analyze the generalization capability of SBD, demonstrating that the trained networks are robust to variations of imaging parameters and of the underlying signal structure. Finally, we release the first publicly available benchmark dataset of TEM images, containing 18,000 examples.

Aakash Kaku, Sreyas Mohan, Avinash Parnandi et al.

Extraneous variables are variables that are irrelevant for a certain task, but heavily affect the distribution of the available data. In this work, we show that the presence of such variables can degrade the performance of deep-learning models. We study three datasets where there is a strong influence of known extraneous variables: classification of upper-body movements in stroke patients, annotation of surgical activities, and recognition of corrupted images. Models trained with batch normalization learn features that are highly dependent on the extraneous variables. In batch normalization, the statistics used to normalize the features are learned from the training set and fixed at test time, which produces a mismatch in the presence of varying extraneous variables. We demonstrate that estimating the feature statistics adaptively during inference, as in instance normalization, addresses this issue, producing normalized features that are more robust to changes in the extraneous variables. This results in a significant gain in performance for different network architectures and choices of feature statistics.

Sreyas Mohan, Zahra Kadkhodaie, Eero P. Simoncelli et al.

Deep convolutional networks often append additive constant ("bias") terms to their convolution operations, enabling a richer repertoire of functional mappings. Biases are also used to facilitate training, by subtracting mean response over batches of training images (a component of "batch normalization"). Recent state-of-the-art blind denoising methods (e.g., DnCNN) seem to require these terms for their success. Here, however, we show that these networks systematically overfit the noise levels for which they are trained: when deployed at noise levels outside the training range, performance degrades dramatically. In contrast, a bias-free architecture -- obtained by removing the constant terms in every layer of the network, including those used for batch normalization-- generalizes robustly across noise levels, while preserving state-of-the-art performance within the training range. Locally, the bias-free network acts linearly on the noisy image, enabling direct analysis of network behavior via standard linear-algebraic tools. These analyses provide interpretations of network functionality in terms of nonlinear adaptive filtering, and projection onto a union of low-dimensional subspaces, connecting the learning-based method to more traditional denoising methodology.

Gautier Izacard, Sreyas Mohan, Carlos Fernandez-Granda

Frequency estimation is a fundamental problem in signal processing, with applications in radar imaging, underwater acoustics, seismic imaging, and spectroscopy. The goal is to estimate the frequency of each component in a multisinusoidal signal from a finite number of noisy samples. A recent machine-learning approach uses a neural network to output a learned representation with local maxima at the position of the frequency estimates. In this work, we propose a novel neural-network architecture that produces a significantly more accurate representation, and combine it with an additional neural-network module trained to detect the number of frequencies. This yields a fast, fully-automatic method for frequency estimation that achieves state-of-the-art results. In particular, it outperforms existing techniques by a substantial margin at medium-to-high noise levels.

Cengiz Pehlevan, Sreyas Mohan, Dmitri B. Chklovskii

Blind source separation, i.e. extraction of independent sources from a mixture, is an important problem for both artificial and natural signal processing. Here, we address a special case of this problem when sources (but not the mixing matrix) are known to be nonnegative, for example, due to the physical nature of the sources. We search for the solution to this problem that can be implemented using biologically plausible neural networks. Specifically, we consider the online setting where the dataset is streamed to a neural network. The novelty of our approach is that we formulate blind nonnegative source separation as a similarity matching problem and derive neural networks from the similarity matching objective. Importantly, synaptic weights in our networks are updated according to biologically plausible local learning rules.

Prasan A Shedligeri, Sreyas Mohan, Kaushik Mitra

Inserting a patterned occluder at the aperture of a camera lens has been shown to improve the recovery of depth map and all-focus image compared to a fully open aperture. However, design of the aperture pattern plays a very critical role. Previous approaches for designing aperture codes make simple assumptions on image distributions to obtain metrics for evaluating aperture codes. However, real images may not follow those assumptions and hence the designed code may not be optimal for them. To address this drawback we propose a data driven approach for learning the optimal aperture pattern to recover depth map from a single coded image. We propose a two stage architecture where, in the first stage we simulate coded aperture images from a training dataset of all-focus images and depth maps and in the second stage we recover the depth map using a deep neural network. We demonstrate that our learned aperture code performs better than previously designed codes even on code design metrics proposed by previous approaches.