Search

Novel-view synthesis is an important problem in computer vision with applications in 3D reconstruction, mixed reality, and robotics. Recent methods like 3D Gaussian Splatting (3DGS) have become the preferred method for this task, providing high-quality novel views in real time. However, the training time of a 3DGS model is slow, often taking 30 minutes for a scene with 200 views. In contrast, our goal is to reduce the optimization time by training for fewer steps while maintaining high rendering quality. Specifically, we combine the guidance from both the position error and the appearance error to achieve a more effective densification. To balance the rate between adding new Gaussians and fitting old Gaussians, we develop a convergence-aware budget control mechanism. Moreover, to make the densification process more reliable, we selectively add new Gaussians from mostly visited regions. With these designs, we reduce the Gaussian optimization steps to one-third of the previous approach while achieving a comparable or even better novel view rendering quality. To further facilitate the rapid fitting of 4K resolution images, we introduce a dilation-based rendering technique. Our method, Turbo-GS, speeds up optimization for typical scenes and scales well to high-resolution (4K) scenarios on standard datasets. Through extensive experiments, we show that our method is significantly faster in optimization than other methods while retaining quality. Project page: https://ivl.cs.brown.edu/research/turbo-gs., Comment: Project page: https://ivl.cs.brown.edu/research/turbo-gs

Understanding bimanual human hand activities is a critical problem in AI and robotics. We cannot build large models of bimanual activities because existing datasets lack the scale, coverage of diverse hand activities, and detailed annotations. We introduce GigaHands, a massive annotated dataset capturing 34 hours of bimanual hand activities from 56 subjects and 417 objects, totaling 14k motion clips derived from 183 million frames paired with 84k text annotations. Our markerless capture setup and data acquisition protocol enable fully automatic 3D hand and object estimation while minimizing the effort required for text annotation. The scale and diversity of GigaHands enable broad applications, including text-driven action synthesis, hand motion captioning, and dynamic radiance field reconstruction. Our website are avaliable at https://ivl.cs.brown.edu/research/gigahands.html .

Despite remarkable progress in image generation models, generating realistic hands remains a persistent challenge due to their complex articulation, varying viewpoints, and frequent occlusions. We present FoundHand, a large-scale domain-specific diffusion model for synthesizing single and dual hand images. To train our model, we introduce FoundHand-10M, a large-scale hand dataset with 2D keypoints and segmentation mask annotations. Our insight is to use 2D hand keypoints as a universal representation that encodes both hand articulation and camera viewpoint. FoundHand learns from image pairs to capture physically plausible hand articulations, natively enables precise control through 2D keypoints, and supports appearance control. Our model exhibits core capabilities that include the ability to repose hands, transfer hand appearance, and even synthesize novel views. This leads to zero-shot capabilities for fixing malformed hands in previously generated images, or synthesizing hand video sequences. We present extensive experiments and evaluations that demonstrate state-of-the-art performance of our method.

In this work, we explore methods to improve galaxy redshift predictions by combining different ground truths. Traditional machine learning models rely on training sets with known spectroscopic redshifts, which are precise but only represent a limited sample of galaxies. To make redshift models more generalizable to the broader galaxy population, we investigate transfer learning and directly combining ground truth redshifts derived from photometry and spectroscopy. We use the COSMOS2020 survey to create a dataset, TransferZ, which includes photometric redshift estimates derived from up to 35 imaging filters using template fitting. This dataset spans a wider range of galaxy types and colors compared to spectroscopic samples, though its redshift estimates are less accurate. We first train a base neural network on TransferZ and then refine it using transfer learning on a dataset of galaxies with more precise spectroscopic redshifts (GalaxiesML). In addition, we train a neural network on a combined dataset of TransferZ and GalaxiesML. Both methods reduce bias by $\sim$ 5x, RMS error by $\sim$ 1.5x, and catastrophic outlier rates by 1.3x on GalaxiesML, compared to a baseline trained only on TransferZ. However, we also find a reduction in performance for RMS and bias when evaluated on TransferZ data. Overall, our results demonstrate these approaches can meet cosmological requirements., Comment: 10 pages, 4 figures, 2 tables, accepted to NeurIPS 2024 Workshop ML4PS

A novel pseudocode search engine is designed to facilitate efficient retrieval and search of academic papers containing pseudocode. By leveraging Elasticsearch, the system enables users to search across various facets of a paper, such as the title, abstract, author information, and LaTeX code snippets, while supporting advanced features like combined facet searches and exact-match queries for more targeted results. A description of the data acquisition process is provided, with arXiv as the primary data source, along with methods for data extraction and text-based indexing, highlighting how different data elements are stored and optimized for search. A weighted BM25-based ranking algorithm is used by the search engine, and factors considered when prioritizing search results for both single and combined facet searches are described. We explain how each facet is weighted in a combined search. Several search engine results pages are displayed. Finally, there is a brief overview of future work and potential evaluation methodology for assessing the effectiveness and performance of the search engine is described.

With the rise of marine exploration, underwater imaging has gained significant attention as a research topic. Underwater video enhancement has become crucial for real-time computer vision tasks in marine exploration. However, most existing methods focus on enhancing individual frames and neglect video temporal dynamics, leading to visually poor enhancements. Furthermore, the lack of ground-truth references limits the use of abundant available underwater video data in many applications. To address these issues, we propose a two-stage framework for enhancing underwater videos. The first stage uses a denoising diffusion probabilistic model to learn a generative prior from unlabeled data, capturing robust and descriptive feature representations. In the second stage, this prior is incorporated into a physics-based image formulation for spatial enhancement, while also enforcing temporal consistency between video frames. Our method enables real-time and computationally-efficient processing of high-resolution underwater videos at lower resolutions, and offers efficient enhancement in the presence of diverse water-types. Extensive experiments on four datasets show that our approach generalizes well and outperforms existing enhancement methods. Our code is available at github.com/suhas-srinath/undive., Comment: Accepted to IEEE/CVF WACV 2025

Recent advancements in radiance field rendering show promising results in 3D scene representation, where Gaussian splatting-based techniques emerge as state-of-the-art due to their quality and efficiency. Gaussian splatting is widely used for various applications, including 3D human representation. However, previous 3D Gaussian splatting methods either use parametric body models as additional information or fail to provide any underlying structure, like human biomechanical features, which are essential for different applications. In this paper, we present a novel approach called HFGaussian that can estimate novel views and human features, such as the 3D skeleton, 3D key points, and dense pose, from sparse input images in real time at 25 FPS. The proposed method leverages generalizable Gaussian splatting technique to represent the human subject and its associated features, enabling efficient and generalizable reconstruction. By incorporating a pose regression network and the feature splatting technique with Gaussian splatting, HFGaussian demonstrates improved capabilities over existing 3D human methods, showcasing the potential of 3D human representations with integrated biomechanics. We thoroughly evaluate our HFGaussian method against the latest state-of-the-art techniques in human Gaussian splatting and pose estimation, demonstrating its real-time, state-of-the-art performance.

To increase driver awareness in a fully autonomous vehicle, we developed several haptic interaction prototypes that signal what the car is planning to do next. The goal was to use haptic cues so that the driver could be situation aware but not distracted from the non-driving tasks they may be engaged in. This paper discusses the three prototypes tested and the guiding metaphor behind each concept. We also highlight the Wizard of Oz protocol adopted to test the haptic interaction prototypes and some key findings from the pilot study., Comment: Copyright held by authors, AutomotiveUI'15 September 1-3, 2015, Nottingham, UK, ACM 978-1-4503-3736-6

Dual-arm manipulation is an area of growing interest in the robotics community. Enabling robots to perform tasks that require the coordinated use of two arms, is essential for complex manipulation tasks such as handling large objects, assembling components, and performing human-like interactions. However, achieving effective dual-arm manipulation is challenging due to the need for precise coordination, dynamic adaptability, and the ability to manage interaction forces between the arms and the objects being manipulated. We propose a novel pipeline that combines the advantages of policy learning based on environment feedback and gradient-based optimization to learn controller gains required for the control outputs. This allows the robotic system to dynamically modulate its impedance in response to task demands, ensuring stability and dexterity in dual-arm operations. We evaluate our pipeline on a trajectory-tracking task involving a variety of large, complex objects with different masses and geometries. The performance is then compared to three other established methods for controlling dual-arm robots, demonstrating superior results.

This paper introduces MotionGlot, a model that can generate motion across multiple embodiments with different action dimensions, such as quadruped robots and human bodies. By leveraging the well-established training procedures commonly used in large language models (LLMs), we introduce an instruction-tuning template specifically designed for motion-related tasks. Our approach demonstrates that the principles underlying LLM training can be successfully adapted to learn a wide range of motion generation tasks across multiple embodiments with different action dimensions. We demonstrate the various abilities of MotionGlot on a set of 6 tasks and report an average improvement of 35.3% across tasks. Additionally, we contribute two new datasets: (1) a dataset of expert-controlled quadruped locomotion with approximately 48,000 trajectories paired with direction-based text annotations, and (2) a dataset of over 23,000 situational text prompts for human motion generation tasks. Finally, we conduct hardware experiments to validate the capabilities of our system in real-world applications.

The widespread adoption of large language models (LLMs) and generative AI (GenAI) tools across diverse applications has amplified the importance of addressing societal biases inherent within these technologies. While the NLP community has extensively studied LLM bias, research investigating how non-expert users perceive and interact with biases from these systems remains limited. As these technologies become increasingly prevalent, understanding this question is crucial to inform model developers in their efforts to mitigate bias. To address this gap, this work presents the findings from a university-level competition, which challenged participants to design prompts for eliciting biased outputs from GenAI tools. We quantitatively and qualitatively analyze the competition submissions and identify a diverse set of biases in GenAI and strategies employed by participants to induce bias in GenAI. Our finding provides unique insights into how non-expert users perceive and interact with biases from GenAI tools.

We propose a zero-shot text-driven 3D shape deformation system that deforms an input 3D mesh of a manufactured object to fit an input text description. To do this, our system optimizes the parameters of a deformation model to maximize an objective function based on the widely used pre-trained vision language model CLIP. We find that CLIP-based objective functions exhibit many spurious local optima; to circumvent them, we parameterize deformations using a novel deformation model called BoxDefGraph which our system automatically computes from an input mesh, the BoxDefGraph is designed to capture the object aligned rectangular/circular geometry features of most manufactured objects. We then use the CMA-ES global optimization algorithm to maximize our objective, which we find to work better than popular gradient-based optimizers. We demonstrate that our approach produces appealing results and outperforms several baselines.

We present a novel method to correct flying pixels within data captured by Time-of-flight (ToF) sensors. Flying pixel (FP) artifacts occur when signals from foreground and background objects reach the same sensor pixel, leading to a confident yet incorrect depth estimation in space - floating between two objects. Commercial RGB-D cameras have a complementary setup consisting of ToF sensors to capture depth in addition to RGB cameras. We propose a novel method to correct FPs by leveraging the aligned RGB and depth image in such RGB-D cameras to estimate the true depth values of FPs. Our method defines a 3D neighborhood around each point, representing a "field of view" that mirrors the acquisition process of ToF cameras. We propose a two-step iterative correction algorithm in which the FPs are first identified. Then, we estimate the true depth value of FPs by solving a least-squares optimization problem. Experimental results show that our proposed algorithm estimates the depth value of FPs as accurately as other algorithms in the literature., Comment: 6 pages, 7 figures, Presented at IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)

Gathering visual information effectively to monitor known environments is a key challenge in robotics. To be as efficient as human surveyors, robotic systems must continuously collect observational data required to complete their survey task. Inspection personnel instinctively know to look at relevant equipment that happens to be ``along the way.'' In this paper, we introduce a novel framework for continuous long-horizon viewpoint planning, for ground robots, applied to tasks involving patrolling, monitoring or visual data gathering in known environments. Our approach to Long Horizon Viewpoint Planning (LHVP), enables the robot to autonomously navigate and collect environmental data optimizing for coverage over the horizon of the patrol. Leveraging a quadruped's mobility and sensory capabilities, our LHVP framework plans patrol paths that account for coupling the viewpoint planner for the arm camera with the mobile base's navigation planner. The viewpath optimization algorithm seeks a balance between comprehensive environmental coverage and dynamically feasible movements, thus ensuring prolonged and effective operation in scenarios including monitoring, security surveillance, and disaster response. We validate our approach through simulations and in the real world and show that our LHVP significantly outperforms naive patrolling methods in terms of area coverage generating information-gathering trajectories for the robot arm. Our results indicate a promising direction for the deployment of mobile robots in long-term, autonomous surveying, and environmental data collection tasks, highlighting the potential of intelligent robotic systems in challenging real-world applications., Comment: 7 pages, 8 figures, 5 tables

Current and future trends in computer hardware, in which the disparity between available flops and memory bandwidth continues to grow, favour algorithm implementations which minimise data movement even at the cost of more flops. In this study we review the requirements for high performance implementations of the kernel independent Fast Multipole Method (kiFMM), a variant of the crucial FMM algorithm for the rapid evaluation of N-body potential problems. Performant implementations of the kiFMM typically rely on Fast Fourier Transforms for the crucial M2L (Multipole-to-Local) operation. However, in recent years for other FMM variants such as the black-box FMM also BLAS based M2L translation operators have become popular that rely on direct matrix compression techniques. In this paper we present algorithmic improvements for BLAS based M2L translation operator and benchmark them against FFT based M2L translation operators. In order to allow a fair comparison we have implemented our own high-performance kiFMM algorithm in Rust that performs competitively against other implementations, and allows us to flexibly switch between BLAS and FFT based translation operators., Comment: 22 pages, 5 figures

The ability to quantify how well an action is carried out, also known as action quality assessment (AQA), has attracted recent interest in the vision community. Unfortunately, prior methods often ignore the score rubric used by human experts and fall short of quantifying the uncertainty of the model prediction. To bridge the gap, we present RICA^2 - a deep probabilistic model that integrates score rubric and accounts for prediction uncertainty for AQA. Central to our method lies in stochastic embeddings of action steps, defined on a graph structure that encodes the score rubric. The embeddings spread probabilistic density in the latent space and allow our method to represent model uncertainty. The graph encodes the scoring criteria, based on which the quality scores can be decoded. We demonstrate that our method establishes new state of the art on public benchmarks, including FineDiving, MTL-AQA, and JIGSAWS, with superior performance in score prediction and uncertainty calibration. Our code is available at https://abrarmajeedi.github.io/rica2_aqa/, Comment: Accepted at European Conference on Computer Vision (ECCV) 2024

We introduce EgoSonics, a method to generate semantically meaningful and synchronized audio tracks conditioned on silent egocentric videos. Generating audio for silent egocentric videos could open new applications in virtual reality, assistive technologies, or for augmenting existing datasets. Existing work has been limited to domains like speech, music, or impact sounds and cannot capture the broad range of audio frequencies found in egocentric videos. EgoSonics addresses these limitations by building on the strengths of latent diffusion models for conditioned audio synthesis. We first encode and process paired audio-video data to make them suitable for generation. The encoded data is then used to train a model that can generate an audio track that captures the semantics of the input video. Our proposed SyncroNet builds on top of ControlNet to provide control signals that enables generation of temporally synchronized audio. Extensive evaluations and a comprehensive user study show that our model outperforms existing work in audio quality, and in our proposed synchronization evaluation method. Furthermore, we demonstrate downstream applications of our model in improving video summarization., Comment: WACV 2025

Next-generation wireless networks aim to deliver data speeds much faster than 5G. This requires base stations with lots of antennas and a large operating bandwidth. These advanced base stations are expected to serve several multiantenna user-equipment (UEs) simultaneously on the same time-frequency resources on both the uplink and the downlink. The UE data rates are affected by the following three main factors: UE rank, which refers to the number of data layers used by each UE, UE frequency allocation, which refers to the assignment of slices of the overall frequency band to use for each UE in an orthogonal frequency-division multiplexing (OFDM) system, and UE power allocation/control, which refers to the allocation of power by the base station for data transmission to each UE on the downlink or the power used by each UE to send data on the uplink. Since multiple UEs are to be simultaneously served, the type of precoder used for downlink transmission and the type of receiver used for uplink reception predominantly influence these three aforementioned factors and the resulting overall UE throughput. This paper addresses the problem of jointly selecting these three parameters specifically when zero-forcing (ZF) precoders are used for downlink transmission and linear minimum mean square error (LMMSE) receivers are employed for uplink reception., Comment: 12 pages in double column format, 9 figures, 1 table. This work has been submitted to the IEEE for possible publication

Improving the reliability and spectral efficiency of wireless systems is a key goal in wireless systems. However, most efforts have been devoted to improving data channel capacity, whereas control-plane capacity bottlenecks are often neglected. In this paper, we propose a means of improving the control-plane capacity and reliability by shrinking the bit size of a key signaling message - the 5G Downlink Control Information (DCI). In particular, a transformer model is studied as a probability distribution estimator for Arithmetic coding to achieve lossless compression. Feature engineering, neural model design, and training technique are comprehensively discussed in this paper. Both temporal and spatial correlations among DCI messages are explored by the transformer model to achieve reasonable lossless compression performance. Numerical results show that the proposed method achieves 21.7% higher compression ratio than Huffman coding in DCI compression for a single-cell scheduling scenario.

The ability to efficiently explore high-dimensional state spaces is essential for the practical success of deep Reinforcement Learning (RL). This paper introduces a new exploration technique called Random Latent Exploration (RLE), that combines the strengths of bonus-based and noise-based (two popular approaches for effective exploration in deep RL) exploration strategies. RLE leverages the idea of perturbing rewards by adding structured random rewards to the original task rewards in certain (random) states of the environment, to encourage the agent to explore the environment during training. RLE is straightforward to implement and performs well in practice. To demonstrate the practical effectiveness of RLE, we evaluate it on the challenging Atari and IsaacGym benchmarks and show that RLE exhibits higher overall scores across all the tasks than other approaches., Comment: Accepted to ICML 2024

We applied machine learning to the unmet medical need of rapid and accurate diagnosis and prognosis of acute infections and sepsis in emergency departments. Our solution consists of a Myrna (TM) Instrument and embedded TriVerity (TM) classifiers. The instrument measures abundances of 29 messenger RNAs in patient's blood, subsequently used as features for machine learning. The classifiers convert the input features to an intuitive test report comprising the separate likelihoods of (1) a bacterial infection (2) a viral infection, and (3) severity (need for Intensive Care Unit-level care). In internal validation, the system achieved AUROC = 0.83 on the three-class disease diagnosis (bacterial, viral, or non-infected) and AUROC = 0.77 on binary prognosis of disease severity. The Myrna, TriVerity system was granted breakthrough device designation by the United States Food and Drug Administration (FDA). This engineering manuscript teaches the standard and novel machine learning methods used to translate an academic research concept to a clinical product aimed at improving patient care, and discusses lessons learned., Comment: 16 pages, 6 figures

This work is motivated by two key trends. On one hand, large language models (LLMs) have shown remarkable versatility in various generative tasks such as writing, drawing, and question answering, significantly reducing the time required for many routine tasks. On the other hand, researchers, whose work is not only time-consuming but also highly expertise-demanding, face increasing challenges as they have to spend more time reading, writing, and reviewing papers. This raises the question: how can LLMs potentially assist researchers in alleviating their heavy workload? This study focuses on the topic of LLMs assist NLP Researchers, particularly examining the effectiveness of LLM in assisting paper (meta-)reviewing and its recognizability. To address this, we constructed the ReviewCritique dataset, which includes two types of information: (i) NLP papers (initial submissions rather than camera-ready) with both human-written and LLM-generated reviews, and (ii) each review comes with "deficiency" labels and corresponding explanations for individual segments, annotated by experts. Using ReviewCritique, this study explores two threads of research questions: (i) "LLMs as Reviewers", how do reviews generated by LLMs compare with those written by humans in terms of quality and distinguishability? (ii) "LLMs as Metareviewers", how effectively can LLMs identify potential issues, such as Deficient or unprofessional review segments, within individual paper reviews? To our knowledge, this is the first work to provide such a comprehensive analysis., Comment: Accepted by EMNLP 2024 main conference

Grasping is an important human activity that has long been studied in robotics, computer vision, and cognitive science. Most existing works study grasping from the perspective of synthesizing hand poses conditioned on 3D or 2D object representations. We propose GenHeld to address the inverse problem of synthesizing held objects conditioned on 3D hand model or 2D image. Given a 3D model of hand, GenHeld 3D can select a plausible held object from a large dataset using compact object representations called object codes.The selected object is then positioned and oriented to form a plausible grasp without changing hand pose. If only a 2D hand image is available, GenHeld 2D can edit this image to add or replace a held object. GenHeld 2D operates by combining the abilities of GenHeld 3D with diffusion-based image editing. Results and experiments show that we outperform baselines and can generate plausible held objects in both 2D and 3D. Our experiments demonstrate that our method achieves high quality and plausibility of held object synthesis in both 3D and 2D.

While Transformers underpin modern large language models (LMs), there is a growing list of alternative architectures with new capabilities, promises, and tradeoffs. This makes choosing the right LM architecture challenging. Recently-proposed $\textit{hybrid architectures}$ seek a best-of-all-worlds approach that reaps the benefits of all architectures. Hybrid design is difficult for two reasons: it requires manual expert-driven search, and new hybrids must be trained from scratch. We propose $\textbf{Manticore}$, a framework that addresses these challenges. Manticore $\textit{automates the design of hybrid architectures}$ while reusing pretrained models to create $\textit{pretrained}$ hybrids. Our approach augments ideas from differentiable Neural Architecture Search (NAS) by incorporating simple projectors that translate features between pretrained blocks from different architectures. We then fine-tune hybrids that combine pretrained models from different architecture families -- such as the GPT series and Mamba -- end-to-end. With Manticore, we enable LM selection without training multiple models, the construction of pretrained hybrids from existing pretrained models, and the ability to $\textit{program}$ pretrained hybrids to have certain capabilities. Manticore hybrids outperform existing manually-designed hybrids, achieve strong performance on Long Range Arena (LRA) tasks, and can improve on pretrained transformers and state space models.