arXiv subjects

Kenneth Chen

Publications and source records attributed to Kenneth Chen.

10 recordsLinked to original sources

arXiv2025

GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts

Recent advances in probabilistic generative models have extended capabilities from static image synthesis to text-driven video generation. However, the inherent randomness of their generation process can lead to unpredictable artifacts, such as impossible physics and temporal inconsistency. Progress in addressing these challenges requires systematic benchmarks, yet existing datasets primarily focus on generative images due to the unique spatio-temporal complexities of videos. To bridge this gap, we introduce GeneVA, a large-scale artifact dataset with rich human annotations that focuses on spatio-temporal artifacts in videos generated from natural text prompts. We hope GeneVA can enable and assist critical applications, such as benchmarking model performance and improving generative video quality.

cs.CV↗

arXiv2025

Cost-Aware Routing for Efficient Text-To-Image Generation

Diffusion models are well known for their ability to generate a high-fidelity image for an input prompt through an iterative denoising process. Unfortunately, the high fidelity also comes at a high computational cost due to the inherently sequential generative process. In this work, we seek to optimally balance quality and computational cost, and propose a framework to allow the amount of computation to vary for each prompt, depending on its complexity. Each prompt is automatically routed to the most appropriate text-to-image generation function, which may correspond to a distinct number of denoising steps of a diffusion model, or a disparate, independent text-to-image model. Unlike uniform cost reduction techniques (e.g., distillation, model quantization), our approach achieves the optimal trade-off by learning to reserve expensive choices (e.g., 100+ denoising steps) only for a few complex prompts, and employ more economical choices (e.g., small distilled model) for less sophisticated prompts. We empirically demonstrate on COCO and DiffusionDB that by learning to route to nine already-trained text-to-image models, our approach is able to deliver an average quality that is higher than that achievable by any of these models alone. Code is available at https://github.com/winglicopy/CATImage.

cs.CV↗

arXiv2025

Physically Grounded Monocular Depth via Nanophotonic Wavefront Encoding

Depth foundation models (DFMs) offer strong learned priors for 3D perception from single RGB images but lack physical depth cues, leading to ambiguities in metric scale. We introduce metalenses, an emerging class of ultrathin planar optical elements, as a solution to physically encode missing metric depth cues via nanophotonics. In this paper, we bridge the gap between metalens and DFMs to achieve accurate metric monocular depth sensing. In a single monocular shot, our metalens embeds depth-dependent positional shifts into two polarized optical wavefronts. With an input adaptation strategty, we enable direct fine-tuning that aligns a pretrained DFM with the optical signals. To scale the training data, we further develop a comprehensive simulation pipeline that synthesizes metalens responses from RGB-D datasets, incorporating physical factors to minimize the sim-to-real gap. Experiments demonstrate that this approach outperforms both monocular metric depth estimation and depth-from-defocus baselines, showing an effective pathway for accurate monocular metric depth sensing.

physics.optics↗

arXiv2024

BudgetFusion: Perceptually-Guided Adaptive Diffusion Models

Diffusion models have shown unprecedented success in the task of text-to-image generation. While these models are capable of generating high-quality and realistic images, the complexity of sequential denoising has raised societal concerns regarding high computational demands and energy consumption. In response, various efforts have been made to improve inference efficiency. However, most of the existing efforts have taken a fixed approach with neural network simplification or text prompt optimization. Are the quality improvements from all denoising computations equally perceivable to humans? We observed that images from different text prompts may require different computational efforts given the desired content. The observation motivates us to present BudgetFusion, a novel model that suggests the most perceptually efficient number of diffusion steps before a diffusion model starts to generate an image. This is achieved by predicting multi-level perceptual metrics relative to diffusion steps. With the popular Stable Diffusion as an example, we conduct both numerical analyses and user studies. Our experiments show that BudgetFusion saves up to five seconds per prompt without compromising perceptual similarity. We hope this work can initiate efforts toward answering a core question: how much do humans perceptually gain from images created by a generative model, per watt of energy?

cs.CV↗

arXiv2024

Image-GS: Content-Adaptive Image Representation via 2D Gaussians

Neural image representations have emerged as a promising approach for encoding and rendering visual data. Combined with learning-based workflows, they demonstrate impressive trade-offs between visual fidelity and memory footprint. Existing methods in this domain, however, often rely on fixed data structures that suboptimally allocate memory or compute-intensive implicit models, hindering their practicality for real-time graphics applications. Inspired by recent advancements in radiance field rendering, we introduce Image-GS, a content-adaptive image representation based on 2D Gaussians. Leveraging a custom differentiable renderer, Image-GS reconstructs images by adaptively allocating and progressively optimizing a group of anisotropic, colored 2D Gaussians. It achieves a favorable balance between visual fidelity and memory efficiency across a variety of stylized images frequently seen in graphics workflows, especially for those showing non-uniformly distributed features and in low-bitrate regimes. Moreover, it supports hardware-friendly rapid random access for real-time usage, requiring only 0.3K MACs to decode a pixel. Through error-guided progressive optimization, Image-GS naturally constructs a smooth level-of-detail hierarchy. We demonstrate its versatility with several applications, including texture compression, semantics-aware compression, and joint image compression and restoration.

cs.CV↗

arXiv2023

Exploiting Human Color Discrimination for Memory- and Energy-Efficient Image Encoding in Virtual Reality

Virtual Reality (VR) has the potential of becoming the next ubiquitous computing platform. Continued progress in the burgeoning field of VR depends critically on an efficient computing substrate. In particular, DRAM access energy is known to contribute to a significant portion of system energy. Today's framebuffer compression system alleviates the DRAM traffic by using a numerically lossless compression algorithm. Being numerically lossless, however, is unnecessary to preserve perceptual quality for humans. This paper proposes a perceptually lossless, but numerically lossy, system to compress DRAM traffic. Our idea builds on top of long-established psychophysical studies that show that humans cannot discriminate colors that are close to each other. The discrimination ability becomes even weaker (i.e., more colors are perceptually indistinguishable) in our peripheral vision. Leveraging the color discrimination (in)ability, we propose an algorithm that adjusts pixel colors to minimize the bit encoding cost without introducing visible artifacts. The algorithm is coupled with lightweight architectural support that, in real-time, reduces the DRAM traffic by 66.9\% and outperforms existing framebuffer compression mechanisms by up to 20.4\%. Psychophysical studies on human participants show that our system introduce little to no perceptual fidelity degradation.

cs.GR↗

arXiv2023

Toward Optimized VR/AR Ergonomics: Modeling and Predicting User Neck Muscle Contraction

Ergonomic efficiency is essential to the mass and prolonged adoption of VR/AR experiences. While VR/AR head-mounted displays unlock users' natural wide-range head movements during viewing, their neck muscle comfort is inevitably compromised by the added hardware weight. Unfortunately, little quantitative knowledge for understanding and addressing such an issue is available so far. Leveraging electromyography devices, we measure, model, and predict VR users' neck muscle contraction levels (MCL) while they move their heads to interact with the virtual environment. Specifically, by learning from collected physiological data, we develop a bio-physically inspired computational model to predict neck MCL under diverse head kinematic states. Beyond quantifying the cumulative MCL of completed head movements, our model can also predict potential MCL requirements with target head poses only. A series of objective evaluations and user studies demonstrate its prediction accuracy and generality, as well as its ability in reducing users' neck discomfort by optimizing the layout of visual targets. We hope this research will motivate new ergonomic-centered designs for VR/AR and interactive graphics applications. Source code is released at: https://github.com/NYU-ICL/xr-ergonomics-neck-comfort.

cs.HC↗

arXiv2023

Fully general relativistic simulations of rapidly rotating quark stars: Oscillation modes and universal relations

(Abridged) Numerical simulation of strange quark stars (QSs) is challenging due to the strong density discontinuity at the stellar surface. In this paper, we report successful simulations of rapidly rotating QSs and study their oscillation modes in full general relativity. Building on top of the numerical relativity code \texttt{Einstein Toolkit}, we implement a positivity-preserving Riemann solver and a dust-like atmosphere to handle the density discontinuity at the surface. We demonstrate the robustness of our numerical method by performing stable evolutions of rotating QSs close to the Keplerian limit and extracting their oscillation modes. We focus on the quadrupolar $l=|m|=2$ $f$-mode and study whether they can still satisfy the universal relations recently proposed for rotating neutron stars (NSs). We find that two of the three proposed relations can still be satisfied by rotating QSs. For the remaining broken relation, we propose a new relation to unify the NS and QS data by invoking the dimensionless spin parameter $j$. The onsets of secular instabilities for rotating QSs are also studied by analyzing the $f$-mode frequencies. Same as the result found previously for NSs, we find that QSs become unstable to the Chandrasekhar-Friedman-Schutz instability when the angular velocity of the star $\Omega \approx 3.4 \sigma_0$ for sequences of constant central energy density, where $\sigma_0$ is the mode frequency of the corresponding nonrotating configurations. For the viscosity-driven instability, we find that QSs become unstable when $j\approx 0.881$ for both sequences of constant central energy density and constant baryon mass. Such a high value of $j$ cannot be achieved by realistic rotating NSs before reaching the Keplerian limit.

gr-qc↗

arXiv2023

Freeform Templates: Combining Freeform Curation with Structured Templates

Online whiteboards are becoming a popular way to facilitate collaborative design work, providing a free-form environment to curate ideas. However, as templates are increasingly being used to scaffold contributions from non-experts designers, it is crucial to understand their impact on the creative process. In this paper, we present the results from a study with 114 students in a large introductory design course. Our results confirm prior findings that templates benefit students by providing a starting point, a shared process, and the ability to access their own work from previous steps. While prior research has criticized templates for being too rigid, we discovered that using templates within a free-form environment resulted in visual patterns of free-form curation where concepts were spatially organized, clustered, color-coded, and connected using arrows and lines. We introduce the concept of "Free-form Templates" to illustrate how templates and free-form curation can be synergistic.

cs.HC↗

arXiv2022

Color-Perception-Guided Display Power Reduction for Virtual Reality

Battery life is an increasingly urgent challenge for today's untethered VR and AR devices. However, the power efficiency of head-mounted displays is naturally at odds with growing computational requirements driven by better resolution, refresh rate, and dynamic ranges, all of which reduce the sustained usage time of untethered AR/VR devices. For instance, the Oculus Quest 2, under a fully-charged battery, can sustain only 2 to 3 hours of operation time. Prior display power reduction techniques mostly target smartphone displays. Directly applying smartphone display power reduction techniques, however, degrades the visual perception in AR/VR with noticeable artifacts. For instance, the "power-saving mode" on smartphones uniformly lowers the pixel luminance across the display and, as a result, presents an overall darkened visual perception to users if directly applied to VR content. Our key insight is that VR display power reduction must be cognizant of the gaze-contingent nature of high field-of-view VR displays. To that end, we present a gaze-contingent system that, without degrading luminance, minimizes the display power consumption while preserving high visual fidelity when users actively view immersive video sequences. This is enabled by constructing a gaze-contingent color discrimination model through psychophysical studies, and a display power model (with respect to pixel color) through real-device measurements. Critically, due to the careful design decisions made in constructing the two models, our algorithm is cast as a constrained optimization problem with a closed-form solution, which can be implemented as a real-time, image-space shader. We evaluate our system using a series of psychophysical studies and large-scale analyses on natural images. Experiment results show that our system reduces the display power by as much as 24% with little to no perceptual fidelity degradation.

cs.HC↗