SEARCH · Searcharxiv

Results for “gr-qc”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

138 records · Page 3Linked to original sources

arXiv2026

Enabling High-Bandwidth Flash for Generative Recommendation Serving with Write-Aware KV Cache Policy

Generative recommendation (GR) systems increasingly leverage user-level KV cache reuse to avoid recomputing long user histories. However, the growing KV cache capacity and bandwidth requirements introduce new challenges for memory system. High-Bandwidth Flash (HBF) provides a promising solution by offering substantially higher capacity than HBM while approaching HBM-class read bandwidth, enabling larger scale KV cache retention and improved serving throughput. Yet conventional Least-Recently-Used (LRU) KV cache management tightly couples KV cache writes with cache misses, generating excessive write traffic that rapidly exhausts flash endurance. In this work, we evaluate a write-aware KV cache policy based on admission-controlled LRU-K for HBF-based GR serving. By filtering low-reuse users before cache admission, LRU-K decouples KV cache writes from misses and significantly reduces unnecessary writes. We develop an analytical model to characterize GR serving performance, KV cache write traffic, and HBF lifetime, and evaluate performance across diverse memory systems and GR workloads. Our results show that HBF-based systems achieve 3.8 to 4.7 times higher throughput than HBM-only systems. Moreover, LRU-K extends HBF lifetime from about one year under conventional LRU to over six years with a moderate K=10, while maintaining comparable or even slightly improved throughput. These results highlight the importance of write aware KV cache policy for sustainable HBF-based GR serving.

cs.AR↗

arXiv2026

DReSG: Diffusion Residuals for Stylized Gaussian Splatting

Reference-guided stylization of scenes represented by 3D Gaussian Splatting (3DGS) is important for efficient and controllable 3D content creation. Existing VGG-feature-based 3D stylization methods provide stable rendered-view optimization, but often under-represent expressive reference style cues; diffusion models offer stronger image priors, yet direct per-view or score-based diffusion guidance can lead to view drift, local artifacts, and hard-to-control appearance updates. We present DReSG, a 3D-grounded residual-feedback framework for stylized Gaussian splatting. DReSG represents attention-guided diffusion proposals as residual targets relative to the current render, and progressively absorbs these residuals into a shared Gaussian scene through multi-view Gaussian feedback. To make this feedback stable and controllable, DReSG modulates residual strength during target construction and combines coverage-aware view selection with conflict-filtered color updates during multi-view fitting. Extensive experiments demonstrate that DReSG achieves competitive reference-guided stylization while better preserving scene structure and cross-view stability. Our project page is available at https://vpx-ecnu.github.io/DReSG-website/.

cs.CV↗

arXiv2026

TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates

3D Gaussian Splatting has become a de facto scene representation for novel view synthesis, yet robustly learning 3D Gaussian primitives from visual input remains challenging. Standard optimization relies on gradient-based updates, but a common issue is the gradient vanishing phenomenon: a pixel far from a Gaussian primitive often has diminishing gradient magnitudes to influence primitive attributes, resulting in suboptimal scene reconstruction. In this paper, we propose a method to address gradient vanishing with a piecewise truncated gradient formulation that improves the optimization stability and robustness to initializations. We show that our method consistently improves 3D Gaussian Splatting with random and COLMAP initializations while being generalizable across static and dynamic Gaussian Splatting. As a by-product, we also examine the limitations of current benchmarks for dynamic scenes, and introduce a novel dataset for benchmarking dynamic Gaussian Splatting using synthetic 3D scenes. We demonstrate the effectiveness of our method in both static and dynamic settings for the public benchmarks and our proposed dataset.

cs.CV↗

arXiv2026

TetraSDF: Analytic Isosurface Extraction with Multi-resolution Tetrahedral Grid

Extracting an explicit surface that exactly matches the zero-level set of a neural signed distance function (SDF) remains challenging. Sampling-based isosurfacing methods such as Marching Cubes introduce discretization error. In contrast, continuous piecewise affine (CPWA) analytic approaches typically require plain ReLU MLPs, which limits the ability to learn high-frequency SDFs in practice. We present TetraSDF, an analytic isosurface extraction framework for SDFs that retains the expressiveness of grid-based encoders while enabling exact zero-level set extraction, by representing the SDF with a ReLU MLP composed with a multi-resolution tetrahedral positional encoder. Our positional encoder's barycentric interpolation preserves a global CPWA structure, allowing us to track ReLU linear regions within an encoder-induced polyhedral complex. We further introduce a fixed analytic input preconditioner derived from the encoder's metric to reduce directional bias, thereby stabilizing training. Across multiple benchmarks, TetraSDF matches or surpasses existing grid-based encoders in SDF reconstruction accuracy, while faithfully recovering the network's zero-level set as a triangle mesh.

cs.CV↗

arXiv2026

No Pixel Left Behind: Filling Gaps in Anime Colorization

Animation production workflows often involve digital colorization of line art, where small unpainted regions ("gaps") frequently occur and remain an underexplored challenge. We conducted a formative study in Japanese animation (anime) pipelines and found that while the paint bucket tool is widely used for base coloring, tiny enclosed areas are frequently overlooked, resulting in time-consuming manual detection and filling. We introduce GapFill, a tool grounded in professional practices that reduces the effort of gap detection, zooming, and color selection. Our deep-learning method suggests appropriate fill colors by referencing surrounding regions, leveraging the flat-color nature of anime-style images. In a user study with 13 professional colorists, our system improved performance and usability in gap-filling tasks over conventional methods. The study also suggested that prediction accuracy alone is not the primary factor for usability, that appropriate colors can be contextually ambiguous, and that GapFill can complement existing tools depending on users' trust in new AI-powered assistance.

cs.HC↗

arXiv2026

DesigNet: Learning to Draw Vector Graphics as Designers Do

AI-driven content generation has made remarkable progress in recent years. However, neural networks and human designers operate in fundamentally different ways, making collaboration between them challenging. We address this gap for Scalable Vector Graphics (SVG) by equipping neural networks with tools commonly used by designers, such as axis alignment and explicit continuity control at command junctions. We introduce DesigNet, a hierarchical Transformer-VAE that operates directly on SVG sequences with a continuous command parameterization. Our main contributions are two differentiable modules: a continuity self-refinement module that predicts $C^0$, $G^1$, and $C^1$ continuity for each curve point and enforces it by modifying Bézier control points, and an alignment self-refinement module with snapping capabilities for horizontal or vertical lines. DesigNet produces editable outlines and achieves competitive results against state-of-the-art methods, with notably higher accuracy in continuity and alignment. These properties ensure the outputs are easier to refine and integrate into professional design workflows. Source Code: https://github.com/TomasGuija/DesigNet.

cs.CV↗

arXiv2026

The Perceptual Cost of Passthrough: How Video See-Through HMDs Degrade Human Visual Perception of Acuity, Contrast, and Color

Video see-through (VST) technology aims to seamlessly blend the virtual and physical worlds by reconstructing reality through cameras. However, while manufacturers promise high perceptual fidelity, it remains unclear how closely recent commercial VST systems preserve basic visual functions across environmental conditions. In this work, we present an end-to-end perceptual benchmark for three popular VST headsets: Apple Vision Pro, Meta Quest 3, and Meta Quest Pro. Using adapted psychophysical measures, we evaluated participants' visual acuity, contrast sensitivity, and color vision under both normal and low-light conditions, with naked-eye vision as the reference. Our results show measurable gaps between VST and naked-eye performance, especially for visual acuity and contrast sensitivity in low-light environments. By mapping these perceptual gaps across devices, visual functions, and lighting levels, this work provides a practical benchmark for current commercial VST capabilities and highlights where experience design or device optimization may need to compensate for perceptual loss.

cs.HC↗

arXiv2026

STyMo: Fast and Controllable Few-Shot Motion Style Transfer

Supporting a wide variety of motion styles is critical for creating diverse virtual characters, but current methods either require large stylized datasets or pre-trained models that cannot generalize beyond their training distribution. We present STyMo, a few-shot approach that learns motion style from only seconds of paired data and trains in one to two minutes. Our key insight is to decompose style into two components: a static component capturing time-invariant posture, and a temporal component capturing frame-wise dynamics. This decomposition yields an interpretable system where posture intensity, temporal exaggeration, and per-body-region style can be adjusted at runtime. Furthermore, the reduction in required training data and computation time structurally permits an iterative authoring workflow. To ensure robustness on arbitrary inputs, we further introduce a stylizability gate that automatically prevents artifacts on out-of-distribution motions. We demonstrate results across diverse motion styles, from subtle emotional variations to exaggerated character archetypes, and release our processed paired dataset to facilitate future research.

cs.GR↗

arXiv2026

Projective Affine Body Dynamics for Multibody Systems

Multibody systems have widespread applications in diverse fields such as robotics, entertainment, and animation. Their capability to model and simulate intricate interactions among interconnected bodies makes them invaluable in various domains. However, complexity arises with factors like non-smooth contact handling, nonlinearity in flexible joints, and parallelization challenges. We introduce a stable and highly parallel GPU algorithm within affine body dynamics for solving constrained multibody dynamics with nonlinear constraints.Our innovation involves reformulating constrained multibody dynamics into a variational form, treating the system as a set of affine bodies connected with peridynamic bonds. This formulation provides a unified model for affine body dynamics, constraints, and contact within the peridynamics framework.It also facilitates the integration of the semi-implicit successive substitution method to solve nonlinear optimization in a global-local iterative manner. The proposed method obviates the necessity of assembling a global Hessian, rendering it highly suitable for efficient implementation on GPUs.This allows real-time simulation of intricate interactions involving both rigid and flexible bodies, encompassing contact, joint constraints, and friction.

cs.GR↗

arXiv2024

A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions

We introduce a neural-preconditioned iterative solver for Poisson equations with mixed boundary conditions. Typical Poisson discretizations yield large, ill-conditioned linear systems. Iterative solvers can be effective for these problems, but only when equipped with powerful preconditioners. Unfortunately, effective preconditioners like multigrid require costly setup phases that must be re-executed every time domain shapes or boundary conditions change, forming a severe bottleneck for problems with evolving boundaries. In contrast, we present a neural preconditioner trained to efficiently approximate the inverse of the discrete Laplacian in the presence of such changes. Our approach generalizes to domain shapes, boundary conditions, and grid sizes outside the training set. The key to our preconditioner's success is a novel, lightweight neural network architecture featuring spatially varying convolution kernels and supporting fast inference. We demonstrate that our solver outperforms state-of-the-art methods like algebraic multigrid as well as recently proposed neural preconditioners on challenging test cases arising from incompressible fluid simulations.

math.NA↗

arXiv2026

Sub-Pixel Affine Registration of Space Debris Images via the Radon Point Spread Function

Inter-frame affine misalignment caused by platform jitter and attitude adjustments poses a fundamental challenge for multi-frame analysis of point targets in optical surveillance. Conventional registration methods rely on spatial intensity correlations or distinctive image features, both of which are largely absent in low-signal-to-noise-ratio point target imagery. We introduce the Radon Point Spread Function (RPSF) to characterize point targets in the Radon-transformed domain, and derive a closed-form framework that jointly estimates inter-frame translation and rotation from as few as four scalar RPSF samples per frame pair. The method requires no iterative optimization, feature extraction or interpolation, which is suitable for resource-constrained onboard processing. Simulation results confirm sub-pixel translation accuracy and a mean rotation error of 0.2556° at 1° Radon angular resolution. Validation on five real space debris datasets including both ground-based and in-orbit observations yields a mean calibration error below 0.5 pixels, substantially exceeding the precision required for reliable multi-frame processing.

cs.CV↗

arXiv2026

ExMesh: Explicit Mesh Reconstruction with Topology Adaptation

Reconstructing surface meshes from multi-view images has remained a core challenge in recent years. Most existing methods, whether implicit or explicit, depend on intermediate representations and post-processing steps like Marching Cubes or TSDF fusion, often resulting in artifacts and fragmented geometry. Directly optimizing explicit meshes is a promising approach. However, it presents two critical challenges. The first is how to adaptively refine mesh topology to capture detail without introducing degenerate faces. The second is how to maintain consistent UV coordinates for high-fidelity texturing as the mesh structure evolves. To overcome these, we propose ExMesh, a novel framework that directly optimizes explicit meshes by integrating differentiable optimization with discrete topology updates. Specifically, we introduce an adaptive vertex splitting and merging strategy, along with real-time UV maintenance, to enable coarse-to-fine optimization while preserving geometric integrity. To our knowledge, ExMesh is the first framework to seamlessly integrate discrete topology operations into a continuous differentiable optimization pipeline. Extensive experiments demonstrate that ExMesh achieves a balance among accuracy, computational efficiency, and mesh conciseness.

cs.CV↗

arXiv2025

Wavelet-Space Representations for Neural Super-Resolution in Rendering Pipelines

We investigate the use of wavelet-space feature decomposition in neural super-resolution for rendering pipelines. Building on recent neural upscaling frameworks, we introduce a formulation that predicts stationary wavelet coefficients rather than directly regressing RGB values. This frequency-aware decomposition separates low- and high-frequency components, enabling sharper texture recovery and reducing blur in challenging regions. Unlike conventional wavelet transforms, our use of the stationary wavelet transform (SWT) preserves spatial alignment across subbands, allowing the network to integrate G-buffer attributes and temporally warped history frames in a shift-invariant manner. The predicted coefficients are recombined through inverse wavelet synthesis, producing resolution-consistent reconstructions across arbitrary scale factors. We conduct extensive evaluations and ablations, showing that incorporating SWT improves both fidelity and perceptual quality with only modest overhead, while remaining compatible with standard rendering architectures. Taken together, our results suggest that wavelet-domain neural super-resolution provides a principled and efficient path toward higher-quality real-time rendering, with broader implications for neural rendering and graphics applications.

cs.GR↗

arXiv2026

Transparency Rendering in Computer-Aided Design: Methodologies, Trade-offs, and Challenges

This paper surveys the state of transparency rendering in Computer-Aided Design (CAD), with a focus on both practical deployment in industrial systems and the underlying algorithms. We first review current approaches to transparency rendering in CAD environments and outline application scenarios in which accurate and performant transparency is critical for design inspection, communication, and decision-making. We then analyze the trade-offs between approximate and exact transparency techniques, comparing their performance-quality balance on desktop and mobile platforms and discussing criteria for selecting appropriate methods. The survey further identifies the need for robust benchmarks, quality metrics, and evaluation methodologies tailored to CAD-specific visualization tasks. We examine techniques for emphasizing important interior components such as importance-driven transparency, silhouette-based methods, and related approaches to support effective spatial understanding in complex assemblies. Finally, we discuss the unique challenges of rendering transparent constructive solid geometry (CSG) objects, including robustness, correctness, and integration with modern rendering pipelines. Collectively, these contributions characterize current capabilities, systematize open problems, and outline future research directions for transparency rendering in CAD visualization.

cs.GR↗

arXiv2026

ECHO: Dyadic 3D Facial Motion Generation with Asymmetric Deterministic Articulation and Stochastic Reaction

We propose ECHO for dyadic 3D facial motion generation under a strict dual-stream audio-only setting, formulating the problem as an asymmetric task involving speech-constrained articulation and one-to-many listener reactions. To address this asymmetry, ECHO decomposes motion into a deterministic anchor that captures stable speech-correlated structure and a stochastic residual that models the remaining one-to-many interaction dynamics. On top of this backbone, Motion Memory acts as a training-only regularizer during brief late-stage fine-tuning to provide local priors for weakly conditioned listening windows, while semantic-group scaling controls residual injection across expression, jaw, and neck. This design balances speaking-side articulatory fidelity with listening-side realism and diversity in a single generation process. Results from unified, state-wise, and ablation evaluations show that conversational 3D motion benefits from decomposing stable and uncertain components rather than applying stochasticity uniformly. ECHO provides a practical formulation and technical basis for deployable conversational digital humans under strict audio-only conditions.

cs.GR↗

arXiv2026

Inverse Rig Optimization from Line Drawings

Stylized 3D character animation is largely hand-authored, with animators authoring rig parameters one keyframe at a time to find the best pose. Because stylized work reads chiefly through contour lines, drawing contours in the camera view is the most direct and precise way to express artistic intent. This mismatch between the rig controls and the artist's goal forces a laborious trial-and-error workflow, with animators repeatedly manipulating rig controls against the rendered view to match the desired contour. To address this, we propose a method that recovers rig parameters from screen-space contour strokes, enabling effective keyframing from sketches. Given strokes that redraw the current contour, our method optimizes the high-level rig parameters defined in the DCC tool. The key is to use a pre-trained MLP rig surrogate that provides a differentiable map from rig parameters to mesh vertices, replacing the original black-box rig within the optimization process. We match user-drawn lines to mesh contour lines and backpropagate the resulting screen-space error through the surrogate to update the rig parameters. Our results demonstrate that the method works for diverse characters and practical scenarios.

cs.GR↗

arXiv2026

PLSR: Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion

High-resolution 3D asset generation is vital in various 3D applications. Existing state-of-the-art diffusion-based models remain constrained by fixed resolutions, limiting their ability to produce details. In this paper, we tackle the challenge of generating more detailed, higher-resolution 3D objects by introducing a 3D super-resolution (SR) framework built on existing 3D generative foundation models. To this end, we design PLSR, a progressive and localized super-resolution solution to achieve this goal effectively and memory efficiently. Technically, given a coarse geometry from a pretrained 3D generator, we decompose the global SR task into localized sub-tasks via an associative input decomposition scheme, adapt a flow-based 3D generator into a localized super-resolution model through low-cost finetuning, and unify them in an iterative patch-wise denoising pipeline for seamless high-resolution output. Experiments on challenging objects show that our approach is able to generate 3D details with new strong fine-detail fidelity while significantly reducing the computational cost, offering a new and practical solution for high-resolution 3D asset generation.

cs.CV↗

arXiv2026

RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives

We present 'RenderFormer-V2', a unified learned transformer-based neural rendering model, complementary to modern physics-based rendering systems, that can handle diverse light-transport effects such as caustics, volumetric scattering, environment lighting, textured and displaced surfaces and out-of-distribution materials without per-scene training or specialized code. RenderFormer-V2 models global light transport as a sequence-to-sequence transformation. Following its predecessor, RenderFormer-V2 also employs a two stage process: a view-independent stage that resolves intra-scene primitive to primitive transport, and a view-dependent stage that transforms the internal neural scene representation into image pixels. Different from RenderFormer, our model employs a novel combined windowed-attention and rendering-informed attention sink in the view-independent stage to improve scalability while maintaining render accuracy. To further improve versatility, RenderFormerV2 supports heterogeneous scene primitives, including environment maps and participating media, and it employs a material encoding independent of the underlying surface reflectance model that encodes material appearance via a novel neural embedding. We demonstrate the versatility of RenderFormer-V2 on a variety of scenes and perform an extensive ablation of the improved attention mechanism.

cs.CV↗