arXiv subjects

Takahiro Harada

Publications and source records attributed to Takahiro Harada.

At least 19 recordsLinked to original sources

arXiv2026

Thread-Efficient Decoding for Neural Texture Compression

Neural texture compression (NTC) achieves higher compression ratios than BCn formats but suffers from GPU thread divergence, which significantly reduces runtime performance. In this work, we propose a shared decoder MLP architecture -- trained with a gradual decoder freezing schedule -- combined with texture clustering to reduce thread divergence by 25%-52% while preserving rendering quality. We evaluate our method on over 500 textures and multiple real rendering scenes, demonstrating up to 8.48x speedup on the Radeon RX 9070 XT GPU compared to non-shared baselines. Our key contributions include: (1) a unified shared decoder architecture that reduces divergence by grouping textures; (2) a training recipe with gradual decoder freezing that improves stability and reconstruction accuracy; (3) a semantic clustering strategy using CLIP embeddings that groups similar textures for effective decoder sharing; and (4) comprehensive performance and ablation studies validating our approach.

cs.CV↗

arXiv2026

PEPS: Positional Encoding Projected Sampling -- Extended

Implicit neural representations (INRs) are increasingly being used as tools to map coordinates to signals, encompassing applications from neural fields to texture compression, shape representations, and beyond. Most INR methods are based on using high-dimensional projections of the initial coordinates through encoders such as grid or positional encoding. Nevertheless, positional encoding is often insufficient and grids, as we show in this paper, require high resolution for being able to learn. In this paper, we demonstrate that positional encoding can be used not only as a high-dimensional embedding but also decomposed as a series of meaningful points. We propose the Positional Encoding Projected Sampling, where we treat the projection of the original coordinate at each frequency as a point of interest. We describe the motion of each point with respect to the frequencies and show that it follows a unique pattern. Finally, we use the unique motion of each point as a basis decomposition for doing learned positional encoding using grids. We prove, using three competitive applications; image representation, texture compression, and signed distance function; that the proposed approach outperforms the current state of the art methods, and often requires 25\% less parameters for equivalent reconstruction error or rendering.

cs.CV↗

arXiv2026

Voxel Deformation-Aware Neural Intersection Function

We extend the Locally-Subdivided Neural Intersection Function (LSNIF) to support parameterized deformable and animated geometry. Our approach introduces a rest-space and deformed-space formulation inspired by meshless rendering, allowing ray samples to be mapped back to a canonical space where a single neural network represents geometry consistently across poses without retraining. To maintain accuracy under deformation-aware training, we incorporate scale-invariant distance regression, uncertainty-weighted multi-task learning, and a hybrid positional-grid encoding. The resulting method preserves the compactness and efficiency of LSNIF while enabling robust neural intersection prediction for dynamic geometry.

cs.GR↗

arXiv2026

Ray Tracing using HIP

In this technical report, we introduce the basics of ray tracing and explain how to accelerate the computation of the rendering algorithm in HIP. We also show how to use a HIP ray tracing framework - HIPRT, leveraging hardware ray tracing features of AMD GPUs. We conclude this technical report with a list of references for further reading.

cs.GR↗

arXiv2025

Geometric Integration for Neural Control Variates

Control variates are a variance-reduction technique for Monte Carlo integration. The principle involves approximating the integrand by a function that can be analytically integrated, and integrating using the Monte Carlo method only the residual difference between the integrand and the approximation, to obtain an unbiased estimate. Neural networks are universal approximators that could potentially be used as a control variate. However, the challenge lies in the analytic integration, which is not possible in general. In this manuscript, we study one of the simplest neural network models, the multilayered perceptron (MLP) with continuous piecewise linear activation functions, and its possible analytic integration. We propose an integration method based on integration domain subdivision, employing techniques from computational geometry to solve this problem in 2D. We demonstrate that an MLP can be used as a control variate in combination with our integration method, showing applications in the light transport simulation.

cs.GR↗

arXiv2025

LSNIF: Locally-Subdivided Neural Intersection Function

Neural representations have shown the potential to accelerate ray casting in a conventional ray-tracing-based rendering pipeline. We introduce a novel approach called Locally-Subdivided Neural Intersection Function (LSNIF) that replaces bottom-level BVHs used as traditional geometric representations with a neural network. Our method introduces a sparse hash grid encoding scheme incorporating geometry voxelization, a scene-agnostic training data collection, and a tailored loss function. It enables the network to output not only visibility but also hit-point information and material indices. LSNIF can be trained offline for a single object, allowing us to use LSNIF as a replacement for its corresponding BVH. With these designs, the network can handle hit-point queries from any arbitrary viewpoint, supporting all types of rays in the rendering pipeline. We demonstrate that LSNIF can render a variety of scenes, including real-world scenes designed for other path tracers, while achieving a memory footprint reduction of up to 106.2x compared to a compressed BVH.

cs.GR↗

arXiv2024

Neural Texture Block Compression

Block compression is a widely used technique to compress textures in real-time graphics applications, offering a reduction in storage size. However, their storage efficiency is constrained by the fixed compression ratio, which substantially increases storage size when hundreds of high-quality textures are required. In this paper, we propose a novel block texture compression method with neural networks, Neural Texture Block Compression (NTBC). NTBC learns the mapping from uncompressed textures to block-compressed textures, which allows for significantly reduced storage costs without any change in the shaders.Our experiments show that NTBC can achieve reasonable-quality results with up to about 70% less storage footprint, preserving real-time performance with a modest computational overhead at the texture loading phase in the graphics pipeline.

eess.IV↗

arXiv2023

GI-1.0: A Fast and Scalable Two-level Radiance Caching Scheme for Real-time Global Illumination

Real-time global illumination is key to enabling more dynamic and physically realistic worlds in performance-critical applications such as games or any other applications with real-time constraints.Hardware-accelerated ray tracing in modern GPUs allows arbitrary intersection queries against the geometry, making it possible to evaluate indirect lighting entirely at runtime. However, only a small number of rays can be traced at each pixel to maintain high framerates at ever-increasing image resolutions. Existing solutions, such as probe-based techniques, approximate the irradiance signal at the cost of a few rays per frame but suffer from a lack of details and slow response times to changes in lighting. On the other hand, reservoir-based resampling techniques capture much more details but typically suffer from poorer performance and increased amounts of noise, making them impractical for the current generation of hardware and gaming consoles. To find a balance that achieves high lighting fidelity while maintaining a low runtime cost, we propose a solution that dynamically estimates global illumination without needing any content preprocessing, thus enabling easy integration into existing real-time rendering pipelines.

cs.GR↗

arXiv2023

Local Positional Encoding for Multi-Layer Perceptrons

A multi-layer perceptron (MLP) is a type of neural networks which has a long history of research and has been studied actively recently in computer vision and graphics fields. One of the well-known problems of an MLP is the capability of expressing high-frequency signals from low-dimensional inputs. There are several studies for input encodings to improve the reconstruction quality of an MLP by applying pre-processing against the input data. This paper proposes a novel input encoding method, local positional encoding, which is an extension of positional and grid encodings. Our proposed method combines these two encoding techniques so that a small MLP learns high-frequency signals by using positional encoding with fewer frequencies under the lower resolution of the grid to consider the local position and scale in each grid cell. We demonstrate the effectiveness of our proposed method by applying it to common 2D and 3D regression tasks where it shows higher-quality results compared to positional and grid encodings, and comparable results to hierarchical variants of grid encoding such as multi-resolution grid encoding with equivalent memory footprint.

cs.GR↗

arXiv2023

Neural Intersection Function

The ray casting operation in the Monte Carlo ray tracing algorithm usually adopts a bounding volume hierarchy (BVH) to accelerate the process of finding intersections to evaluate visibility. However, its characteristics are irregular, with divergence in memory access and branch execution, so it cannot achieve maximum efficiency on GPUs. This paper proposes a novel Neural Intersection Function based on a multilayer perceptron whose core operation contains only dense matrix multiplication with predictable memory access. Our method is the first solution integrating the neural network-based approach and BVH-based ray tracing pipeline into one unified rendering framework. We can evaluate the visibility and occlusion of secondary rays without traversing the most irregular and time-consuming part of the BVH and thus accelerate ray casting. The experiments show the proposed method can reduce the secondary ray casting time for direct illumination by up to 35% compared to a BVH-based implementation and still preserve the image quality.

cs.GR↗

arXiv2023

Fluid mode spectroscopy for measuring kinematic viscosity of fluids in open cylindrical containers

On a daily basis we stir tee or coffee with a spoon and leave it to rest. We know empirically the larger the stickiness, viscosity, of the fluid, more rapidly its velocity slows down. It is surprising, therefore, that the variation, the decay rate of the velocity, has not been utilized for measuring (kinematic) viscosity of fluids. This study shows that a spectroscopy decomposing a velocity field into fluid modes (Stokes eigenmodes) allows us to measure accurately the kinematic viscosity. The method, Fluid Mode Spectroscopy (FMS), is based on the fact that each Stokes eigenmode has its inherent decay rate of eigenvalue and that the dimensionless rate of the slowest decaying mode (SDM) is constant, dependent only on the normalized shape of a fluid container, obtained analytically for some shapes including cylindrical containers. The FMS supplements major conventional measuring methods with each other, particularly useful for measuring relatively low kinematic viscosity and for a direct measurement of viscosity at zero shear rate without extrapolation. The method is validated by the experiments of water poured into an open cylindrical container, as well as by the corresponding numerical simulations.

physics.flu-dyn↗

arXiv2023

Subspace Culling for Ray-Box Intersection

Ray tracing is an essential operation for realistic image synthesis. The acceleration of ray tracing has been studied for a long period of time because algorithms such as light transport simulations require a large amount of ray tracing. One of the major approaches to accelerate the intersections is to use bounding volumes for early pruning for primitives in the volume. The axis-aligned bounding box is a popular bounding volume for ray tracing because of its simplicity and efficiency. However, the conservative bounding volume may produce extra empty space in addition to its content. Especially, primitives that are thin and diagonal to the axis give false-positive hits on the box volume due to the extra space. Although more complex bounding volumes such as oriented bounding boxes may reduce more false-positive hits, they are computationally expensive. In this paper, we propose a novel culling approach to reduce false-positive hits for the bounding box by embedding a binary voxel data structure to the volume. As a ray is represented as a conservative voxel volume as well in our approach, the ray--voxel intersection is cheaply done by bitwise AND operations. Our method is applicable to hierarchical data structures such as bounding volume hierarchy (BVH). It reduces false-positive hits due to the ray--box test and reduces the number of intersections during the traversal of BVH in ray tracing. We evaluate the reduction of intersections with several scenes and show the possibility of performance improvement despite the culling overhead. We also introduce a compression approach with a lookup table for our voxel data. We show that our compressed voxel data achieves significant false-positive reductions with a small amount of memory.

cs.GR↗

arXiv2023

Combining GPU Tracing Methods within a Single Ray Query

A recent trend in real-time rendering is the utilization of the new hardware ray tracing capabilities. Often, usage of a distance field representation is proposed as an alternative when hardware ray tracing is deemed too costly, and the two are seen as competing approaches. In this work, we show that both approaches can work together effectively for a single ray query on modern hardware. We choose to use hardware ray tracing where precision is most important, while avoiding its heavy cost by using a distance field when possible. While a simple approach, in our experiments the resulting tracing algorithm overcomes the associated overhead and allows a user-defined middle ground between the performance of distance field traversal and the improved visual quality of hardware ray tracing.

cs.GR↗

arXiv2023

Progressive Material Caching

The evaluation of material networks is a relatively resource-intensive process in the rendering pipeline. Modern production scenes can contain hundreds or thousands of complex materials with massive networks, so there is a great demand for an efficient way of handling material networks. In this paper, we introduce an efficient method for progressively caching the material nodes without an overhead on the rendering performance. We evaluate the material networks as usual in the rendering process. Then, the output value of part of the network is stored in a cache and can be used in the evaluation of the next materials. Using our method, we can render the scene with performance equal to or better than that of the method without caching, with a slight difference in the images rendered with caching and without it.

cs.GR↗

arXiv2011

Go-and-Back method: Effective estimation of the hidden motion of proteins from single-molecule time series

We present an effective method for estimating the motion of proteins from the motion of attached probe particles in single-molecule experiments. The framework naturally incorporates Langevin dynamics to compute the most probable trajectory of the protein. By using a perturbation expansion technique, we achieve computational costs more than four orders of magnitude smaller than the conventional gradient descent method without loss of simplicity in the computation algorithm. We present illustrative applications of the method using simple models of single-molecule experiments and confirm that the proposed method yields reasonable and stable estimates of the hidden motion in a highly efficient manner.

physics.chem-ph↗

arXiv2010

Optimal waveform for the entrainment of a weakly forced oscillator

A theory for obtaining waveform for the effective entrainment of a weakly forced oscillator is presented. Phase model analysis is combined with calculus of variation to derive a waveform with which entrainment of an oscillator is achieved with minimum power forcing signal. Optimal waveforms are calculated from the phase response curve and a solution to a balancing condition. The theory is tested in chemical entrainment experiments in which oscillations close to and further away from a Hopf bifurcation exhibited sinusoidal and higher harmonic nontrivial optimal waveforms, respectively.

nlin.CD↗

arXiv2009

Macroscopic Expression Connecting the Rate of Energy Dissipation and Violation of the Fluctuation-Response Relation

A direct connection between the magnitude of the violation of the fluctuation-response relation (FRR) and the rate of energy dissipation is presented in terms of field variables of nonequilibrium systems. Here, we consider the density field of a colloidal suspension either in a relaxation process or in a nonequilibrium steady state driven by an external field. Using a path-integral representation of the temporal evolution of the density field, we find an equality that relates the magnitude of the violation of the FRR for scalar and vector potentials of the velocity field to the rate of energy dissipation for the entire system. Our result demonstrates that the violation of the FRR for field variables captures the entropic component of the dissipated free energy.

cond-mat.stat-mech↗

arXiv2008

Contraction-induced cluster formation in cardiac cell culture

Evolution of the spatial arrangement of cells in a primary culture of cardiac tissue derived from newborn rats was studied experimentally over extended period. It was found that cells attract each other spontaneously to form a clustered structure over the timescale of several days. These clusters exhibit spontaneous rhythmic contraction and have been confirmed to consist of cardiac muscle cells. Addition of a contraction inhibitor (2,3-butanedione-2-monoxime) to the culture medium resulted in the inhibition of both the spontaneous contractions exhibited by the cells as well as the formation of clusters. Furthermore, the formation of clusters is suppressed when high concentrations of collagen are used for coating the substratum to which the cells adhere. From these experimental observations, it was deduced that the cells are mechanically stressed by the tension associated with repeated contractions and that this results in the cells becoming compact and attracting each other, finally resulting in the formation of clusters. This process can be interpreted as modulation of a cellular network by the activity associated with contraction, which could be employed to control cellular networks by modifying the dynamics associated with the contractions in cardiac tissue culture.

q-bio.CB↗