arXiv subjects

Yicheng Zhan

Publications and source records attributed to Yicheng Zhan.

9 recordsLinked to original sources

arXiv2026

Hologram Representation via Quadratic Phase Gaussian Splatting

We introduce Complex-Valued Quadratic Phase Gaussian (CVQPG), a novel hologram representation method that replaces standard 2D Gaussian representations used in 2D Gaussian Splatting with 2D quadratic phase functions. CVQPG incorporates additional learnable parameters to control the curvature of these bases. We evaluate our approach against state-of-the-art methods, exceeding the visual quality by +0.19 dB (RGB) and +0.33 dB (grayscale) on average in holographic reconstructions. Specifically, our equal parameter count evaluations show that modulating the primitive's wavefront is an effective and lightweight enhancement for hologram representations. In addition, our frequency domain analysis illustrates that CVQPG has successfully preserved the mid-to-high frequency band of natural images.

cs.GR↗

arXiv2026

Clustered Codebook Quantization for 2D Gaussian-based Image Compression

Gaussian-based image representations effectively model image content using compact parametric primitives while preserving high visual fidelity, yet storing a large number of floating-point parameters per primitive degrades rate-distortion efficiency at higher fidelity targets. To improve the rate-distortion performance in Gaussian representation, we present our Cluster-Guided Vector Quantization (CGVQ), a Gaussian primitive based image compression method. Our key idea is to partition Gaussian parameters further into homogeneous groups prior to quantization, enabling higher compression efficiency and accurate parameter reconstruction. In practice, our extensive experiments show that CGVQ decreases the bpp by 20% with respect to our baseline, while maintaining on-par visual quality

cs.CV↗

arXiv2026

Complex-Valued 2D Gaussian Representation for Computer-Generated Holography

Complex-valued Gaussian primitives have recently been explored for representing holographic radiance fields in 3D novel view synthesis. In this work, we extend this line of research to the hologram optimization domain and propose a structured representation based on complex-valued 2D Gaussian primitives. Inspired by Gabor's theory, we show that our primitive attains the minimum space-frequency uncertainty and reduces the parameter search space by 5:1 compared to per-pixel parameterization. To enable end-to-end training, we develop a differentiable rasterizer for our representation, integrated with a GPU-optimized light propagation kernel in free space. Extensive experiments show that our method reduces VRAM usage by up to 30% and accelerates optimization by 50% over standard autodiff-based implementations, delivers up to 13 dB higher PSNR than prior Gaussian-based methods, and achieves up to 3200x faster rendering while maintaining reconstruction quality on par with existing CGH approaches. For evaluation, we introduce a conversion procedure that adapts our representation to practical hologram formats, including smooth and random phase-only holograms. By reducing the hologram parameter search space, our representation enables a more scalable hologram estimation in the next-generation computer-generated holography systems.

cs.CV↗

arXiv2026

Configurable Holography: Towards Display and Scene Adaptation

Rendering holograms for holographic displays is often an iterative and computationally costly process. Emerging learned holography methods have alleviated this bottleneck by enabling fast hologram rendering with improved reconstruction quality. However, existing methods still depend on fixed display hardware and scene parameters, requiring retraining for each new configuration. This limits rapid adaptation to different visual needs, including scene brightness, user focus preference, and hardware compatibility. We introduce Configurable Holography, a learned CGH framework in which a single model adapts to diverse display-scene parameters through explicit conditioning, eliminating the need for retraining. As a prototype, we present a configurable structure and derive a family of models that continuously adapt to propagation distance, volume depth, peak brightness, pixel pitch, and wavelength. To further improve efficiency, we incorporate auxiliary monocular depth estimation for depth-aware 3D hologram synthesis from RGB-only inputs and apply knowledge distillation for interactive inference. Our extensive simulation and hardware experiments on three holographic display prototypes with different combinations of configurations show on-par reconstruction quality with existing methods, offering up to 2x speed-up in fp32. Our work represents an initial step toward flexible, general-purpose learned holography systems that can seamlessly adapt across diverse hardware and user-specific visual requirements.

cs.CV↗

arXiv2026

Complex-Valued Holographic Radiance Fields

Modeling wave properties of light is an important milestone for advancing physically-based rendering. In this paper, we propose complex-valued holographic radiance fields, a method that optimizes scenes without relying on intensity-based intermediaries. By leveraging multi-view images, our method directly optimizes a scene representation using complex-valued Gaussian primitives representing amplitude and phase values aligned with the scene geometry. Our approach eliminates the need for computationally expensive holographic rendering that typically utilizes a single view of a given scene. This accelerates holographic rendering speed by 30x-10,000x while achieving on-par image quality with state-of-the-art holography methods, representing a promising step towards bridging the representation gap between modeling wave properties of light and 3D geometry of scenes.

cs.GR↗

arXiv2026

Enhancing Binary Encoded Crime Linkage Analysis Using Siamese Network

Effective crime linkage analysis is crucial for identifying serial offenders and enhancing public safety. To address limitations of traditional crime linkage methods in handling high-dimensional, sparse, and heterogeneous data, we propose a Siamese Autoencoder framework that learns meaningful latent representations and uncovers correlations in complex crime data. Using data from the Violent Crime Linkage Analysis System (ViCLAS), maintained by the Serious Crime Analysis Section of the UK's National Crime Agency, our approach mitigates signal dilution in sparse feature spaces by integrating geographic-temporal features at the decoder stage. This design amplifies behavioral representations rather than allowing them to be overshadowed at the input level, yielding consistent improvements across multiple evaluation metrics. We further analyze how different domain-informed data reduction strategies influence model performance, providing practical guidance for preprocessing in crime linkage contexts. Our results show that advanced machine learning approaches can substantially enhance linkage accuracy, improving AUC by up to 9% over traditional methods while offering interpretable insights to support investigative decision-making.

cs.LG↗

arXiv2025

Assessing Learned Models for Phase-only Hologram Compression

We evaluate the performance of four common learned models utilizing INR and VAE structures for compressing phase-only holograms in holographic displays. The evaluated models include a vanilla MLP, SIREN, and FilmSIREN, with TAESD as the representative VAE model. Our experiments reveal that a pretrained image VAE, TAESD, with 2.2M parameters struggles with phase-only hologram compression, revealing the need for task-specific adaptations. Among the INRs, SIREN with 4.9k parameters achieves %40 compression with high quality in the reconstructed 3D images (PSNR = 34.54 dB). These results emphasize the effectiveness of INRs and identify the limitations of pretrained image compression VAEs for hologram compression task.

cs.GR↗

arXiv2024

Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions

Computer-Generated Holography (CGH) is a set of algorithmic methods for identifying holograms that reconstruct Three-Dimensional (3D) scenes in holographic displays. CGH algorithms decompose 3D scenes into multiplanes at different depth levels and rely on simulations of light that propagated from a source plane to a targeted plane. Thus, for n planes, CGH typically optimizes holograms using n plane-to-plane light transport simulations, leading to major time and computational demands. Our work replaces multiple planes with a focal surface and introduces a learned light transport model that could propagate a light field from a source plane to the focal surface in a single inference. Our learned light transport model leverages spatially adaptive convolution to achieve depth-varying propagation demanded by targeted focal surfaces. The proposed model reduces the hologram optimization process up to 1.5x, which contributes to hologram dataset generation and the training of future learned CGH models.

cs.GR↗

arXiv2024

AutoColor: Learned Light Power Control for Multi-Color Holograms

Multi-color holograms rely on simultaneous illumination from multiple light sources. These multi-color holograms could utilize light sources better than conventional single-color holograms and can improve the dynamic range of holographic displays. In this letter, we introduce AutoColor , the first learned method for estimating the optimal light source powers required for illuminating multi-color holograms. For this purpose, we establish the first multi-color hologram dataset using synthetic images and their depth information. We generate these synthetic images using a trending pipeline combining generative, large language, and monocular depth estimation models. Finally, we train our learned model using our dataset and experimentally demonstrate that AutoColor significantly decreases the number of steps required to optimize multi-color holograms from > 1000 to 70 iteration steps without compromising image quality.

cs.CV↗