Thread‑Efficient Decoding for Neural Texture Compression proposes a shared decoder MLP architecture trained with a gradual decoder freezing schedule and texture clustering to reduce GPU thread divergence by 25‑52%. The method preserves rendering quality while achieving up to 8.48× speedup on a Radeon RX 9070 XT compared to non‑shared baselines. Experiments on over 500 textures and multiple real rendering scenes validate the performance gains and provide comprehensive ablation studies.
arXiv:2607.13808v2 Announce Type: replace Abstract: Neural radiance representations in Gaussian Splatting (GS) deliver high-fidelity color detail but impose substantial rendering overhead from networ...
arXiv:2609.23169v1 Announce Type: new Abstract: High-quality texture generation is essential for creating realistic and production-ready 3D assets. Recent multi-view diffusion methods have shown prom...
arXiv:2609.23606v1 Announce Type: new Abstract: Mesh texture compression typically relies on 2D UV atlases, whose chart discontinuities and mapping overhead can limit coding efficiency. To tackle thi...
arXiv:2607. 17842v1 Announce Type: cross Abstract: Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed.
arXiv:2610.29691v1 Announce Type: new Abstract: Generative image compression (GIC) delivers strong perceptual quality at low bitrates. However, GIC methods with strong perceptual quality often rely o...
The paper introduces a new learning paradigm for visual generation that separates knowledge acquisition and high-fidelity rendering. Autoregressive pretraining is used to acquire semantic knowledge, while diffusion models are employed afterward for detailed image synthesis. The authors demonstrate that this approach improves learning efficiency and final generation quality, and they provide compute‑optimal scaling laws that enable training a 3B‑parameter text‑to‑image model with only 6,600 H100 GPU‑hours, achieving state‑of‑the‑art scores on GenEval and DPG‑Bench.
arXiv:2609.18602v1 Announce Type: new Abstract: Despite recent progress in learned image compression, existing methods remain computationally expensive on resource-constrained hardware, particularly...
arXiv:2609.39222v1 Announce Type: new Abstract: High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff be...
arXiv:2609.37831v1 Announce Type: new Abstract: Real-time diffusion-based video super-resolution (VSR) is in high demand for online streaming, yet stringent latency requirements often compromise gene...
arXiv:2609.23380v1 Announce Type: new Abstract: Gaussian Splatting has enabled real-time novel view synthesis, but its tightly coupled geometry and appearance representation often require a large num...
arXiv:2501.13558v4 Announce Type: replace Abstract: Splat-based radiance fields have rapidly diversified in primitive type, kernel support, and appearance parameterization. This diversity makes compr...
arXiv:2609.25537v1 Announce Type: new Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing laten...