ADATEX4D introduces an adaptive texture-capacity module for deformation-based 4D Gaussian Splatting, allowing each Gaussian to carry packed RGBA triplanes whose axes grow independently based on visibility-normalized screen-space gradients and deformed local scales. The method reduces texture storage by more than half on datasets such as N3DV and PanopticSports while preserving reconstruction quality. Under fixed memory budgets, adaptive allocation improves quality over uniform texture assignment and lowers overall model and peak memory usage.
By De Jiang, Peiqiang Wang, Kehong Yuan, Shaohua Ma
arXiv:2512.07197v2 Announce Type: replace
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful explicit representation enabling real-time, high-fidelity 3D reconstruction and novel view s...
By Seokhyun Youn, Soohyun Lee, Geonho Kim, Weeyoung Kwon, Sung-Ho Bae, Jihyong Oh
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...
By Zhiwei Li, Yijia Guo, Yishi Lu, Liwen Hu, Hong Rao, Shengbo Chen, Lei Ma
arXiv:2609.23509v1 Announce Type: new
Abstract: Novel view synthesis is a key task for dynamic scene reconstruction, where high rendering speed is essential for applications such as virtual reality....
By Huiwen Xue (School of Software, Northwestern Polytechnical University), Kaixing Zhao (School of Software, Northwestern Polytechnical University), Zuheng Ming (L2TI, Universit\'e Sorbonne Paris Nord, EmboMind Research), Tingcheng Li (School of Electronic Information,Engineering, Suzhou University of Science,Technology)
F4Splat introduces a feed‑forward predictive densification strategy for 3D Gaussian splatting that allocates Gaussians based on a densification‑score guided by spatial complexity and multi‑view overlap. The method predicts per‑region scores to estimate required Gaussian density, enabling explicit control over the total Gaussian budget without retraining. This adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, yielding compact yet high‑quality 3D representations and superior novel‑view synthesis performance with fewer Gaussians.
By Injae Kim, Chaehyeon Kim, Minseong Bae, Minseok Joo, Hyunwoo J. Kim
arXiv:2609.14129v1 Announce Type: cross
Abstract: Ultra-High-Definition (UHD) video presents significant challenges for efficient storage and real-time decoding. Learning-based methods, such as Neura...
By Chenhao Zhang, Fengqing Zhu
arXiv:2604.18980v2 Announce Type: replace
Abstract: Reducing the number of Gaussian-tile pairs is one of the most promising approaches to improve 3D Gaussian Splatting (3D-GS) rendering speed on GPUs...
By Joongho Jo, Hyerin Lim, Hanjun Choi, Jongsun Park
arXiv:2609.07557v1 Announce Type: cross
Abstract: 3D Gaussian Splatting has recently revolutionised novel view synthesis as well as many other 3D vision methods and applications. Drawing inspiration...
By Simone Foti, Caner Korkmaz, Stefanos Zafeiriou, Tolga Birdal
CC-4DGS introduces a storage‑efficient framework for dynamic 4D Gaussian splatting by replacing large multi‑resolution hash tables with a deterministic dense hash encoding and compact neural decoders, reducing deformation storage to 1–3 MB per scene. It also compresses canonical point‑cloud attributes through conditional autoencoding, selective quantization, and residual codebooks, achieving 3–5× reduction in point‑cloud size with negligible quality loss. The combined approach maintains real‑time rendering performance while lowering total storage to 20–30 MB, matching state‑of‑the‑art reconstruction accuracy on N3DV and Technicolor Light Field datasets.
By Kyungdae Park, Chae Eun Rhee
arXiv:2607.20813v2 Announce Type: replace
Abstract: Pixel-aligned Gaussian splatting enables efficient and generalizable novel-view synthesis. However, high-resolution rendering faces a critical trad...
By Jiun Lee, Jaekwang Kim, Sangmin Lee
Feed-forward 3D Gaussian Splatting (3DGS) enables scalable scene reconstruction without per-scene optimization, yet produces dense Gaussians that are costly to store and transmit. Existing feed-forward Gaussian compression methods formulate decoding as deterministic representation recovery, which becomes inadequate at low bitrates when high-frequency textures and view-dependent appearance are discarded.
Dynamic 4D Gaussian Splatting has emerged as an efficient representation for dynamic novel view synthesis through explicit scene modeling and real-time rendering. However, existing methods typically require dense multi-view videos for sufficient geometric constraints, making capture expensive and limiting sparse-camera deployment.