研究人员正在推进3D高斯溅射（3DGS）技术，以提高效率、准确性和编辑能力。新方法侧重于结合不确定性量化以实现更好的主动视图选择和场景重建，开发可证明的核集构造用于压缩，并增强具有一致性增强框架的以自我为中心的场景生成。此外，进展包括大规模场景的结构感知调度、动态场景的运动方差引导时间注意力、鲁棒的部件级编辑以及用于纹理操纵的内在分解。
AI
arXiv:2607.05522v1 Announce Type: cross Abstract: 3D Gaussian splatting (3DGS) is a strong representation for real-time novel-view synthesis, but its standard training pipeline relies on point estimates and hand-tuned heuristics, providing no native uncertainty or principled comp…
arXiv:2607.03819v1 Announce Type: cross Abstract: Challenges remain in ego-centric 3D scene generation due to limited view overlap and the dominant influence of individual perspectives on scene interpretation. These factors hinder the creation of viewpoint-consistent and semantic…
arXiv:2607.02721v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) enables high-quality real-time novel-view synthesis, but practical scenes often contain millions of Gaussians, making compression essential for deployment on limited hardware. Existing reduction method…
CGGS is a text-to-3D framework that enhances 3D-content-awareness and addresses geometric distortions through a multi-stage approach involving ego-centric generation, layout decoration, and geometric refinement.
3D Gaussian Splatting has demonstrated remarkable potential in novel view synthesis. In contrast to small-scale scenes, large-scale scenes inevitably contain sparsely observed regions with excessively sparse initial points. In this case, supervising Gaussians initialized from low…
3D Gaussian Splatting (3DGS) enables real-time novel view synthesis for static scenes. Extending it to dynamic scenes via deformation fields has recently attracted significant attention, particularly for dynamic scene reconstructionband distractor-free. However, existing deformat…
arXiv cs.AI
TIER_1English(EN)·Hayeon Kim, Ji Ha Jang, Se Young Chun·
arXiv:2507.11061v3 Announce Type: replace-cross Abstract: Recent advances in 3D neural representations and instance-level editing models have enabled the efficient creation of high-quality 3D content. However, achieving precise local 3D edits remains challenging, especially for G…
arXiv cs.AI
TIER_1English(EN)·Alexandre Lanvin, Jeffrey Hu, Simon Lucas, Adrien Bousseau, George Drettakis·
arXiv:2606.31637v1 Announce Type: cross Abstract: Intrinsic decomposition which expresses image colors as the product of diffuse albedo and shading, possibly augmented with view-dependent residuals has a long history in image editing as it enables the modification of object color…
arXiv:2603.23297v2 Announce Type: replace-cross Abstract: Despite their output being ultimately consumed by human viewers, 3D Gaussian Splatting (3DGS) methods often rely on ad-hoc combinations of pixel-level losses, resulting in blurry renderings. To address this, we systematica…
Intrinsic decomposition which expresses image colors as the product of diffuse albedo and shading, possibly augmented with view-dependent residuals has a long history in image editing as it enables the modification of object colors and textures without altering lighting. We exten…
arXiv:2506.07069v2 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, combining high-quality reconstruction with efficient rendering. It has been widely adopted in domains such as AR/VR, robotics, and …
arXiv:2606.30024v1 Announce Type: cross Abstract: Recent advances in deep learning have notably improved steganographic message hiding. However, designing a generalizable steganographic approach for 3D Gaussian Splatting (3DGS) that can embed meaningful 3D scene content remains c…
arXiv:2606.28656v1 Announce Type: cross Abstract: Deformable 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for rendering dynamic scenes in a wide range of 3D applications. However, existing deformation field-based approaches largely lack explicit object-level …
3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis, yet it suffers from severe overfitting under sparse-view settings due to insufficient geometric constraints. While recent methods introduce monocular depth priors to mitigate this, the…
Recent advances in 3D Gaussian Splatting have demonstrated unprecedented success in novel view synthesis. However, the substantial inference and storage overhead driven by high-order Spherical Harmonics (SH) are primary bottlenecks for mobile platforms. In this paper, we present …
Merging multiple 3D Gaussian Splatting (3DGS) scenes into a single unified Gaussian representation is essential for large-scale 3D mapping and long-term map management. Despite its importance, this area remains underexplored, and existing solutions exhibit several limitations. Le…
arXiv cs.AI
TIER_1English(EN)·Hana Kim, Minje Kim, Tae-Kyun Kim·
arXiv:2606.27584v1 Announce Type: cross Abstract: 3D scene inpainting is essential for reconstructing areas corrupted by occlusions or limited viewpoints. While recent methods leverage Gaussian Splatting (GS) for efficient 3D editing, they often depend on precise multi-view segme…
Flux-GS enables real-time high-fidelity 3D Gaussian Splatting on mobile platforms through efficient lighting representation, attribute-conditioned enhancement, and multi-view densification strategies.
Gaussian Splatting has been recently explored for satellite 3D reconstruction, demonstrating flexibility and efficiency in representing radiometrically diverse satellite scenes. However, the limited top viewpoint of satellite imagery results in insufficient supervision on buildin…
While 3D Gaussian Splatting (3DGS) provides an efficient and explicit representation for novel view synthesis, enforcing stylistic coherence across viewpoints remains challenging. Existing 3D stylization methods typically apply 2D feature-matching losses independently per rendere…
arXiv:2312.00206v4 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has recently enabled real-time rendering of unbounded 3D scenes for novel view synthesis. However, this technique requires dense training views to accurately reconstruct 3D geometry. A limited …
Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve high-frequency visual details of input images due to two structural bottlenecks. First, they adopt discriminative 2D fea…
Video diffusion models are adapted to decode explicit surface primitives directly from latent space, enabling high-quality 3D scene generation with improved geometric accuracy and real-time rendering capabilities.
Multi4D addresses the trade-off between motion consistency and visual fidelity in dynamic 3D Gaussian splatting through a multi-level competitive allocation framework that enables adaptive specialization and efficient representation.
3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated r…
arXiv:2411.15723v4 Announce Type: replace Abstract: High-fidelity surface reconstruction from multi-view images is a core problem in 3D computer vision. While neural implicit surfaces like SDFs offer smooth geometry, they are often bottlenecked by the computational intensity of v…
arXiv:2607.08250v1 Announce Type: new Abstract: Dynamic scene reconstruction remains challenging due to the heterogeneous and spatially varying nature of real-world motion. Although recent 3D Gaussian Splatting methods have introduced diverse deformation formulations for dynamic …
Dynamic scene reconstruction remains challenging due to the heterogeneous and spatially varying nature of real-world motion. Although recent 3D Gaussian Splatting methods have introduced diverse deformation formulations for dynamic novel view synthesis, each method typically reli…
arXiv cs.CV
TIER_1English(EN)·Mijeong Kim, Jungtaek Kim, Bohyung Han·
arXiv:2604.02915v2 Announce Type: replace Abstract: We present GP-4DGS, a novel framework that integrates Gaussian Processes (GPs) into 4D Gaussian Splatting (4DGS) for principled probabilistic modeling of dynamic scenes. While existing 4DGS methods focus on deterministic reconst…
arXiv cs.CV
TIER_1English(EN)·Kristof Overdulve, Lode Jorissen, Nick Michiels·
arXiv:2607.05598v1 Announce Type: cross Abstract: Novel View Synthesis (NVS) methods, such as 3D Gaussian Splatting (3DGS), rely heavily on the assumption of clean, multi-view consistent, posed input images. Real-world captures can violate this assumption due to screen-space arti…
arXiv cs.CV
TIER_1English(EN)·Mehdi Hosseinzadeh, Shin-Fang Chng, Yi Xu, Simon Lucey, Ian Reid, Ravi Garg·
arXiv:2512.17547v2 Announce Type: replace Abstract: 3D Gaussians have become a powerful scene representation for real-time splatting and high-quality novel-view synthesis. This has motivated generalizable splatting -- methods that adapt feed-forward geometry prediction networks t…
arXiv:2601.03024v3 Announce Type: replace Abstract: We propose Self-Augmented Residual 3D Gaussian Splatting (SA-ResGS), a novel framework to stabilize uncertainty quantification and enhancing uncertainty-aware supervision in next-best-view (NBV) selection for active scene recons…
arXiv:2607.05347v1 Announce Type: new Abstract: While feedforward 3D reconstruction excels at efficient novel view synthesis, it typically falters when faced with scenes under varying illumination. To this end, we introduce WildSplat, the first feedforward 3D Gaussian Splatting f…
arXiv cs.CV
TIER_1English(EN)·Yimo Wang, Bin Kang, Shuojue Yang, Yueming Jin·
arXiv:2607.04761v1 Announce Type: new Abstract: Real-time, text-promptable 4D reconstruction is indispensable for autonomous surgical interaction. Severe misalignment between semantic meaning and physical anatomy still persists, largely because existing solutions integrate Vision…
arXiv:2607.04256v1 Announce Type: new Abstract: Current feed-forward 3D reconstruction methods predict pixel aligned Gaussian primitives, resulting in highly redundant representations. A natural solution is to prune the redundant Gaussians, but naive pruning introduces severe art…
arXiv cs.CV
TIER_1English(EN)·Seungjun Tak, Yewon Jeon, Jaeik Hwang, SukMin Hwang, Seongbo Ha, Hyeonwoo Yu·
arXiv:2607.04127v1 Announce Type: new Abstract: We present a real-time LiDAR-based framework for Gaussian Splatting SLAM that tightly couples fast G-ICP registration with spherical rasterization-based dense mapping for large-scale sequences. Leveraging LiDAR geometry rather than …
arXiv:2607.03872v1 Announce Type: new Abstract: Reconstructing high-fidelity 3D building models from UAV imagery is essential for large-scale digital twin development. However, existing 3D Gaussian Splatting (3DGS) techniques often struggle with building facades, failing to captu…
arXiv:2607.03765v1 Announce Type: new Abstract: 3D reconstruction from sparse views is a challenging task in 3D computer vision. Recent studies on 3D Gaussian Splatting (3DGS) have achieved remarkable results with sparse views in novel view synthesis, yet reconstructing high-qual…
arXiv:2607.03390v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has revolutionized novel-view synthesis with its fast and high-fidelity rendering. However, rendering at high FPS and low latency across various scenes remains a challenge, especially when large amounts …
arXiv cs.CV
TIER_1English(EN)·Anurag Dalal, Daniel Hagen, Kjell G. Robbersmyr, Kristian Muri Knausg{\aa}rd·
arXiv:2607.03209v1 Announce Type: new Abstract: This paper introduces a fast method for high-quality 3D Gaussian Splatting (3DGS) reconstruction without traditional Structure-from-Motion (SfM). The proposed approach leverages 3D Foundation Models (3DFMs) for camera pose and point…
While feedforward 3D reconstruction excels at efficient novel view synthesis, it typically falters when faced with scenes under varying illumination. To this end, we introduce WildSplat, the first feedforward 3D Gaussian Splatting framework capable of appearance-conditioned novel…
Real-time, text-promptable 4D reconstruction is indispensable for autonomous surgical interaction. Severe misalignment between semantic meaning and physical anatomy still persists, largely because existing solutions integrate Vision-Language Models into deformable fields via a ri…
arXiv cs.CV
TIER_1English(EN)·Joanna Waczy\'nska, Tomasz Szczepanik, Piotr Borycki, S{\l}awomir Tadeja, Thomas Bohn\'e, Przemys{\l}aw Spurek·
arXiv:2410.01521v3 Announce Type: replace Abstract: Implicit Neural Representations (INRs) approximate discrete data through continuous functions and are commonly used for encoding 2D images. Traditional image-based INRs employ neural networks to map pixel coordinates to RGB valu…
arXiv cs.CV
TIER_1English(EN)·Hyunjoon Park, Donghyeon Cho·
arXiv:2607.01708v1 Announce Type: new Abstract: Reliable instance-level scene understanding is a fundamental prerequisite for object-level interactions and high-fidelity 3D representations. While current methods often leverage 2D foundation segmentation models to obtain these pri…
arXiv cs.CV
TIER_1English(EN)·Polina Karpikova, Wenjing Bian, Haofei Xu, Hendrik Lensch, Andreas Geiger·
arXiv:2607.02301v1 Announce Type: new Abstract: Inverse rendering aims to recover both 3D geometry and physically meaningful material properties from images, enabling applications such as relighting and novel view synthesis. Optimization-based methods achieve high fidelity but re…
arXiv:2607.01803v1 Announce Type: new Abstract: Recent advances in 3D content generation from text or images have achieved impressive results, yet view inconsistency from 2D generators and the scarcity of high-quality 3D data remain significant bottlenecks. Existing solutions typ…
arXiv:2607.01290v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-fidelity rendering. However, existing assets often suffer from quality bottlenecks such as missing details and texture noise. Prior attempts to enhance t…
arXiv:2607.01578v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables real-time novel view synthesis for static scenes. Extending it to dynamic scenes via deformation fields has recently attracted significant attention, particularly for dynamic scene reconstruction…
arXiv cs.CV
TIER_1English(EN)·Weiyi Xue, Fan Lu, Chi Zhang, Tianhang Wang, Sanqing Qu, Zehan Zheng, Boyuan Zheng, Junqiao Zhao, Guang Chen·
arXiv:2607.01698v1 Announce Type: new Abstract: 3D Gaussian Splatting has demonstrated remarkable potential in novel view synthesis. In contrast to small-scale scenes, large-scale scenes inevitably contain sparsely observed regions with excessively sparse initial points. In this …
arXiv:2607.01860v1 Announce Type: cross Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled significant progress in dense dynamic Simultaneous Localization And Mapping (SLAM). Prevailing methods typically discard predefined dynamic objects, ignoring that transi…
Inverse rendering aims to recover both 3D geometry and physically meaningful material properties from images, enabling applications such as relighting and novel view synthesis. Optimization-based methods achieve high fidelity but require costly per-scene fitting, while image-spac…
arXiv:2408.16982v3 Announce Type: replace Abstract: 2D Gaussian Splatting has recently emerged as a significant method in 3D reconstruction, enabling novel view synthesis and geometry reconstruction simultaneously. While the well-known Gaussian kernel is broadly used, its lack of…
arXiv:2607.00595v1 Announce Type: new Abstract: Gaussian Splatting has achieved significant improvements by incorporating warping-based techniques. However, such methods suffer from pixel-level inaccuracies due to uncertain geometry. This uncertainty leads to spatial misalignment…
Gaussian Splatting has achieved significant improvements by incorporating warping-based techniques. However, such methods suffer from pixel-level inaccuracies due to uncertain geometry. This uncertainty leads to spatial misalignments in the warped images, which disrupt residual l…
Producing 3D human representations from input views on the fly is essential for immersive live streaming systems, where representation compactness is as critical as high fidelity given limited computational power and transmission bandwidth. Although recent feed-forward reconstruc…
Generating high-quality novel views at real-time frame rates remains a central challenge in 3D vision, particularly in sparse-view scenarios. Neural radiance fields have demonstrated robust reconstruction from limited observations, but their reliance on volumetric rendering leads…
arXiv:2603.25265v2 Announce Type: replace Abstract: We present ViewSplat, a view-adaptive 3D Gaussian splatting network for novel view synthesis from unposed images. While recent feed-forward 3D Gaussian splatting has significantly accelerated 3D scene reconstruction by bypassing…
arXiv:2604.17969v3 Announce Type: replace Abstract: Visual search in 3D environments requires embodied agents to actively explore their surroundings and acquire task-relevant evidence. However, existing visual search and embodied AI benchmarks, including EQA, typically rely on st…
arXiv:2602.19323v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time and high-fidelity 3D reconstruction from posed images. However, recent studies reveal its vulnerability to adversarial corruptions in input views, whe…
arXiv:2511.14540v2 Announce Type: replace Abstract: This paper focuses on a challenging setting of simultaneously modeling geometry and appearance of hand-object interaction scenes without any object priors. We follow the trend of dynamic 3D Gaussian Splatting based methods, and …
arXiv cs.CV
TIER_1English(EN)·Wenhao Yuan, Yiyuan Ge, Deli Cai·
arXiv:2606.30545v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis, yet it suffers from severe overfitting under sparse-view settings due to insufficient geometric constraints. While recent methods introd…
arXiv:2606.30017v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting have demonstrated unprecedented success in novel view synthesis. However, the substantial inference and storage overhead driven by high-order Spherical Harmonics (SH) are primary bottlenecks …
arXiv:2606.30014v1 Announce Type: new Abstract: Real-to-sim reconstruction for embodied AI requires geometry that is useful for collision reasoning, navigation, and agent-environment interaction, not only photorealistic novel-view synthesis. However, close-range urban facades are…
arXiv:2606.29976v1 Announce Type: new Abstract: Reconstructing dynamic 3D scenes from monocular videos is challenging due to scene complexity and temporal dynamics. With the advancement of 3D Gaussian Splatting in novel view synthesis, existing methods extend 3D Gaussians to 4D d…
arXiv:2606.29794v1 Announce Type: new Abstract: Existing 3D Gaussian Splatting (3DGS) frameworks rely on camera-specific rasterization, suffering from inconsistent solid-angle sampling and degraded performance across heterogeneous camera models (e.g., perspective, fisheye, omnidi…
arXiv:2606.29782v1 Announce Type: new Abstract: Merging multiple 3D Gaussian Splatting (3DGS) scenes into a single unified Gaussian representation is essential for large-scale 3D mapping and long-term map management. Despite its importance, this area remains underexplored, and ex…
arXiv cs.CV
TIER_1English(EN)·Jerrin Bright, John Zelek·
arXiv:2606.28820v1 Announce Type: new Abstract: Reconstructing dynamic human--object interaction scenes from monocular video is difficult because the human, manipulated object, and background obey different motion models while sharing the same pixels. Existing dynamic radiance-fi…
arXiv cs.CV
TIER_1English(EN)·Mohamed Shawky Sabae, Philipp Langsteiner, Jan-Niklas Dihlmann, Hendrik Lensch·
arXiv:2606.28635v1 Announce Type: new Abstract: Inverse rendering requires separating illumination from surface materials, which is highly ambiguous due to their tight coupling in observed images. While Gaussian Splatting is efficient for novel view synthesis, existing relightabl…
arXiv cs.CV
TIER_1English(EN)·Shuang Song, Jiyong Kim, Rongjun Qin·
arXiv:2606.28581v1 Announce Type: new Abstract: High-resolution satellite imagery demands 3D reconstruction methods that deliver both speed and geometric accuracy. Recent adaptations of 3D Gaussian Splatting (3DGS) to satellite imagery demonstrate strong efficiency, but reconstru…
3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis, yet it suffers from severe overfitting under sparse-view settings due to insufficient geometric constraints. While recent methods introduce monocular depth priors to mitigate this, the…
arXiv:2606.28321v1 Announce Type: new Abstract: We present StructSplat, a feed-forward and generalizable 3D Gaussian reconstruction framework that operates directly on uncalibrated images without requiring camera parameters. Existing methods either rely on per-scene optimization …
arXiv cs.CV
TIER_1English(EN)·Xiaobiao Du, Yida Wang, Xin Yu·
arXiv:2410.02103v4 Announce Type: replace Abstract: Recent works in volume rendering, \textit{e.g.} NeRF and 3D Gaussian Splatting (3DGS), significantly advance the rendering quality and efficiency with the help of the learned implicit neural radiance field or 3D Gaussians. Rende…
arXiv cs.CV
TIER_1English(EN)·Huaiyuan Weng, Huibin Li, Chul Min Yeum·
arXiv:2606.27509v1 Announce Type: new Abstract: In this study, we develop a Structured framework for Gaussian Splatting (3DGS) with LiDAR integration (Structured-Li-GS). It is a lightweight Gaussian Splatting pipeline that leverages LiDAR-inertial-visual SLAM. Structured-Li-GS ac…
We present StructSplat, a feed-forward and generalizable 3D Gaussian reconstruction framework that operates directly on uncalibrated images without requiring camera parameters. Existing methods either rely on per-scene optimization or assume known camera poses, and often entangle…
arXiv cs.CV
TIER_1English(EN)·Robin Y. Park, Mark C. Eid, Rhydian Windsor, Amir Jamaludin, Ana I. L. Namburete, Jo\~ao F. Henriques, Andrew Zisserman·
arXiv:2606.26236v1 Announce Type: cross Abstract: The objective of this paper is to improve radiological gradings measured on MRIs of spines, by resampling scans so that the new view planes are better aligned with the target anatomy than the original sparse images. To this end, w…
arXiv cs.CV
TIER_1English(EN)·Jiyong Kim, Shuang Song, Ronjgun Qin·
arXiv:2606.27223v1 Announce Type: new Abstract: Gaussian Splatting has been recently explored for satellite 3D reconstruction, demonstrating flexibility and efficiency in representing radiometrically diverse satellite scenes. However, the limited top viewpoint of satellite imager…
arXiv cs.CV
TIER_1English(EN)·Zhihao Wen, Yixin Yang, Bojian Wu, Yang Zhou, Dani Lischinski, Daniel Cohen-Or, Hui Huang·
arXiv:2606.26754v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) provides an efficient and explicit representation for novel view synthesis, enforcing stylistic coherence across viewpoints remains challenging. Existing 3D stylization methods typically apply 2D f…
Gaussian Splatting has been recently explored for satellite 3D reconstruction, demonstrating flexibility and efficiency in representing radiometrically diverse satellite scenes. However, the limited top viewpoint of satellite imagery results in insufficient supervision on buildin…
While 3D Gaussian Splatting (3DGS) provides an efficient and explicit representation for novel view synthesis, enforcing stylistic coherence across viewpoints remains challenging. Existing 3D stylization methods typically apply 2D feature-matching losses independently per rendere…
arXiv cs.CV
TIER_1English(EN)·Seungyeon Yoo, Youngseok Jang, Dabin Kim, Youngsoo Han, Seungwoo Jung, H. Jin Kim·
arXiv:2602.11575v3 Announce Type: replace-cross Abstract: Visual navigation models often struggle in real-world dynamic environments due to limited robustness to the sim-to-real gap and the difficulty of training policies tailored to target deployment environments (e.g., househol…
arXiv cs.CV
TIER_1English(EN)·Yang Zheng, Hao Tan, Kai Zhang, Peng Wang, Leonidas Guibas, Gordon Wetzstein, Wang Yifan·
arXiv:2512.05354v2 Announce Type: replace Abstract: The rise of 3D Gaussian Splatting has revolutionized photorealistic 3D asset creation, yet a critical gap remains for their interactive refinement and editing. Existing approaches based on diffusion or optimization are ill-suite…
arXiv:2509.19297v3 Announce Type: replace Abstract: Feed-forward 3D Gaussian Splatting (3DGS) has emerged as a highly effective solution for novel view synthesis. Existing methods predominantly rely on a \emph{pixel-aligned} Gaussian prediction paradigm, where each 2D pixel is ma…
arXiv cs.CV
TIER_1English(EN)·Orest Kupyn, Goutam Bhat, Philipp Henzler, Fabian Manhardt, Christian Rupprecht, Federico Tombari·
arXiv:2606.24876v1 Announce Type: new Abstract: Generating explorable 3D scenes from a single image requires strong generative priors and accurate geometric representations suitable for downstream use. Current video diffusion models offer high-quality generation and implicitly en…
arXiv cs.CV
TIER_1English(EN)·Min Hyeok Bang, Jun Hyeong Kim, Seung-Wook Kim, Se-Ho Lee·
arXiv:2606.24144v1 Announce Type: new Abstract: In this paper, we present a novel geometry-aware style transfer framework for 3D Gaussian splatting (3DGS) that simultaneously transfers appearance attributes and geometric structures. Unlike prior works that primarily focus on colo…
Generating explorable 3D scenes from a single image requires strong generative priors and accurate geometric representations suitable for downstream use. Current video diffusion models offer high-quality generation and implicitly encode multi-view geometric structure in latent sp…
Despite modeling temporal motion, dynamic 3D Gaussian Splatting (3DGS) methods still inherit a static densification strategy that is ill-suited for dynamic scenes. This neglect of temporal behavior leads to under-reconstructed and blurry dynamic regions, as short-lived Gaussians …
