arXiv:2606.11390v1 Announce Type: cross Abstract: Gaussian splatting methods have become increasingly popular for neural reconstruction of the real world. However, they are often limited in scale and resolution due to compute and memory constraints. We present a multi-GPU Gaussia…
3D Gaussian Splatting (3DGS) is a powerful technique for creating high-fidelity 3D assets. However, the widespread sharing and iterative modification of 3DGS models across digital platforms create pressing challenges for intellectual property protection and forensic traceability.…
arXiv:2606.07670v1 Announce Type: cross Abstract: Deformable 3D Gaussian Splatting (D-3DGS) re-constructs dynamic scenes from monocular video by deforming a canonical set of 3D Gaussians through a positional-encoded MLP of frame time t. Although fitted to a continuous variable, t…
arXiv:2606.05124v1 Announce Type: cross Abstract: After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation. However, extracting accurate geometric information directly from 3DGS re…
After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation. However, extracting accurate geometric information directly from 3DGS remains challenging and can often reduce the appeara…
arXiv cs.AI
TIER_1English(EN)·Ningjing Fan, Yiqun Wang, Dongming Yan, Peter Wonka·
arXiv:2603.07664v3 Announce Type: replace-cross Abstract: The reflective appearance, especially strong and typically near-field specular reflections, poses a fundamental challenge for accurate surface reconstruction and novel view synthesis. Existing Gaussian splatting methods ei…
ZipSplat is a token-based feed-forward method that decouples 3D Gaussian placement from pixel grid, enabling efficient scene reconstruction with fewer Gaussians and superior performance on pose-free imaging tasks.
arXiv cs.LG
TIER_1English(EN)·Jens U. Kreber, Lukas Mack, Joerg Stueckler·
arXiv:2606.01950v1 Announce Type: cross Abstract: World models enable intelligent agents to predict the consequences of their actions on the environment. In this paper, we propose Multi Rigid Object Gaussian World Model (MRO-GWM), a novel model that learns action-conditional dyna…
arXiv:2603.09632v3 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, subsequently extending into numerous spatial AI applications. However, most existing 3DGS methods operate in isolation, focusing on…
arXiv cs.LG
TIER_1English(EN)·Mia Gaia Polansky, George Kopanas, Stephan Garbin, Todd Zickler, Dor Verbin·
arXiv:2605.29136v1 Announce Type: cross Abstract: We introduce a probabilistic splat-based radiance field framework that retains the fast rasterization and test-time efficiency of 3D Gaussian Splatting (3DGS) while replacing heuristic primitive manipulation with gradient-based op…
arXiv cs.AI
TIER_1English(EN)·ZY Chen, F Zhu, H Zhu, DY Kong, XK Kuang, YJ Zhang, CM Jiang·
arXiv:2603.12647v3 Announce Type: replace-cross Abstract: Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene reconstruction and novel view synthesis. However, most existing methods either rely solely on cameras or use LiDAR only fo…
arXiv cs.LG
TIER_1English(EN)·Yuyang Tan, Renhe Zhang, Hang Zhang, Ao Li, Xin Tan·
arXiv:2605.26576v1 Announce Type: cross Abstract: Referring 3D Gaussian Splatting (R3DGS), which utilizes natural language for 3D object segmentation, has emerged as a crucial capability for embodied AI. However, existing methods typically rely on expensive per-scene manual annot…
arXiv:2605.24304v1 Announce Type: cross Abstract: Articulated object reconstruction from sparse-view images is an ill-posed problem that requires simultaneous inference of geometry and underlying articulation structure. Existing methods for articulated object reconstruction based…
arXiv cs.LG
TIER_1English(EN)·Hyeseong Kim, Geonhui Son, Deukhee Lee, Dosik Hwang·
arXiv:2605.22069v1 Announce Type: cross Abstract: Novel view synthesis from sparse-view inputs poses a significant challenge in 3D computer vision, particularly for achieving high-quality scene reconstructions with limited viewpoints. We introduce TWINGS, a framework that enhance…
Feed-forward 3D Gaussian Splatting (3DGS) models offer fast single-pass reconstruction,but scaling them to match per-scene optimization quality is fundamentally hindered by the scarcity of large-scale 3D annotations.A practical compromise is predict-then-refine,where post-predict…
arXiv:2606.11894v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) removes the need for time-consuming per-scene optimization required by traditional 3DGS. However, existing feed-forward approaches struggle with real-world photo collections that include div…
arXiv:2606.11782v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) achieves impressive real-time rendering, it frequently struggles to synthesize high-frequency textures, a limitation heavily exacerbated in memory-constrained and rate-distortion-optimized (RDO) pi…
arXiv cs.CV
TIER_1English(EN)·Mingzhe Lyu, Jinqiang Cui, Hong Zhang·
arXiv:2606.11841v1 Announce Type: new Abstract: Low-light novel view synthesis is challenging because dark multi-view images contain noise, weak structural detail, and compressed dynamic range. Recent 3D Gaussian Splatting (3DGS) methods address these challenges by generating pse…
Feed-forward 3D Gaussian Splatting (3DGS) removes the need for time-consuming per-scene optimization required by traditional 3DGS. However, existing feed-forward approaches struggle with real-world photo collections that include diverse lighting conditions and transient objects. …
Low-light novel view synthesis is challenging because dark multi-view images contain noise, weak structural detail, and compressed dynamic range. Recent 3D Gaussian Splatting (3DGS) methods address these challenges by generating pseudo ground-truth (pseudo-GT) images as supervisi…
While 3D Gaussian Splatting (3DGS) achieves impressive real-time rendering, it frequently struggles to synthesize high-frequency textures, a limitation heavily exacerbated in memory-constrained and rate-distortion-optimized (RDO) pipelines. To address this, we propose a versatile…
arXiv:2606.10612v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) is a powerful technique for creating high-fidelity 3D assets. However, the widespread sharing and iterative modification of 3DGS models across digital platforms create pressing challenges for intellectua…
3D Gaussian Splatting (3DGS) is a powerful technique for creating high-fidelity 3D assets. However, the widespread sharing and iterative modification of 3DGS models across digital platforms create pressing challenges for intellectual property protection and forensic traceability.…
arXiv:2606.09034v1 Announce Type: new Abstract: Neural radiance field (NeRF) and 3D Gaussian splatting (3DGS) are two mainstream approaches for novel view synthesis. They often show complementary performance, i.e., 3DGS demonstrating faster rendering speed and NeRF demonstrating …
arXiv:2606.09074v1 Announce Type: new Abstract: Existing pruning methods for 3D Gaussian splatting (3DGS) suffer from either severe quality degradation or prohibitive computational overhead. In this paper, we propose REFINE, a highly accelerated 3DGS pruning framework centered on…
arXiv cs.CV
TIER_1English(EN)·Yongfei Guo, Qizhou Huo, Xuan Sun, Yuanhao Gong·
arXiv:2606.07932v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has become an efficient explicit representation for radiance field reconstruction and real-time novel view synthesis. However, its standard photometric loss treats flat and structure-rich regions similar…
arXiv cs.CV
TIER_1English(EN)·Valentin Wagner, Sebastian Bullinger, Christoph Bodensteiner, Michael Arens·
arXiv:2606.06690v1 Announce Type: new Abstract: We present RPC-GS, the first Gaussian Splatting framework for satellite imagery that operates natively with Rational Polynomial Camera (RPC) models. The RPC model is the de facto standard for representing the complex imaging geometr…
arXiv:2606.07179v1 Announce Type: new Abstract: Streaming 3D Gaussian Splatting requires highly scalable, progressive representations. Existing progressive methods rely on \textit{discrete layering}, accumulating separate splat sets for each level of detail. This structural indep…
Streaming 3D Gaussian Splatting requires highly scalable, progressive representations. Existing progressive methods rely on \textit{discrete layering}, accumulating separate splat sets for each level of detail. This structural independence between layers inherently leads to error…
arXiv:2606.05650v1 Announce Type: cross Abstract: Dynamic 3D Gaussian Splatting (3DGS) holds great promise as a 3D video streaming technology since it can represent complex 3D scenes with high fidelity. In this approach, every frame in a 3D video represents the environment as a c…
arXiv cs.CV
TIER_1English(EN)·Jean Cordonnier, Chenghao Xu, Olga Fink, Malcolm Mielle·
arXiv:2606.05491v1 Announce Type: new Abstract: Multi-modal novel view synthesis (NVS) combining RGB and thermal imagery enables precise 3D scene reconstruction with visual and thermal information. However, existing methods typically rely on precisely calibrated RGB-thermal image…
arXiv cs.CV
TIER_1Deutsch(DE)·Alexander Veicht, Sunghwan Hong, D\'aniel Bar\'ath, Marc Pollefeys·
arXiv:2606.05102v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting methods reconstruct a scene from posed or pose-free images in a single forward pass, yet current approaches predict one Gaussian per input pixel, tying the representation budget to camera resolutio…
Feed-forward 3D Gaussian Splatting methods reconstruct a scene from posed or pose-free images in a single forward pass, yet current approaches predict one Gaussian per input pixel, tying the representation budget to camera resolution rather than scene complexity. A flat wall and …
arXiv:2606.03254v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) allows efficient and high-fidelity novel view synthesis (NVS) from an offline recorded image sequence. However, achieving online NVS from streaming and unposed image inputs remains challengi…
arXiv:2606.03120v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables real-time novel view synthesis by representing scenes as collections of anisotropic Gaussians optimized via differentiable rasterization. However, standard pixel-space losses (L1, SSIM) constrain…
arXiv cs.CV
TIER_1English(EN)·Adrian Ramlal, John S. Zelek·
arXiv:2606.03479v1 Announce Type: new Abstract: Dynamic 3D Gaussian Splatting (3DGS) methods reconstruct time-varying scenes from synchronized multi-camera video using photometric supervision. When a moving object becomes fully occluded from all training cameras, this supervision…
arXiv cs.CV
TIER_1English(EN)·Qingpo Wuwu, Xiaobao Wei, Peng Chen, Nan Huang, Zhongyu Zhao, Hao Wang, Ming Lu, Ningning Ma, Shanghang Zhang·
arXiv:2606.03909v1 Announce Type: new Abstract: While 3D Gaussian Splatting has shown promising results in street scene reconstruction, existing methods require massive numbers of Gaussian primitives to capture fine details, leading to prohibitive storage costs and slow rendering…
While 3D Gaussian Splatting has shown promising results in street scene reconstruction, existing methods require massive numbers of Gaussian primitives to capture fine details, leading to prohibitive storage costs and slow rendering speeds. We observe that dynamic objects (e.g., …
Dynamic 3D Gaussian Splatting (3DGS) methods reconstruct time-varying scenes from synchronized multi-camera video using photometric supervision. When a moving object becomes fully occluded from all training cameras, this supervision vanishes: the Gaussians representing it receive…
arXiv cs.CV
TIER_1English(EN)·Adrian Ramlal, Yan Song Hu, John S. Zelek·
arXiv:2606.00450v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) is a technique for creating and rendering 3D scenes, however its performance depends heavily on the quality of initial seed points. To improve 3DGS initialization, this study presents and evaluates sever…
arXiv:2603.06989v3 Announce Type: replace Abstract: This paper introduces MipSLAM, a frequency-aware 3D Gaussian Splatting (3DGS) SLAM framework capable of high-fidelity anti-aliased novel view synthesis and robust pose estimation under varying camera configurations. Existing 3DG…
arXiv:2602.20807v2 Announce Type: replace Abstract: Combining 3D Gaussian splatting with Simultaneous Localization and Mapping (SLAM) has gained popularity as it enables continuous 3D environment reconstruction during motion. However, existing methods struggle in dynamic environm…
arXiv:2606.00817v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) renders new views of a scene in real time. Like every rasterizer, it answers only primary rays, the rays from the camera through the image. It cannot trace the secondary rays that shadows, ambient occl…
arXiv:2606.02346v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) achieves remarkable novel view synthesis quality with real-time rendering, yet suffers from excessive memory consumption due to millions of Gaussian primitives. Existing pruning methods rely on heuristic…
arXiv cs.CV
TIER_1English(EN)·Dawid Paj\k{a}k, Martin Bisson, Rodolfo Lima·
arXiv:2606.00352v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has become the standard for real-time novel view synthesis on commodity GPUs. Its pipeline ties spatial partitioning and rasterization to one tile size, yet the two pull in opposite directions: partition…
3D Gaussian Splatting (3DGS) achieves remarkable novel view synthesis quality with real-time rendering, yet suffers from excessive memory consumption due to millions of Gaussian primitives. Existing pruning methods rely on heuristic importance scores or synchronous batch updates,…
arXiv:2605.30863v1 Announce Type: new Abstract: Dynamic scene reconstruction and novel view synthesis are fundamental to next-generation visual intelligence applications such as virtual reality, robotics, and digital twins. However, high-fidelity reconstruction of complex, time-v…
arXiv cs.CV
TIER_1English(EN)·Finn Dr\"oge, Cecilia Curreli, Abhishek Saroha, Daniel Cremers·
arXiv:2605.30987v1 Announce Type: new Abstract: The tasks of object removal and inpainting 3D Gaussian Splatting (3DGS) scenes face challenges such as 3D consistency across camera views. In comparing 2D inpainters and their suitability for the 3D domain, we find that reconstructi…
arXiv:2510.09364v2 Announce Type: replace Abstract: 3D Gaussian splatting (3DGS) has demonstrated impressive performance in synthesizing high-fidelity novel views. Nonetheless, its effectiveness critically depends on the quality of the initialized point cloud. Specifically, achie…
arXiv cs.CV
TIER_1English(EN)·Pengteng Li, Yunfan Lu, Pinhao Song, Weiyu Guo, Huizai Yao, F. Richard Yu, Hui Xiong·
arXiv:2509.18898v2 Announce Type: replace Abstract: In this paper, we propose the first Structure-from-Motion (SfM)-free deblurring 3D Gaussian Splatting method via event camera, dubbed DeblurSplat. We address the motion-deblurring problem in two ways. First, we leverage the pret…
arXiv cs.CV
TIER_1English(EN)·Hannah Schieber, Dominik Frischmann, Victor Schaack, Angela P. Schoellig, Daniel Roth·
arXiv:2605.31376v1 Announce Type: cross Abstract: Autonomous robots in unknown indoor environments require both reliable collision avoidance and object-level understanding. Classical representations such as TSDF support safe planning but lack semantics, while photorealistic metho…
Autonomous robots in unknown indoor environments require both reliable collision avoidance and object-level understanding. Classical representations such as TSDF support safe planning but lack semantics, while photorealistic methods like Gaussian Splatting (GS) provide rich appea…
arXiv:2605.30342v1 Announce Type: new Abstract: We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predict…
arXiv:2605.29549v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) is a recent approach for scene rendering. Although primarily designed for view synthesis, its potential for scene understanding tasks remains underexplored. In this work, we conduct a comparative evaluat…
arXiv cs.CV
TIER_1English(EN)·Manoj Biswanath, Chenxin Cai, Hannah Schieber, Daniel Roth, Benjamin Busam·
arXiv:2605.30328v1 Announce Type: new Abstract: Efficient and robust 3D scene representation is crucial in autonomous driving, robotics, and related fields. While RGB images provide valuable content for 3D reconstruction, other modalities like thermal or depth can enable addition…
We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predictions from the 3DGS. To address this, we introduc…
Efficient and robust 3D scene representation is crucial in autonomous driving, robotics, and related fields. While RGB images provide valuable content for 3D reconstruction, other modalities like thermal or depth can enable additional information on the environment. Lately, novel…
arXiv:2605.20150v2 Announce Type: replace Abstract: Training 3D Gaussian Splatting (3DGS) at billion-primitive scale is fundamentally memory-bound: each Gaussian primitive carries a large attribute vector, and the aggregate parameter table quickly exceeds GPU capacity, limiting p…
arXiv cs.CV
TIER_1English(EN)·Wenzhi Guo, Guangchi Fang, Shu Yang, Bing Wang·
arXiv:2601.17354v5 Announce Type: replace Abstract: While 3D Gaussian Splatting (3DGS) enables real-time rendering, its training demands workstation-level compute and memory, making mobile deployment impractical under minute-scale time budgets and limited peak memory. We present …
arXiv cs.CV
TIER_1English(EN)·Zhengxian Yang, Fei Xie, Xutao Xue, Rui Zhang, Taicheng Huang, Yang Liu, Mengqi Ji, Tao Yu·
arXiv:2604.00648v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has enabled efficient 3D scene reconstruction from everyday images with real-time, high-fidelity rendering, greatly advancing VR/AR applications. Fisheye cameras, with their wider field of view (FOV)…
arXiv:2605.26629v1 Announce Type: new Abstract: Novel-view synthesis and 3D reconstruction from sparse posed images are central to robotics and AR/VR. Yet, feed-forward 3D Gaussian reconstruction fails under lowlight due to noise, color shifts, and unreliable correspondence. We p…
arXiv:2605.26447v1 Announce Type: new Abstract: Underwater scene reconstruction is essential for immersive exploration of aquatic environments, yet remains challenging due to complex participating-media effects such as absorption and scattering, as well as the limited field of vi…
Novel-view synthesis and 3D reconstruction from sparse posed images are central to robotics and AR/VR. Yet, feed-forward 3D Gaussian reconstruction fails under lowlight due to noise, color shifts, and unreliable correspondence. We propose DelowlightSplat, a lowlight-aware feed-fo…
arXiv:2605.24964v1 Announce Type: new Abstract: Reconstructing high-quality 3D scenes from low-resolution multi-view images remains challenging for 3D Gaussian Splatting (3DGS), because insufficient high-frequency observations often lead to blurred textures, weak boundaries, and …
arXiv:2605.25563v1 Announce Type: new Abstract: While feed-forward 3D Gaussian splatting reconstructs renderable Gaussian primitives from sparse context views without per-scene optimization, existing pipelines do not provide a compact scene representation for storage or transmiss…
arXiv:2605.25909v1 Announce Type: new Abstract: Reconstructing and predicting dynamic 3D scenes from multi-view videos is a foundational task for robotics, AR/VR, and digital twins. Recent physics-informed Gaussian Splatting methods achieve impressive future frame extrapolation b…
Reconstructing and predicting dynamic 3D scenes from multi-view videos is a foundational task for robotics, AR/VR, and digital twins. Recent physics-informed Gaussian Splatting methods achieve impressive future frame extrapolation but lack semantic awareness and suffer from large…
arXiv:2605.23672v1 Announce Type: new Abstract: Reconstructing dynamic 3D scenes from monocular videos is a fundamental yet highly challenging task, as real-world motions often involve both long-term smooth transformations and short-term complex deformations. Existing methods eit…
arXiv:2605.23287v1 Announce Type: new Abstract: We present LangFlash, a feed-forward framework for 3D Language Gaussian Splatting that reconstructs 3D scenes parameterized by Gaussian primitives enriched with language-aligned semantic features from sparse unposed multi-view image…
Reconstructing dynamic 3D scenes from monocular videos is a fundamental yet highly challenging task, as real-world motions often involve both long-term smooth transformations and short-term complex deformations. Existing methods either struggle to maintain temporal consistency or…
We present LangFlash, a feed-forward framework for 3D Language Gaussian Splatting that reconstructs 3D scenes parameterized by Gaussian primitives enriched with language-aligned semantic features from sparse unposed multi-view images. Unlike optimization-based 3D methods, LangFla…
arXiv cs.CV
TIER_1English(EN)·Jiangwei Mo, Xi Lu, Hanlin Wu·
arXiv:2605.22147v1 Announce Type: new Abstract: High-resolution remote sensing images (RSIs) are crucial for Earth observation applications, yet acquiring them is often limited by sensor constraints and costs. In recent years, generative super-resolution (SR) methods, particularl…
arXiv:2605.22020v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) models offer fast single-pass reconstruction,but scaling them to match per-scene optimization quality is fundamentally hindered by the scarcity of large-scale 3D annotations.A practical comp…
arXiv cs.CV
TIER_1English(EN)·Sifan Zhou, Hang Zhang, Yuhang Wang, Ming Li·
arXiv:2605.22342v1 Announce Type: new Abstract: While 4D Gaussian Splatting (4DGS) has revolutionized high-fidelity dynamic reconstruction, safeguarding the intellectual property of these assets remains an open challenge. Conventional steganographic techniques often neglect the u…
While 4D Gaussian Splatting (4DGS) has revolutionized high-fidelity dynamic reconstruction, safeguarding the intellectual property of these assets remains an open challenge. Conventional steganographic techniques often neglect the underlying kinematic manifolds, triggering non-ph…
2D Gaussian splatting provides an efficient explicit representation for image reconstruction, but existing methods still require costly per-image iterative optimization or rely on handcrafted priors for primitive allocation. We present AIR, a self-supervised feed-forward framewor…
Training 3D Gaussian Splatting (3DGS) at billion-primitive scale is fundamentally memory-bound: each Gaussian primitive carries a large attribute vector, and the aggregate parameter table quickly exceeds GPU capacity, limiting prior systems to tens of millions of Gaussians on com…
3D Gaussian Splatting (3DGS) provides an explicit and efficient scene representation, but its primitives lack inherent object-level identity, hindering downstream tasks such as open-vocabulary scene understanding. Existing methods typically address this by either distilling high-…
Reconstructing large-scale urban scenes from sparse aerial views is a crucial yet challenging task. Due to biased top-down and shallow-oblique camera poses, sparse aerial captures exhibit strong evidence imbalance: roofs and open regions are repeatedly observed, while facades, di…
While 3D Gaussian Splatting (3DGS) has revolutionized real-time photorealistic view synthesis, its fundamental reliance on symmetric Gaussian distributions introduces visual artifacts that hinder accurate spatial data exploration. Specifically, symmetric kernels struggle to captu…
We introduce GaussianZoom, a generative zoom-in 3D reconstruction system with an iterative progressive framework that combines geometry-consistent scene modeling and multi-scale semantic reasoning to enable high-fidelity extreme zoom-in rendering from low-resolution inputs. To ac…
3D Gaussian Splatting (3D-GS) enables real-time 3D scene reconstruction but lacks robust segmentation for editing tasks such as object removal, extraction, and recoloring. Existing approaches that lift 2D segmentations to the 3D domain suffer from view inconsistencies and coarse …
