Generating a consistent whole-house VR tour from a floorplan and style reference requires both photorealistic panoramas and cross-view spatial coherence. Pure 2D generators produce appealing single panoramas but re-imagine geometry and materials when the viewpoint changes, wherea…
3D Gaussian Splatting (3DGS) has emerged as a leading representation for real-time novel view synthesis and been widely adopted in various downstream applications. The core strength of 3DGS lies in its efficient kernel-based scene representation, where Gaussian primitives provide…
Reliable autonomous driving relies on large-scale, well-labeled data and robust models. However, manual data collection is resource-intensive, and traditional simulation suffers from a persistent reality gap. While recent generative frameworks and radiance-field methods improve v…
As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emp…
arXiv:2605.02086v1 Announce Type: new Abstract: 3D Gaussian splatting (3DGS) is a state-of-the-art representation for real-time photorealistic novel-view synthesis, yet a single high-fidelity scene typically occupies hundreds of megabytes to several gigabytes, exceeding the budge…
The perception of an Autonomous Driving System (ADS) critically depends on relevant, comprehensive, and diverse datasets to ensure its safety while operating in the environment. Field data collection lacks completeness with respect to the list of rare but still possible safety-re…
3D Gaussian Splatting (3DGS) has been widely adopted for scene reconstruction, where training inherently constitutes a highly coupled and non-convex optimization problem. Recent works commonly incorporate geometric priors, such as LiDAR measurements, either for initialization or …
We propose WildSplatter, a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting conditions. 3DGS is an effective scene representation that enables high-quality, real-time rendering; however, it typically requ…
Generating a consistent whole-house VR tour from a floorplan and style reference requires both photorealistic panoramas and cross-view spatial coherence. Pure 2D generators produce appealing single panoramas but re-imagine geometry and materials when the viewpoint changes, wherea…
3D Gaussian Splatting (3DGS) has emerged as a leading representation for real-time novel view synthesis and been widely adopted in various downstream applications. The core strength of 3DGS lies in its efficient kernel-based scene representation, where Gaussian primitives provide…
Recent advances in 3D Gaussian Splatting (3DGS) have achieved remarkable success in high-fidelity Novel View Synthesis (NVS), yet the optimization process inevitably introduces noisy Gaussian primitives due to the sparse and incomplete initialization from Structure-from-Motion (S…
We present BlitzGS, a distributed 3DGS framework that reduces active Gaussian workload for fast city-scale reconstruction. BlitzGS manages this workload at three coupled levels. At the system level, the framework shards Gaussians across GPUs by index parity rather than spatial bl…
3D Language Gaussian Splatting (3DLGS) augments 3D Gaussian Splatting with language-aligned visual features for open-vocabulary 3D scene understanding. A core challenge is efficiently associating high-dimensional vision-language embeddings with millions of 3D Gaussians while pres…
Reliable autonomous driving relies on large-scale, well-labeled data and robust models. However, manual data collection is resource-intensive, and traditional simulation suffers from a persistent reality gap. While recent generative frameworks and radiance-field methods improve v…
Recent advances in 3D Gaussian Splatting (3DGS) have enabled significant progress in photorealistic novel view synthesis. However, traditional 3DGS relies on a slow, iterative optimization process, which limits its use in scenarios demanding real-time results. To overcome this bo…
Generalizable 3D Gaussian Splatting has recently emerged as an efficient approach for novel-view synthesis, enabling feed-forward synthesis from only a few input views. However, existing pixel-wise feed-forward methods suffer from over-bright renderings when the number of input v…
In-the-wild 3D Gaussian Splatting remains challenging due to transient distractors and illumination-induced cross-view appearance inconsistencies. Existing methods mainly rely on image-level masking to suppress unreliable supervision, but masking alone cannot fully eliminate resi…
3D Gaussian Splatting (3DGS) is becoming a practical representation for novel view synthesis, but its growing adoption, together with rapid advances in instruction-driven 3DGS editing, also exposes a dual copyright risk: once a 3DGS-based asset is released, it can be used without…
Surface reconstruction with differentiable rendering has achieved impressive performance in recent years, yet the pervasive photometric ambiguities have strictly bottlenecked existing approaches. This paper presents AmbiSuR, a framework that explores an intrinsic solution upon Ga…
Retrospective novel view synthesis (NVS) of dynamic scenes is fundamental to applications such as sports. Recent dynamic 3D Gaussian Splatting (3DGS) approaches introduce temporally coupled formulations to enforce motion coherence across time. In this paper, we argue that, in a s…
Dropout-based sparse-view 3D Gaussian Splatting (3DGS) methods alleviate overfitting by randomly suppressing Gaussian primitives during training. Existing methods mainly focus on designing increasingly sophisticated dropout strategies, while they overlook the resulting inconsiste…
Transmissive scenes are ubiquitous in daily life, yet reconstructing and rendering them remains highly challenging due to the inherent entanglement between near-field reflections from the surrounding environment on the transmissive surface, and the transmitted content of the scen…
arXiv:2605.05876v1 Announce Type: cross Abstract: We present 3D Surface Splatting (3DSS), the first differentiable surface splatting renderer for physically-based inverse rendering from multi-view images. Our central insight is that the surface separation problem at the heart of …
arXiv:2412.03077v2 Announce Type: replace Abstract: 4D reconstruction from casually captured monocular videos is challenging due to inherent ambiguity in reconstructing dynamic 3D geometry. To address this challenge, we introduce Robust Dynamic Gaussian Splatting (RoDyGS), a meth…
arXiv:2605.05155v1 Announce Type: new Abstract: As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existin…
arXiv:2605.04844v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as an advanced technique for real-time novel view synthesis by representing scene geometry and appearance using differentiable Gaussian primitives. However, efficiently computing precise Gaus…
arXiv cs.CV
TIER_1English(EN)·Binh Long Nguyen, Kien Nguyen, Sridha Sridharan, Clinton Fookes, Peyman Moghadam·
arXiv:2605.04506v1 Announce Type: new Abstract: We introduce Ilov3Splat, a novel framework for instance-level open-vocabulary 3D scene understanding built on 3D Gaussian Splatting (3D-GS). Most prior work depends on 2D rendering-based matching or point-level semantic association,…
arXiv:2601.00285v2 Announce Type: replace Abstract: Reconstructing a dynamic target moving over a large area is challenging. Standard approaches for dynamic object reconstruction require dense coverage in both the viewing space and the temporal dimension, typically relying on mul…
arXiv cs.CV
TIER_1English(EN)·Xuezhen Wang, Li Ma, Yulin Shen, Zeyu Wang, Pedro V. Sander·
arXiv:2603.13783v2 Announce Type: replace Abstract: Temporal retiming, the ability to reconstruct and render dynamic scenes at arbitrary timestamps, is crucial for applications such as slow-motion playback, temporal editing, and post-production. However, most existing 4D Gaussian…
As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emp…
3D Gaussian Splatting (3DGS) has emerged as an advanced technique for real-time novel view synthesis by representing scene geometry and appearance using differentiable Gaussian primitives. However, efficiently computing precise Gaussian-tile intersections remains a critical task …
We introduce Ilov3Splat, a novel framework for instance-level open-vocabulary 3D scene understanding built on 3D Gaussian Splatting (3D-GS). Most prior work depends on 2D rendering-based matching or point-level semantic association, which undermines cross-view consistency, lacks …
arXiv cs.CV
TIER_1English(EN)·Lucas Yunkyu Lee, Soonho Kim, Youngwook Kim, Sangmin Kim, Jaesik Park·
arXiv:2605.03337v1 Announce Type: new Abstract: The recent surge in 4D Gaussian Splatting (4DGS) has achieved impressive dynamic scene reconstruction. While these methods demonstrate remarkable performance, the specific drivers behind such gains remain less explored, making a sys…
arXiv:2605.01466v1 Announce Type: new Abstract: Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, yet we identify that standard hard projection severs …
arXiv cs.CV
TIER_1English(EN)·Shima Salehi, Atharva Agashe, Andrew J. McFarland, Joshua Peeples·
arXiv:2601.17185v2 Announce Type: replace Abstract: We propose a new method for few-shot 3D reconstruction that integrates global and local frequency regularization to stabilize geometry and preserve fine details under sparse-view conditions, addressing a key limitation of existi…
arXiv:2503.19703v3 Announce Type: replace Abstract: Highly accurate geometric precision and dense image features characterize True Digital Orthophoto Maps (TDOMs), which are in great demand for applications such as urban planning, infrastructure management, and environmental moni…
arXiv:2503.12001v4 Announce Type: replace Abstract: The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle wi…
arXiv:2411.18966v2 Announce Type: replace Abstract: Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to repre…
arXiv:2405.15491v4 Announce Type: replace Abstract: We present GSDeformer, a method that enables cage-based deformation on 3D Gaussian Splatting (3DGS). Our approach bridges cage-based deformation and 3DGS by using a proxy point-cloud representation. This point cloud is generated…
arXiv:2605.01995v1 Announce Type: new Abstract: The perception of an Autonomous Driving System (ADS) critically depends on relevant, comprehensive, and diverse datasets to ensure its safety while operating in the environment. Field data collection lacks completeness with respect …
The recent surge in 4D Gaussian Splatting (4DGS) has achieved impressive dynamic scene reconstruction. While these methods demonstrate remarkable performance, the specific drivers behind such gains remain less explored, making a systematic understanding of the underlying principl…
arXiv:2605.00408v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) has demonstrated impressive real-time rendering performance, its efficacy remains constrained by a reliance on heuristic density control. Despite numerous refinements to these handcrafted rules, su…
arXiv:2605.00052v1 Announce Type: new Abstract: Hybrid-capture novel view synthesis combines images at substantially different camera distances (e.g., aerial drone and ground-level views). Standard 3D Gaussian Splatting (3DGS), trained for 30K iterations with one rendered view pe…
arXiv cs.CV
TIER_1English(EN)·Prajwal Gupta C. R., Divyam Sheth, Jinjoo Ha, Mirela Ostrek, Justus Thies·
arXiv:2605.00569v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for generating photorealistic renderings of a scene in real-time. However, the volumetric nature of 3DGS limits its ability to accurately capture surface geometry. To …
arXiv:2605.00177v1 Announce Type: cross Abstract: We consider the problem of synthesizing photorealistic, physically plausible combustion effects in in-the-wild 3D scenes. Traditional CFD and graphics pipelines can produce realistic fire effects but rely on handcrafted geometry, …
arXiv:2511.12895v3 Announce Type: replace Abstract: High Dynamic Range (HDR) 3D reconstruction is pivotal for professional content creation in filmmaking and virtual production. Existing methods typically rely on multi-exposure Low Dynamic Range (LDR) supervision to constrain the…
arXiv:2508.04929v5 Announce Type: replace-cross Abstract: As a critical modality for structural biology, cryogenic electron microscopy (cryo-EM) facilitates the determination of macromolecular structures at near-atomic resolution. The core computational task in single-particle cr…
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for generating photorealistic renderings of a scene in real-time. However, the volumetric nature of 3DGS limits its ability to accurately capture surface geometry. To address this, 2D Gaussian Splatting (2DGS) was p…
While 3D Gaussian Splatting (3DGS) has demonstrated impressive real-time rendering performance, its efficacy remains constrained by a reliance on heuristic density control. Despite numerous refinements to these handcrafted rules, such methods inherently lack the flexibility to ad…
arXiv cs.CV
TIER_1English(EN)·Andrea Dunn Beltran, Daniel Rho, Aarav Mehta, Xinqi Xiong, Ra\'ul San Jos\'e Est\'epar, Ron Alterovitz, Marc Niethammer, Roni Sengupta·
arXiv:2604.28179v1 Announce Type: new Abstract: Bronchoscopic navigation relies on registering endoscopic video to a preoperative CT scan, but respiratory motion deforms the airway by 5-20 mm, creating CT-to-body divergence that limits localization accuracy. In practice, this is …
arXiv cs.CV
TIER_1English(EN)·Linjie Lyu, Ayush Tewari, Jianchun Chen, Thomas Leimk\"uhler, Christian Theobalt·
arXiv:2604.28016v1 Announce Type: new Abstract: 3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control relies on screen-space positional gradients, which do not distinguish between ge…
arXiv:2604.27552v1 Announce Type: new Abstract: While 3D Gaussian splatting (3DGS) offers explicit and efficient scene representations for cone-beam computed tomography reconstruction, conventional photometric optimization inherently suffers from spectral bias under ultra sparse-…
arXiv cs.CV
TIER_1English(EN)·Wongi Park, Jordan A. James, Myeongseok Nam, Minjae Lee, Soomok Lee, Sang-Hyun Lee, William J. Beksi·
arXiv:2604.27422v1 Announce Type: new Abstract: We propose a 3D novel sparse-view synthesis framework for unconstrained real-world scenarios that contain distractors. Unlike existing methods that primarily perform novel-view synthesis from a sparse set of constrained images witho…
arXiv cs.CV
TIER_1English(EN)·Boyang Tony Yu, Yanlin Jin, Yun He, Akshat Dave, Ravi Ramamoorthi, Guha Balakrishnan·
arXiv:2503.22676v5 Announce Type: replace Abstract: We present TranSplat, a method for instant, accurate object relighting within the Gaussian Splatting (GS) framework. Rather than relying on costly inverse rendering routines, we propose a BRDF-free radiance transfer strategy tha…
We consider the problem of synthesizing photorealistic, physically plausible combustion effects in in-the-wild 3D scenes. Traditional CFD and graphics pipelines can produce realistic fire effects but rely on handcrafted geometry, expert-tuned parameters, and labor-intensive workf…
Bronchoscopic navigation relies on registering endoscopic video to a preoperative CT scan, but respiratory motion deforms the airway by 5-20 mm, creating CT-to-body divergence that limits localization accuracy. In practice, this is mitigated through breath-hold protocols, which a…
3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control relies on screen-space positional gradients, which do not distinguish between geometric misplacement and frequency aliasing, oft…
While 3D Gaussian splatting (3DGS) offers explicit and efficient scene representations for cone-beam computed tomography reconstruction, conventional photometric optimization inherently suffers from spectral bias under ultra sparse-view conditions, leading to over-smoothing and a…
We propose a 3D novel sparse-view synthesis framework for unconstrained real-world scenarios that contain distractors. Unlike existing methods that primarily perform novel-view synthesis from a sparse set of constrained images without transient elements or leverage unconstrained …
arXiv:2604.16747v2 Announce Type: replace Abstract: Dynamic 3D Gaussian Splatting methods achieve strong training-view PSNR on monocular video but generalize poorly: on the D-NeRF benchmark we measure an average train-test PSNR gap of 6.18 dB, rising to 11 dB on individual scenes…
arXiv:2604.26799v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-training compression methods still rely on many coupl…
arXiv cs.CV
TIER_1English(EN)·Rui Song, Tianhui Cai, Markus Gross, Yun Zhang, Walter Zimmer, Zhiyu Huang, Olaf Wysocki, Jiaqi Ma·
arXiv:2604.26238v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has been widely adopted for scene reconstruction, where training inherently constitutes a highly coupled and non-convex optimization problem. Recent works commonly incorporate geometric priors, such as L…
3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-training compression methods still rely on many coupled hyperparameters across pruning, transformatio…
arXiv cs.CV
TIER_1English(EN)·Jingi Kim, Wonjun Kim·
arXiv:2604.25466v1 Announce Type: new Abstract: Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural represe…
arXiv cs.CV
TIER_1English(EN)·Michele Grimaldi, David Nakath, Oscar Pizarro, Jonatan Scharff Willners, Ignacio Carlucho, Yvan R. Petillot·
arXiv:2604.19133v2 Announce Type: replace Abstract: Robust 3D reconstruction across varying environmental conditions remains a critical challenge for robotic perception, particularly when transitioning between air and water. To address this, we introduce BALTIC, a controlled benc…
arXiv:2511.07743v3 Announce Type: replace Abstract: Ultrasound imaging is a cornerstone of non-invasive clinical diagnostics, yet its limited field of view poses challenges for novel view synthesis. We present UltraGS, a real-time framework that adapts Gaussian Splatting to senso…
3D Gaussian Splatting (3DGS) has been widely adopted for scene reconstruction, where training inherently constitutes a highly coupled and non-convex optimization problem. Recent works commonly incorporate geometric priors, such as LiDAR measurements, either for initialization or …
Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural representations to accurately position 3D Gaussians. Al…
arXiv:2511.17092v4 Announce Type: replace Abstract: Articulated objects are ubiquitous in daily environments, and their 3D reconstruction holds great significance across various fields. However, existing articulated object reconstruction methods typically require costly inputs su…
arXiv:2604.23803v1 Announce Type: new Abstract: Egocentric video provides a unique view into human perception and interaction, with growing relevance for augmented reality, robotics, and assistive technologies. However, rapid camera motion and complex scene dynamics pose major ch…
arXiv:2604.23551v1 Announce Type: new Abstract: Reconstructing realistic underwater scenes from underwater video remains a meaningful yet challenging task in the multimedia domain. The inherent spatiotemporal degradations in underwater imaging, including caustics, flickering, att…
arXiv:2604.23675v1 Announce Type: cross Abstract: This work presents GS-DOT, a novel image reconstruction framework based on Gaussian Splatting (GS) for diffuse optical tomography (DOT). Inspired by GS for rendering applications, absorption coefficients are represented as a spars…
arXiv cs.CV
TIER_1English(EN)·Daniel Wang, Patrick Rim, Tian Tian, Dong Lao, Alex Wong, Ganesh Sundaramoorthi·
arXiv:2506.05480v4 Announce Type: replace-cross Abstract: We introduce ODE-GS, a novel approach that integrates 3D Gaussian Splatting with latent neural ordinary differential equations (ODEs) to enable future extrapolation of dynamic 3D scenes. Unlike existing dynamic scene recon…
arXiv:2604.20046v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has revolutionized novel view synthesis with high-quality rendering through continuous aggregations of millions of 3D Gaussian primitives. However, it suffers from a substantial memory footprint, par…
arXiv:2604.22439v1 Announce Type: new Abstract: We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features, in order to obtain an accurate and robust 3D semantic Gaussian Splatting. The 2D features ex…
arXiv cs.CV
TIER_1English(EN)·Feiyu An, Yufei Deng, Zihui Zhang, Rong Xiao·
arXiv:2604.22183v1 Announce Type: new Abstract: Achieving sharp 3D reconstruction from motion-blurred images alone becomes challenging, motivating recent methods to incorporate event cameras, benefiting from microsecond temporal resolution. However, they suffer from residual arti…
arXiv cs.CV
TIER_1English(EN)·David Recasens, Robert Maier, Aljaz Bozic, Stephane Grabli, Javier Civera, Tony Tung, Edmond Boyer·
arXiv:2604.22129v1 Announce Type: new Abstract: Gaussian Splatting (GS) has emerged as an efficient approach for high-quality novel view synthesis. While early GS variants struggled to accurately model the scene's geometry, recent advancements constraining the Gaussians' spread a…
We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features, in order to obtain an accurate and robust 3D semantic Gaussian Splatting. The 2D features extracted from vision foundation models suffer fro…
Achieving sharp 3D reconstruction from motion-blurred images alone becomes challenging, motivating recent methods to incorporate event cameras, benefiting from microsecond temporal resolution. However, they suffer from residual artifacts and blurry texture details due to misleadi…
Gaussian Splatting (GS) has emerged as an efficient approach for high-quality novel view synthesis. While early GS variants struggled to accurately model the scene's geometry, recent advancements constraining the Gaussians' spread and shapes, such as 2D Gaussian Splatting, have s…
While 3D Gaussian Splatting (3DGS) achieves real-time photorealistic rendering, its performance degrades significantly when training images contain transient objects that violate multi-view consistency. Existing methods face a circular dependency: accurate transient detection req…
We propose WildSplatter, a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting conditions. 3DGS is an effective scene representation that enables high-quality, real-time rendering; however, it typically requ…
