Related papers: Resonance4D: Frequency-Domain Motion Supervision f…
3D Gaussian splatting (3DGS) is an innovative rendering technique that surpasses the neural radiance field (NeRF) in both rendering speed and visual quality by leveraging an explicit 3D scene representation. Existing 3DGS approaches require…
We present a framework that enables fast reconstruction and real-time rendering of urban-scale scenes while maintaining robustness against appearance variations across multi-view captures. Our approach begins with scene partitioning for…
Motion segmentation in dynamic scenes is highly challenging, as conventional methods heavily rely on estimating camera poses and point correspondences from inherently noisy motion cues. Existing statistical inference or iterative…
We tackle the task of learning dynamic 3D semantic radiance fields given a single monocular video as input. Our learned semantic radiance field captures per-point semantics as well as color and geometric properties for a dynamic 3D scene,…
Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors often break down in highly dynamic regions where multi-view…
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, where…
3D Gaussian Splatting (3DGS) enables high-quality rendering of 3D scenes and is getting increasing adoption in domains like autonomous driving and embodied intelligence. However, 3DGS still faces major efficiency challenges when faced with…
Recent advances in video diffusion models have enabled the generation of high-quality videos. However, these videos still suffer from unrealistic deformations, semantic violations, and physical inconsistencies that are largely rooted in the…
Real-time reconstruction of deformable surgical scenes is vital for advancing robotic surgery, improving surgeon guidance, and enabling automation. Recent methods achieve dense reconstructions from da Vinci robotic surgery videos, with…
Reconstructing dynamic 3D scenes from blurry monocular videos is challenging as motion-induced blur entangles object motion and geometry, hindering geometric consistency. We present Kinematics-GS, a kinematics-aware framework that models…
Dynamic scene reconstruction from monocular video is essential for real-world applications. We introduce DGNS, a hybrid framework integrating \underline{D}eformable \underline{G}aussian Splatting and Dynamic \underline{N}eural…
Recent advancements in high-fidelity dynamic scene reconstruction have leveraged dynamic 3D Gaussians and 4D Gaussian Splatting for realistic scene representation. However, to make these methods viable for real-time applications such as…
3D Gaussians, as a low-level scene representation, typically involve thousands to millions of Gaussians. This makes it difficult to control the scene in ways that reflect the underlying dynamic structure, where the number of independent…
Current 4D Gaussian frameworks for dynamic scene reconstruction deliver impressive visual fidelity and rendering speed, however, the inherent trade-off between storage costs and the ability to characterize complex physical motions…
Recent advances in 4D Gaussian Splatting (4DGS) editing still face challenges with view, temporal, and non-editing region consistency, as well as with handling complex text instructions. To address these issues, we propose 4DGS-Craft, a…
Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization. A key challenge lies in finding an…
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…
High-resolution Magnetic Resonance Imaging (MRI) is vital for clinical diagnosis but limited by long acquisition times and motion artifacts. Super-resolution (SR) reconstructs low-resolution scans into high-resolution images, yet existing…
We introduce SirenPose, a geometry-aware loss formulation that integrates the periodic activation properties of sinusoidal representation networks with keypoint-based geometric supervision, enabling accurate and temporally consistent…
Free-Viewpoint Video (FVV) enables immersive 3D experiences, but efficient compression of dynamic 3D representation remains a major challenge. Existing dynamic 3D Gaussian Splatting methods couple reconstruction with optimization-dependent…