Related papers: Versatile Video Tokenization with Generative 2D Ga…

Implicit Neural Representations (INRs) employ neural networks to approximate discrete data as continuous functions. In the context of video data, such models can be utilized to transform the coordinates of pixel locations along with frame…

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 with moving…

3D Gaussian Splatting (GS) has emerged as a powerful representation for high-quality scene reconstruction, offering compelling rendering quality. However, the training process of GS often suffers from slow convergence due to inefficient…

Novel view synthesis of dynamic scenes has been an intriguing yet challenging problem. Despite recent advancements, simultaneously achieving high-resolution photorealistic results, real-time rendering, and compact storage remains a…

We propose a method to enhance 3D Gaussian Splatting (3DGS)~\cite{Kerbl2023}, addressing challenges in initialization, optimization, and density control. Gaussian Splatting is an alternative for rendering realistic images while supporting…

Leveraging text, images, structure maps, or motion trajectories as conditional guidance, diffusion models have achieved great success in automated and high-quality video generation. However, generating smooth and rational transition videos…

Although 3D Gaussian Splatting (3D-GS) achieves efficient rendering for novel view synthesis, extending it to dynamic scenes still results in substantial memory overhead from replicating Gaussians across frames. To address this challenge,…

Tensor singular value decomposition (t-SVD) is a promising tool for multi-dimensional image representation, which decomposes a multi-dimensional image into a latent tensor and an accompanying transform matrix. However, two critical…

We introduce GS2E (Gaussian Splatting to Event), a large-scale synthetic event dataset for high-fidelity event vision tasks, captured from real-world sparse multi-view RGB images. Existing event datasets are often synthesized from dense RGB…

3D Gaussian Splatting (3DGS) has emerged as a powerful representation due to its efficiency and high-fidelity rendering. 3DGS training requires a known camera pose for each input view, typically obtained by Structure-from-Motion (SfM)…

Implicit neural representations for video have been recognized as a novel and promising form of video representation. Existing works pay more attention to improving video reconstruction quality but little attention to the decoding speed.…

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…

We propose HoliGS, a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos. Unlike prior 4D Gaussian splatting and dynamic NeRF pipelines, which struggle with training overhead…

Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, manifesting efficient and high-fidelity novel view synthesis. However, accurately representing surfaces, especially in large and complex scenarios,…

Modeling dynamic, large-scale urban scenes is challenging due to their highly intricate geometric structures and unconstrained dynamics in both space and time. Prior methods often employ high-level architectural priors, separating static…

Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject…

3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…

Reconstructing static 3D scene from monocular video with dynamic objects is important for numerous applications such as virtual reality and autonomous driving. Current approaches typically rely on background for static scene reconstruction,…

In this work, we revisit several key design choices of modern Transformer-based approaches for feed-forward 3D Gaussian Splatting (3DGS) prediction. We argue that the common practice of regressing Gaussian means as depths along camera rays…

While the generation of 3D content from single-view images has been extensively studied, the creation of physically consistent 3D dynamic scenes from videos remains in its early stages. We propose a novel framework leveraging generative 3D…