Related papers: FLAG-4D: Flow-Guided Local-Global Dual-Deformation…
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,…
Egocentric video is crucial for next-generation 4D scene reconstruction, with applications in AR/VR and embodied AI. However, reconstructing dynamic first-person scenes is challenging due to complex ego-motion, occlusions, and hand-object…
Recently, the generation of dynamic 3D objects from a video has shown impressive results. Existing methods directly optimize Gaussians using whole information in frames. However, when dynamic regions are interwoven with static regions…
Fluid deformation and strain history are central to wide range of fluid mechanical phenomena ranging from fluid mixing and particle transport to stress development in complex fluids and the formation of Lagrangian coherent structures…
We present Orientation-anchored Gaussian Splatting (OriGS), a novel framework for high-quality 4D reconstruction from casually captured monocular videos. While recent advances extend 3D Gaussian Splatting to dynamic scenes via various…
4D Gaussian Splatting (4DGS) has recently gained considerable attention as a method for reconstructing dynamic scenes. Despite achieving superior quality, 4DGS typically requires substantial storage and suffers from slow rendering speed. In…
Understanding dynamic scenes from casual videos is critical for scalable robot learning, yet four-dimensional (4D) reconstruction under strictly monocular settings remains highly ill-posed. To address this challenge, our key insight is that…
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 per-scene…
The advancement of 4D (i.e., sequential 3D) generation opens up new possibilities for lifelike experiences in various applications, where users can explore dynamic objects or characters from any viewpoint. Meanwhile, video generative models…
3D Gaussian Splatting (3DGS) has revolutionized 3D scene reconstruction, which effectively balances rendering quality, efficiency, and speed. However, existing 3DGS approaches usually generate plausible outputs and face significant…
Recent methods have made significant progress in synthesizing novel views with long video sequences. This paper proposes a highly scalable method for dynamic novel view synthesis with continual learning. We leverage the 3D Gaussians to…
In the literature, it has been shown that the evolution of the known explicit 3D surface to the target one can be learned from 2D images using the instantaneous flow field, where the known and target 3D surfaces may largely differ in…
Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to…
Dense 4D reconstruction from unposed images remains a critical challenge, with current methods relying on slow test-time optimization or fragmented, task-specific feedforward models. We introduce UFO-4D, a unified feedforward framework to…
We propose a method to reconstruct dynamic fire in 3D from a limited set of camera views with a Gaussian-based spatiotemporal representation. Capturing and reconstructing fire and its dynamics is highly challenging due to its volatile…
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…
Feed-forward 3D reconstruction for autonomous driving has advanced rapidly, yet existing methods struggle with the joint challenges of sparse, non-overlapping camera views and complex scene dynamics. We present UniSplat, a general…
Reconstructing dynamic driving scenes is essential for developing autonomous systems through sensor-realistic simulation. Although recent methods achieve high-fidelity reconstructions, they either rely on costly human annotations for object…
Real-time reconstruction of dynamic 3D scenes from uncalibrated video streams demands robust online methods that recover scene dynamics from sparse observations under strict latency and memory constraints. Yet most dynamic reconstruction…
Endoscopic surgery relies on intraoperative video, making image quality a decisive factor for surgical safety and efficacy. Yet, endoscopic videos are often degraded by uneven illumination, tissue scattering, occlusions, and motion blur,…