SplashSplat introduces a new benchmark of 20 real-world splashing liquid scenes captured with seven synchronized 4K cameras at 60 fps, providing per-view liquid and container masks and fixed evaluation splits. The method reconstructs per‑frame liquid signed distance fields (SDFs) from these masks, fuses them into a coarse velocity field, and uses Lagrangian carriers to generate differentiable local Gaussian representations for rendering. SplashSplat outperforms existing dynamic Gaussian splatting techniques on both real and synthetic data, offering more physically plausible motion, lower training cost, and enabling temporal interpolation and style transfer without re‑optimization.
arXiv:2607. 25321v1 Announce Type: new Abstract: Video diffusion models generate visually compelling content but routinely violate elementary physics when the subject involves fluids: liquid columns break apart in mid-air, container water levels fail to rise as liquid is poured in, and splashes disperse without regard to momentum or gravity.
arXiv:2608.22906v1 Announce Type: new Abstract: Recent monocular 3D Gaussian Splatting (3DGS) streaming reconstruction methods have achieved impressive performance by balancing reconstruction quality...
arXiv:2608.21828v1 Announce Type: new Abstract: Novel-view synthesis of dynamic scenes, crucial for AR/VR applications, remains a challenging problem. Recent methods adapt representations like 3D Gau...
Recent monocular 3D Gaussian Splatting (3DGS) streaming reconstruction methods have achieved impressive performance by balancing reconstruction quality and efficiency. However, extending these framewo...
Novel view rendering of large and complex reconstructed scenes is becoming increasingly photorealistic. However, most reconstructions remain static and lack the ambient motion that makes environments immersive.
Reconstructing photorealistic scenes in unconstrained underwater environments remains challenging due to severe media-induced light scattering and unpredictable dynamic objects. Recent feed-forward vi...
arXiv:2606. 16278v1 Announce Type: cross Abstract: Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect and reproduce at scale.
The paper introduces TruncGradGS, a piecewise truncated gradient approach that mitigates gradient vanishing in 3D Gaussian Splatting, enhancing optimization stability and robustness to initializations. It demonstrates consistent improvements over random and COLMAP initializations in both static and dynamic settings. Additionally, the authors highlight limitations of existing dynamic scene benchmarks and present a new synthetic dataset for evaluating dynamic Gaussian Splatting.
Camera intrinsics are vital for recovering 3D structure from 2D video. However, most 3D algorithms assume fixed intrinsics throughout a video, an assumption that often fails for real-world in-the-wild videos.
arXiv:2608.22888v1 Announce Type: new Abstract: Reconstructing photorealistic scenes in unconstrained underwater environments remains challenging due to severe media-induced light scattering and unpr...
arXiv:2607. 20628v1 Announce Type: cross Abstract: Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data, yet robust restoration is critical for downstream pipelines such as mobile imaging and 3D reconstruction.
arXiv:2503. 04500v3 Announce Type: replace-cross Abstract: Video understanding has largely relied on deep spatiotemporal architectures, including 3D convolutional networks and optical flow (OF) based models.