arXiv Computer Vision
ChronoFuseGS: Multi-Temporal Gaussian Fusion with Per-Splat Persistence and Change Visualization
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
3d ago
EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis
arXiv:2601.15951v2 Announce Type: replace Abstract: Novel view synthesis (NVS) of static and dynamic urban scenes is essential for autonomous driving simulation, yet existing methods often struggle t...
Hugging Face Trending Papers
Jul 20
AniGS: Bridging Rendering and Diffusion Prior for 3D Scene Animation
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.
arXiv Computer Vision
5d ago
Holo-World: Unified Camera, Object and Weather Control for Video World Model
arXiv:2606.20083v4 Announce Type: replace Abstract: Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental stat...
arXiv AI
Jun 2
A Survey of 3D Reconstruction with Event Cameras
arXiv:2505. 08438v4 Announce Type: replace-cross Abstract: Event cameras are rapidly emerging as powerful vision sensors for 3D reconstruction, uniquely capable of asynchronously capturing per-pixel brightness changes.
arXiv Machine Learning
Jul 23
SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery
arXiv:2603. 18634v3 Announce Type: replace-cross Abstract: Rapid, large-scale 3D reconstruction from multi-date satellite imagery is vital for environmental monitoring, urban planning, and disaster response, yet remains difficult due to illumination changes, sensor heterogeneity, and the cost of per-scene optimization.
arXiv AI
Sep 10
WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting
WildRelight is the first in-the-wild dataset designed to evaluate single-image relighting models, featuring high-resolution outdoor scenes captured under strictly aligned, temporally varying natural illuminations paired with high-dynamic-range environment maps. The benchmark demonstrates that state-of-the-art models trained on synthetic data suffer severe domain shifts when applied to real-world imagery. Leveraging the dataset’s temporal structure, the authors introduce a physics-guided inference framework combining Diffusion Posterior Sampling with Temporal Sampling-Aware Test-Time Adaptation, enabling synthetic models to self-supervise and align with real-world statistics on-the-fly.