3 papers
cs.CV2025
SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations
Songchun Zhang, Huiyao Xu, Sitong Guo +4
Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting…
cs.CV2025
LL-Gaussian: Low-Light Scene Reconstruction and Enhancement via Gaussian Splatting for Novel View Synthesis
Hao Sun, Fenggen Yu, Huiyao Xu +2
Novel view synthesis (NVS) in low-light scenes remains a significant challenge due to degraded inputs characterized by severe noise, low dynamic range (LDR) and unreliable initiali…
cs.CV2024
Learning Novel View Synthesis from Heterogeneous Low-light Captures
Quan Zheng, Hao Sun, Huiyao Xu +1
Neural radiance field has achieved fundamental success in novel view synthesis from input views with the same brightness level captured under fixed normal lighting. Unfortunately,…