5 papers
The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge
Haoru Wang, Kai Ye, Minghan Qin +3
Recent advances in feed-forward Novel View Synthesis (NVS) have led to a divergence between two design philosophies: bias-driven methods, which rely on explicit 3D knowledge, such…
From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images
Fei Yu, Yu Liu, Luyang Tang +10
City-scale 3D reconstruction from satellite imagery presents the challenge of extreme viewpoint extrapolation, where our goal is to synthesize ground-level novel views from sparse…
CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting
Zhigang Cheng, Mingchao Sun, Yu Liu +5
Level of Detail (LoD) is a fundamental technique in real-time computer graphics for managing the rendering costs of complex scenes while preserving visual fidelity. Traditionally,…
PointCNN++: Performant Convolution on Native Points
Lihan Li, Haofeng Zhong, Rui Bu +4
Existing convolutional learning methods for 3D point cloud data are divided into two paradigms: point-based methods that preserve geometric precision but often face performance cha…
Value-State Gated Attention for Mitigating Extreme-Token Phenomena in Transformers
Rui Bu, Haofeng Zhong, Wenzheng Chen +1
Large models based on the Transformer architecture are susceptible to extreme-token phenomena, such as attention sinks and value-state drains. These issues, which degrade model per…