5 papers
Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs
Bao Tang, Shuai Zhang, Yueting Zhu +5
Timestep distillation is an effective approach for improving the generation efficiency of diffusion models. The Consistency Model (CM), as a trajectory-based framework, demonstrate…
DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance
Jijun Xiang, Longliang Liu, Xuan Zhu +3
Depth enhancement, which converts raw dToF signals into dense depth maps using RGB guidance, is crucial for improving depth perception in high-precision tasks such as 3D reconstruc…
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image
Jijun Xiang, Xuan Zhu, Xianqi Wang +4
Depth enhancement, which uses RGB images as guidance to convert raw signals from dToF into high-precision, dense depth maps, is a critical task in computer vision. Although existin…
PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View
Longliang Liu, Miaojie Feng, Junda Cheng +3
Panoramic optical flow enables a comprehensive understanding of temporal dynamics across wide fields of view. However, severe distortions caused by sphere-to-plane projections, suc…
SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
Xuan Zhu, Jijun Xiang, Xianqi Wang +5
Lightweight direct Time-of-Flight (dToF) sensors are ideal for 3D sensing on mobile devices. However, due to the manufacturing constraints of compact devices and the inherent physi…