7 papers · 1 filter
ICTPolarReal: A Polarized Reflection and Material Dataset of Real World Objects
Jing Yang, Krithika Dharanikota, Emily Jia +2
Accurately modeling how real-world materials reflect light remains a core challenge in inverse rendering, largely due to the scarcity of real measured reflectance data. Existing ap…
DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation
Junyi Ouyang, Wenbin Teng, Gonglin Chen +2
Long-trajectory video generation is a crucial yet challenging task for world modeling primarily due to the limited scalability of existing video diffusion models (VDMs). Autoregres…
ARSS: Taming Decoder-only Autoregressive Visual Generation for View Synthesis From Single View
Wenbin Teng, Gonglin Chen, Haiwei Chen +1
Diffusion models have achieved impressive results in world modeling tasks, including novel view generation from sparse inputs. However, most existing diffusion-based NVS methods ge…
FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation
Wenbin Teng, Gonglin Chen, Haiwei Chen +1
Recent progress in 3D reconstruction has enabled realistic 3D models from dense image captures, yet challenges persist with sparse views, often leading to artifacts in unseen areas…
RDD: Robust Feature Detector and Descriptor using Deformable Transformer
Gonglin Chen, Tianwen Fu, Haiwei Chen +3
As a core step in structure-from-motion and SLAM, robust feature detection and description under challenging scenarios such as significant viewpoint changes remain unresolved despi…
Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation
Yunxuan Cai, Sitao Xiang, Zongjian Li +2
Digital modeling and reconstruction of human faces serve various applications. However, its availability is often hindered by the requirements of data capturing devices, manual lab…