6 papers
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…
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…
Mind-to-Face: Neural-Driven Photorealistic Avatar Synthesis via EEG Decoding
Haolin Xiong, Tianwen Fu, Pratusha Bhuvana Prasad +5
Current expressive avatar systems rely heavily on visual cues, failing when faces are occluded or when emotions remain internal. We present Mind-to-Face, the first framework that d…
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…
Geometry-Aware Feature Matching for Large-Scale Structure from Motion
Gonglin Chen, Jinsen Wu, Haiwei Chen +5
Establishing consistent and dense correspondences across multiple images is crucial for Structure from Motion (SfM) systems. Significant view changes, such as air-to-ground with ve…