collaborators

6 papers

cs.CV2026

Geometric Reciprocity: Unlocking Self-Supervision for Stereoscopic Video Generation

Jingyi Lu, Kai Han

Monocular-to-stereo conversion synthesizes stereoscopic content from 2D videos for immersive 3D experiences. In modern Depth-Image-Based Rendering (DIBR) approaches, stereo inpaint…

cs.CV2026

Semantic Correspondence: Unified Benchmarking and a Strong Baseline

Kaiyan Zhang, Xinghui Li, Jingyi Lu +1

Establishing semantic correspondence is a challenging task in computer vision, aiming to match keypoints with the same semantic information across different images. Benefiting from…

cs.CV2026

SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers

Minghao Yin, Jiahao Lu, Wenbo Hu +3

Video diffusion transformers address their tokens by position on the pixel-time grid: an address in the tensor, not in the world. The address we would want, the world point a token…

cs.GR2026

Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats

Xiaoyang Liu, Shangzhe Wu, Kai Han

3D Gaussian Splatting (3DGS) has achieved state-of-the-art photorealistic rendering, but the representation gap prevents these assets from being physically interactive. Production-…

cs.CV2026

VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation

Yan Luo, Ahmadou Aidara, Jingyi Lu +3

Classifier-free guidance (CFG) is the primary control over how strongly text semantics move a flow-based sampler, yet standard practice holds its scale fixed across the entire ODE…

cs.CV2025

Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping

Jingyi Lu, Kai Han

Drag-based image editing has emerged as a powerful paradigm for intuitive image manipulation. However, existing approaches predominantly rely on manipulating the latent space of ge…