collaborators

7 papers

cs.GR2026

Generative Motion In-betweening by Diffusion over Continuous Implicit Representations

Shiyu Fan, Paul Henderson, Edmond S. L. Ho

Recent advances in generative models have yielded impressive progress on motion in-betweening, allowing for more complex, varied, and realistic motion transitions. However, recent…

cs.CV2025

A Convolutional Neural Deferred Shader for Physics Based Rendering

Zhuo He, Yingdong Ru, Qianying Liu +2

Recent advances in neural rendering have achieved impressive results on photorealistic shading and relighting, by using a multilayer perceptron (MLP) as a regression model to learn…

cs.CV2025

ReMatch: Boosting Representation through Matching for Multimodal Retrieval

Qianying Liu, Xiao Liang, Zhiqiang Zhang +6

We present ReMatch, a framework that leverages the generative strength of MLLMs for multimodal retrieval. Previous approaches treated an MLLM as a simple encoder, ignoring its gene…

cs.CV2025

Flow and Depth Assisted Video Prediction with Latent Transformer

Eliyas Suleyman, Paul Henderson, Eksan Firkat +1

Video prediction is a fundamental task for various downstream applications, including robotics and world modeling. Although general video prediction models have achieved remarkable…

cs.CV2025

Beyond Reconstruction: A Physics Based Neural Deferred Shader for Photo-realistic Rendering

Zhuo He, Paul Henderson, Nicolas Pugeault

Deep learning based rendering has achieved major improvements in photo-realistic image synthesis, with potential applications including visual effects in movies and photo-realistic…

cs.CV2025

Generative Fields: Uncovering Hierarchical Feature Control for StyleGAN via Inverted Receptive Fields

Zhuo He, Paul Henderson, Nicolas Pugeault

StyleGAN has demonstrated the ability of GANs to synthesize highly-realistic faces of imaginary people from random noise. One limitation of GAN-based image generation is the diffic…