11 papers · 1 filter
Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories
Merve Kocabas, Gege Gao, Bernhard Schölkopf +1
Diffusion and flow-based generative models produce strong images, yet their controllability remains largely endpoint-centric: users specify conditions and receive final outputs, wh…
Ultra-lightweight Neural Video Representation Compression
Ho Man Kwan, Tianhao Peng, Ge Gao +4
Recent works have demonstrated the viability of utilizing over-fitted implicit neural representations (INRs) as alternatives to autoencoder-based models for neural video compressio…
View-Consistent Diffusion Representations for 3D-Consistent Video Generation
Duolikun Danier, Ge Gao, Steven McDonagh +3
Video generation models have made significant progress in generating realistic content, enabling applications in simulation, gaming, and film making. However, current generated vid…
GFix: Perceptually Enhanced Gaussian Splatting Video Compression
Siyue Teng, Ge Gao, Duolikun Danier +5
3D Gaussian Splatting (3DGS) enhances 3D scene reconstruction through explicit representation and fast rendering, demonstrating potential benefits for various low-level vision task…
ViVo: A Dataset for Volumetric Video Reconstruction and Compression
Adrian Azzarelli, Ge Gao, Ho Man Kwan +4
As research on neural volumetric video reconstruction and compression flourishes, there is a need for diverse and realistic datasets, which can be used to develop and validate reco…
Instance Data Condensation for Image Super-Resolution
Tianhao Peng, Ho Man Kwan, Yuxuan Jiang +5
Deep learning based Image Super-Resolution (ISR) relies on large training datasets to optimize model generalization; this requires substantial computational and storage resources d…