6 papers
ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling
Chirag Vashist, Ke Li
Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching. Along the way, the underlying techniques have become more complicated and…
One Pass Is Not Enough: Recursive Latent Refinement for Generative Models
Mehdi Esmaeilzadeh, Alexia Jolicoeur-Martineau, Chirag Vashist +1
Despite remarkable progress, image generation is far from solved. The dominant metric, FID, conflates sample fidelity with mode coverage and is close to being saturated. Yet a mode…
Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion
Junru Lin, Chirag Vashist, Mikaela Angelina Uy +4
Existing dynamic scene interpolation methods typically assume that the motion between consecutive timesteps is small enough so that displacements can be locally approximated by lin…
Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis
Chirag Vashist, Shichong Peng, Ke Li
An emerging area of research aims to learn deep generative models with limited training data. Prior generative models like GANs and diffusion models require a lot of data to perfor…
Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering
Alireza Moazeni, Shichong Peng, Yanshu Zhang +2
Recent point-based intrinsic decomposition and inverse rendering methods have advanced the modelling of the shading and albedo of 3D scenes. However, we identify a fundamental limi…
IHashNet: Iris Hashing Network based on efficient multi-index hashing
Avantika Singh, Chirag Vashist, Pratyush Gaurav +2
Massive biometric deployments are pervasive in today's world. But despite the high accuracy of biometric systems, their computational efficiency degrades drastically with an increa…