A neural particle dynamics model is trained on real videos using dense Gaussians and rendering supervision, without particle-level labels, plus a new dataset of about 500 videos.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Realiz3D decouples visual domain from 3D controls in diffusion models via domain-aware residual adapters to enable photorealistic controllable generation.
FlashLips delivers 100+ FPS mask-free lip-sync by reconstructing target frames in latent space from an audio-predicted lips-pose vector using a compact U-Net trained solely on reconstruction losses and self-supervised mask removal.
IR-Flow uses rectified flow to build linear transport between degraded and clean images via multilevel flows and cumulative velocity fields, enabling competitive restoration quality with only a few sampling steps.
citing papers explorer
-
Learning a Particle Dynamics Model with Real-world Videos
A neural particle dynamics model is trained on real videos using dense Gaussians and rendering supervision, without particle-level labels, plus a new dataset of about 500 videos.
-
Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning
Realiz3D decouples visual domain from 3D controls in diffusion models via domain-aware residual adapters to enable photorealistic controllable generation.
-
FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs
FlashLips delivers 100+ FPS mask-free lip-sync by reconstructing target frames in latent space from an audio-predicted lips-pose vector using a compact U-Net trained solely on reconstruction losses and self-supervised mask removal.
-
IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow
IR-Flow uses rectified flow to build linear transport between degraded and clean images via multilevel flows and cumulative velocity fields, enabling competitive restoration quality with only a few sampling steps.