3 papers
cs.CV2026
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
Cao Duy, Phong Nguyen-Ha
Recent advances in 3D content generation from text or images have achieved impressive results, yet view inconsistency from 2D generators and the scarcity of high-quality 3D data re…
cs.CV2026
Track the Noise, Move the World:3D-Grounded Motion-Consistent Noise for Controllable Video Generation
Long Vu, Tan Ngo, Animesh Karnewar +5
Modern image-and-text-to-video diffusion models can synthesize highly realistic videos by iteratively denoising an initial Gaussian noise tensor conditioned on reference image and…
cs.CV2025
An End-to-End Depth-Based Pipeline for Selfie Image Rectification
Ahmed Alhawwary, Janne Mustaniemi, Phong Nguyen-Ha +1
Portraits or selfie images taken from a close distance typically suffer from perspective distortion. In this paper, we propose an end-to-end deep learning-based rectification pipel…