Search Results for author:
Found 11 papers, 7 papers with code
MusicInfuser: Making Video Diffusion Listen and Dance
We introduce MusicInfuser, an approach for generating high-quality dance videos that are synchronized to a specified music track.
Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories
Combined with the generative process, we impose identity-preserving gradients to refine the edited NeRF.
Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
Our contributions include: (1) introducing STG as an efficient, high-performing guidance technique for video diffusion models, (2) eliminating the need for auxiliary models by simulating a weak model through layer skipping, and (3) ensuring quality-enhanced guidance without compromising sample diversity or dynamics unlike CFG.
Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention
Recent attempts to extend guidance to unconditional models have relied on heuristic techniques, resulting in suboptimal generation quality and unintended effects.
Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting
3D reconstruction from multi-view images is one of the fundamental challenges in computer vision and graphics.
Retrieval-Augmented Score Distillation for Text-to-3D Generation
We leverage the retrieved asset to incorporate its geometric prior in the variational objective and adapt the diffusion model's 2D prior toward view consistency, achieving drastic improvements in both geometry and fidelity of generated scenes.
DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation
In the paradigm of AI-generated content (AIGC), there has been increasing attention to transferring knowledge from pre-trained text-to-image (T2I) models to text-to-video (T2V) generation.
Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation
In this work, we explore existing frameworks for score-distilling text-to-3D generation and identify the main causes of the view inconsistency problem -- the embedded bias of 2D diffusion models.
DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Models
Generative models have recently undergone significant advancement due to the diffusion models.
Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters.
