8 papers · 1 filter
Speculative Forcing for Efficient Autoregressive Video Generation
Hyunwook Choi, Seungryong Kim, Dongyoon Han +1
Few-step autoregressive video generators enable streaming generation, yet they run every token through the final denoising step, regardless of how much refinement it needs. We find…
CORAL: Correspondence Alignment for Improved Virtual Try-On
Jiyoung Kim, Youngjin Shin, Siyoon Jin +6
Existing methods for Virtual Try-On (VTON) often struggle to preserve fine garment details, especially in unpaired settings where accurate person-garment correspondence is required…
Projected Representation Conditioning for High-fidelity Novel View Synthesis
Min-Seop Kwak, Minkyung Kwon, Jinhyeok Choi +2
We propose a novel framework for diffusion-based novel view synthesis in which we leverage external representations as conditions, harnessing their geometric and semantic correspon…
Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
Junwan Kim, Jiho Park, Seonghu Jeon +1
Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing a…
CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models
Minkyung Kwon, Jinhyeok Choi, Jiho Park +6
Multi-view diffusion models have recently emerged as a powerful paradigm for novel view synthesis, yet the underlying mechanism that enables their view-consistency remains unclear.…
Exploring Conditions for Diffusion models in Robotic Control
Heeseong Shin, Byeongho Heo, Dongyoon Han +2
While pre-trained visual representations have significantly advanced imitation learning, they are often task-agnostic as they remain frozen during policy learning. In this work, we…
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
Min-Seop Kwak, Junho Kim, Sangdoo Yun +4
We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require…
Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images
Jiwon Kim, Byeongho Heo, Sangdoo Yun +2
Semantic correspondence methods have advanced to obtaining high-quality correspondences employing complicated networks, aiming to maximize the model capacity. However, despite the…