20 papers
GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion
Yeji Choi, Jinhyeok Choi, Jaewon Min +3
We present GeoFace, a geometry-constrained multi-view diffusion framework for consistent face generation from a single input. % While recent multi-view diffusion models achieve pho…
TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling
Hyunmin Cho, Donghoon Ahn, Susung Hong +3
Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time guidance methods rely on external…
Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
Jin Hyeon Kim, Jaeeun Lee, Claire Kim +8
Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typically trained and evaluated un…
Looped Diffusion Language Models
Sanghyun Lee, Chunsan Hong, Seungryong Kim +3
Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models for language modeling, yet the effective design of transformer architectures for MDM…
WorldKV: Efficient World Memory with World Retrieval and Compression
Jung Yi, Minjae Kim, Paul Hyunbin Cho +3
Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a previously seen viewpo…
Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation
Youngdong Jang, Gyeongrok Oh, Jong Wook Kim +6
LiDAR scene flow estimation is essential for autonomous driving, as it provides 3D motion for each point. Self-supervised approaches use static-dynamic classification to mitigate t…