5 papers
Early Failure Detection and Intervention in Video Diffusion Models
Kwon Byung-Ki, Sohwi Lim, Nam Hyeon-Woo +2
Text-to-video (T2V) diffusion models have rapidly advanced, yet generations still occasionally fail in practice, such as low text-video alignment or low perceptual quality. Since d…
HDR-NSFF: High Dynamic Range Neural Scene Flow Fields
Shin Dong-Yeon, Kim Jun-Seong, Kwon Byung-Ki +1
Radiance of real-world scenes typically spans a much wider dynamic range than what standard cameras can capture. While conventional HDR methods merge alternating-exposure frames, t…
JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers
Kwon Byung-Ki, Qi Dai, Lee Hyoseok +2
We present JointDiT, a diffusion transformer that models the joint distribution of RGB and depth. By leveraging the architectural benefit and outstanding image prior of the state-o…
Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior
Lee Hyoseok, Kyeong Seon Kim, Kwon Byung-Ki +1
Depth completion, predicting dense depth maps from sparse depth measurements, is an ill-posed problem requiring prior knowledge. Recent methods adopt learning-based approaches to i…
Learning-based Axial Video Motion Magnification
Kwon Byung-Ki, Oh Hyun-Bin, Kim Jun-Seong +2
Video motion magnification amplifies invisible small motions to be perceptible, which provides humans with a spatially dense and holistic understanding of small motions in the scen…