84 citations · 92 across the 5 of their papers we have counts for
8 papers · 1 filter
ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation
Seunghun Lee, Wonhyeok Choi, Changjae Kim +2
In this paper, we present a direct adaptation strategy (ADAS), which aims to directly adapt a single model to multiple target domains in a semantic segmentation task without pretra…
VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction
Jaesung Choe, Sunghoon Im, Francois Rameau +2
To reconstruct a 3D scene from a set of calibrated views, traditional multi-view stereo techniques rely on two distinct stages: local depth maps computation and global depth maps f…
DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation
Seunghun Lee, Sunghyun Cho, Sunghoon Im
In this paper, we present DRANet, a network architecture that disentangles image representations and transfers the visual attributes in a latent space for unsupervised cross-domain…
Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency
Seokju Lee, Sunghoon Im, Stephen Lin +1
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervis…
Instance-wise Depth and Motion Learning from Monocular Videos
Seokju Lee, Sunghoon Im, Stephen Lin +1
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervis…
Learning Residual Flow as Dynamic Motion from Stereo Videos
Seokju Lee, Sunghoon Im, Stephen Lin +1
We present a method for decomposing the 3D scene flow observed from a moving stereo rig into stationary scene elements and dynamic object motion. Our unsupervised learning framewor…