4 papers
Grid-Preserving Knowledge Distillation: Transferring Convolutional Inductive Bias to Vision Transformers under Data Scarcity
Junyong Choi, Cheolhyeon Park, Jaehoon Cho
Vision Transformers demonstrate remarkable global modeling capacity but often underperform in data-scarce regimes. Distilling convolutional inductive biases from a CNN teacher prov…
PLOT: Pseudo-Labeling via Object Tracking for Monocular 3D Object Detection
Seokyeong Lee, Sithu Aung, Junyong Choi +3
Monocular 3D object detection is crucial for scalable perception across fields like autonomous driving, robotics, and surveillance. However, progress is hindered by limited 3D anno…
Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes
JunYong Choi, Min-Cheol Sagong, SeokYeong Lee +3
We propose a diffusion-based inverse rendering framework that decomposes a single RGB image into geometry, material, and lighting. Inverse rendering is inherently ill-posed, making…
MAIR++: Improving Multi-view Attention Inverse Rendering with Implicit Lighting Representation
JunYong Choi, SeokYeong Lee, Haesol Park +3
In this paper, we propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, SVBRDF, and 3D spatially-varying lighting. Whi…