Selected Publications

For learning single image depth predictor from monocular sequences, we show that the depth CNN predictor can be learned without a pose CNN predictor, by incorporating a differentiable implementation of DVO, along with a novel depth normalization strategy.
CVPR 2018

We provide the first approach of its kind (to our knowledge) for semantic object-centric PBA on natural sequences – which gives the global 6DoF camera poses of each frame and the dense 3D shape, with PBA-like accuracy but denser depth maps.
arXiv preprint

In this paper we define the new task of pose-aware shape reconstruction from a single image, and we design architectures of pose-aware shape reconstruction using weak constraint from reprojecting the predicted shape back on to the image with the predicted pose.
ICCV 2017 [Spotlight]

We introduce learned shape prior in the form of deep shape generators into Photometric Bundle Adjustment (PBA) and propose to accommodate full 3D shape generated by the shape prior within the optimization-based inference framework, demonstrating impressive results.
WACV 2018


Learning Depth from Monocular Videos using Direct Methods. . CVPR 2018

Preprint Code Project

Semantic Photometric Bundle Adjustment on Natural Sequences. . arXiv preprint

Preprint PDF

Rethinking Reprojection: Closing the Loop for Pose-aware Shape Reconstruction from a Single Image. . ICCV 2017 [Spotlight]

PDF Poster Slides Video

Object-Centric Photometric Bundle Adjustment with Deep Shape Prior. . WACV 2018


Structure from Category: A Generic and Prior-less Approach. . In 3DV 2016

PDF Code Poster

The Conditional Lucas & Kanade Algorithm. . ECCV 2016

PDF Code Project