39 citations · 76 across the 18 of their papers we have counts for
9 papers · 2 filters
MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation
Rajeev Yasarla, Hong Cai, Jisoo Jeong +3
We propose MAMo, a novel memory and attention frame-work for monocular video depth estimation. MAMo can augment and improve any single-image depth estimation networks into video de…
OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding
Minghua Liu, Ruoxi Shi, Kaiming Kuang +6
We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framew…
X-Align++: cross-modal cross-view alignment for Bird's-eye-view segmentation
Shubhankar Borse, Senthil Yogamani, Marvin Klingner +4
Bird's-eye-view (BEV) grid is a typical representation of the perception of road components, e.g., drivable area, in autonomous driving. Most existing approaches rely on cameras on…
EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation
Yunxiao Shi, Hong Cai, Amin Ansari +1
The ubiquitous multi-camera setup on modern autonomous vehicles provides an opportunity to construct surround-view depth. Existing methods, however, either perform independent mono…
Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation
Liwen Wu, Rui Zhu, Mustafa B. Yaldiz +7
Inverse path tracing has recently been applied to joint material and lighting estimation, given geometry and multi-view HDR observations of an indoor scene. However, it has two maj…
DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction
Shubhankar Borse, Debasmit Das, Hyojin Park +3
We present DejaVu, a novel framework which leverages conditional image regeneration as additional supervision during training to improve deep networks for dense prediction tasks su…
DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling
Jisoo Jeong, Hong Cai, Risheek Garrepalli +1
We propose a novel data augmentation approach, DistractFlow, for training optical flow estimation models by introducing realistic distractions to the input frames. Based on a mixin…
4D Panoptic Segmentation as Invariant and Equivariant Field Prediction
Minghan Zhu, Shizhong Han, Hong Cai +3
In this paper, we develop rotation-equivariant neural networks for 4D panoptic segmentation. 4D panoptic segmentation is a benchmark task for autonomous driving that requires recog…
TransAdapt: A Transformative Framework for Online Test Time Adaptive Semantic Segmentation
Debasmit Das, Shubhankar Borse, Hyojin Park +4
Test-time adaptive (TTA) semantic segmentation adapts a source pre-trained image semantic segmentation model to unlabeled batches of target domain test images, different from real-…