Extensive experiments on real and synthetic data show that, despite only using noisy bursts during training, models trained with our self-supervised strategy match, and sometimes surpass, the quality of fully-supervised baselines trained with synthetic data or weakly-paired ground-truth.
These approaches however suffer from ``catastrophic forgetting'' issue due to finetuning of base detector, leading to sub-optimal performance on the base classes.
Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function.
Ranked #18 on Visual Object Tracking on LaSOT (Precision metric)
The deep reparametrization allows us to directly model the image formation process in the latent space, and to integrate learned image priors into the prediction.
Ranked #4 on Burst Image Super-Resolution on BurstSR
no code implementations • 7 Jun 2021 • Goutam Bhat, Martin Danelljan, Radu Timofte, Kazutoshi Akita, Wooyeong Cho, Haoqiang Fan, Lanpeng Jia, Daeshik Kim, Bruno Lecouat, Youwei Li, Shuaicheng Liu, Ziluan Liu, Ziwei Luo, Takahiro Maeda, Julien Mairal, Christian Micheloni, Xuan Mo, Takeru Oba, Pavel Ostyakov, Jean Ponce, Sanghyeok Son, Jian Sun, Norimichi Ukita, Rao Muhammad Umer, Youliang Yan, Lei Yu, Magauiya Zhussip, Xueyi Zou
This paper reviews the NTIRE2021 challenge on burst super-resolution.
We propose a novel architecture for the burst super-resolution task.
Ranked #6 on Burst Image Super-Resolution on SyntheticBurst
This effectively limits the performance and generalization capabilities of existing video segmentation methods.
This allows us to achieve a rich internal representation of the target in the current frame, significantly increasing the segmentation accuracy of our approach.
Such approaches are however prone to fail in case of e. g. fast appearance changes or presence of distractor objects, where a target appearance model alone is insufficient for robust tracking.
Ranked #8 on Object Tracking on FE108
In our proposed approach, we create an energy-based model of the conditional target density p(y|x), using a deep neural network to predict the un-normalized density from (x, y).
Ranked #1 on Object Detection on COCO test-dev (Hardware Burden metric)
The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking.
Ranked #5 on Object Tracking on FE108
We argue that this approach is fundamentally limited since target estimation is a complex task, requiring high-level knowledge about the object.
Ranked #7 on Object Tracking on FE108
Recent attempts, based on 3D deep learning approaches (3D-CNNs), have achieved below-expected results.
Ranked #15 on Semantic Segmentation on Semantic3D
Moreover, our fast variant, using hand-crafted features, operates at 60 Hz on a single CPU, while obtaining 65. 0% AUC on OTB-2015.
Ranked #12 on Visual Object Tracking on VOT2017/18