In this paper we learn to segment hands and hand-held objects from motion. Our system takes a single RGB image and hand location as input to segment the hand and hand-held object. For learning, we generate responsibility maps that show how well a hand's motion explains other pixels' motion in video. We use these responsibility maps as pseudo-labels to train a weakly-supervised neural network using an attention-based similarity loss and contrastive loss. Our system outperforms alternate methods, achieving good performance on the 100DOH, EPIC-KITCHENS, and HO3D datasets.

We organize our supplementary material as follows: In Section A, we present more analytical results on VSPW dataset. In Section B, we provide more ablation studies on Cityscapes dataset. In Section D, we provide computational cost analysis and training details. In Section E, we provide comparison with bi-directional optical flow. A.1 Explanation of Video Consistency Following [3], we use Video Consistency (VC) to evaluate the category consistency among adjacent frames in the videos.

Video Semantic Segmentation (VSS) involves assigning a semantic label to each pixel in a video sequence. Prior work in this field has demonstrated promising results by extending image semantic segmentation models to exploit temporal relationships across video frames; however, these approaches often incur significant computational costs. In this paper, we propose an efficient mask propagation framework for VSS, called MPVSS. Our approach first employs a strong querybased image segmentor on sparse key frames to generate accurate binary masks and class predictions. We then design a flow estimation module utilizing the learned queries to generate a set of segment-aware flow maps, each associated with a mask prediction from the key frame.

Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their dependence on precise camera poses from structure-from-motion, which is prohibitively expensive to run at scale. We propose a method that jointly reconstructs camera poses and 3D neural scene representations online and in a single forward pass. We estimate poses by first lifting frame-to-frame optical flow to 3D scene flow via differentiable rendering, preserving locality and shift-equivariance of the image processing backbone. SE(3) camera pose estimation is then performed via a weighted least-squares fit to the scene flow field. This formulation enables us to jointly supervise pose estimation and a generalizable neural scene representation via re-rendering the input video, and thus, train end-to-end and fully self-supervised on real-world video datasets. We demonstrate that our method performs robustly on diverse, real-world video, notably on sequences traditionally challenging to optimization-based pose estimation techniques.

This paper presents a simple, self-supervised method for magnifying subtle motions in video: given an input video and a magnification factor, we manipulate the video such that its new optical flow is scaled by the desired amount. To train our model, we propose a loss function that estimates the optical flow of the generated video and penalizes how far if deviates from the given magnification factor. Thus, training involves differentiating through a pretrained optical flow network. Since our model is self-supervised, we can further improve its performance through test-time adaptation, by finetuning it on the input video. It can also be easily extended to magnify the motions of only user-selected objects. Our approach avoids the need for synthetic magnification datasets that have been used to train prior learning-based approaches.

Neural Information Processing Systems http://nips.cc/