Related papers: Transferable End-to-end Room Layout Estimation via…

Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision. This is often achieved by employing Structure from Motion (SfM) or Simultaneous Localization and Mapping…

Planning with LLMs is bottlenecked by token-by-token generation and repeated full forward passes, making multi-step lookahead and rollout-based search expensive in latency and compute. We propose EmbedPlan, which replaces autoregressive…

In this paper, we investigate video analytics in low-light environments, and propose an end-edge coordinated system with joint video encoding and enhancement. It adaptively transmits low-light videos from cameras and performs enhancement…

In this paper a semi-supervised deep framework is proposed for the problem of 3D shape inverse rendering from a single 2D input image. The main structure of proposed framework consists of unsupervised pre-trained components which…

Unsupervised domain adaptation remains a critical challenge in enabling the knowledge transfer of models across unseen domains. Existing methods struggle to balance the need for domain-invariant representations with preserving…

Matching images and sentences demands a fine understanding of both modalities. In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply…

Solving the camera-to-robot pose is a fundamental requirement for vision-based robot control, and is a process that takes considerable effort and cares to make accurate. Traditional approaches require modification of the robot via markers,…

End-to-end multimodal learning on knowledge graphs has been left largely unaddressed. Instead, most end-to-end models such as message passing networks learn solely from the relational information encoded in graphs' structure: raw values, or…

Domain adaptation is one of the prominent strategies for handling both domain shift, that is widely encountered in large-scale land use/land cover map calculation, and the scarcity of pixel-level ground truth that is crucial for supervised…

Learning systems often expand their ambient features or latent representations over time, embedding earlier representations into larger spaces with limited new latent structure. We study transfer learning for structured matrix estimation…

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not…

We present the first end to end approach for real time material estimation for general object shapes with uniform material that only requires a single color image as input. In addition to Lambertian surface properties, our approach fully…

Autonomous parking is a crucial task in the intelligent driving field. Traditional parking algorithms are usually implemented using rule-based schemes. However, these methods are less effective in complex parking scenarios due to the…

Inherent ambiguity in layout annotations poses significant challenges to developing accurate 360{\deg} room layout estimation models. To address this issue, we propose a novel Bi-Layout model capable of predicting two distinct layout types.…

High-resolution images for remote sensing applications are often not affordable or accessible, especially when in need of a wide temporal span of recordings. Given the easy access to low-resolution (LR) images from satellites, many remote…

Recent advances of image-to-image translation focus on learning the one-to-many mapping from two aspects: multi-modal translation and multi-domain translation. However, the existing methods only consider one of the two perspectives, which…

Latent-space interpolation is commonly used to demonstrate the generalization ability of deep latent variable models. Various algorithms have been proposed to calculate the best trajectory between two encodings in the latent space. In this…

We present a new pipeline for holistic 3D scene understanding from a single image, which could predict object shapes, object poses, and scene layout. As it is a highly ill-posed problem, existing methods usually suffer from inaccurate…

We tackle the task of semantic alignment where the goal is to compute dense semantic correspondence aligning two images depicting objects of the same category. This is a challenging task due to large intra-class variation, changes in…

We present LaLaLoc to localise in environments without the need for prior visitation, and in a manner that is robust to large changes in scene appearance, such as a full rearrangement of furniture. Specifically, LaLaLoc performs…