Related papers: RAFT-MSF: Self-Supervised Monocular Scene Flow usi…

A significant challenge facing current optical flow methods is the difficulty in generalizing them well to the real world. This is mainly due to the high cost of hand-crafted datasets, and existing self-supervised methods are limited by…

State-of-the-art self-supervised learning approaches for monocular depth estimation usually suffer from scale ambiguity. They do not generalize well when applied on distance estimation for complex projection models such as in fisheye and…

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…

The research on neural radiance fields for new view synthesis has experienced explosive growth with the development of new models and extensions. The NERF algorithm, suitable for underwater scenes or scattering media, is also evolving.…

Scene depth estimation from stereo and monocular imagery is critical for extracting 3D information for downstream tasks such as scene understanding. Recently, learning-based methods for depth estimation have received much attention due to…

Depth estimation plays an important role in the robotic perception system. Self-supervised monocular paradigm has gained significant attention since it can free training from the reliance on depth annotations. Despite recent advancements,…

Dense depth estimation from a single image is a key problem in computer vision, with exciting applications in a multitude of robotic tasks. Initially viewed as a direct regression problem, requiring annotated labels as supervision at…

Nighttime self-supervised monocular depth estimation has received increasing attention in recent years. However, using night images for self-supervision is unreliable because the photometric consistency assumption is usually violated in the…

Over the past few years, self-supervised monocular depth estimation that does not depend on ground-truth during the training phase has received widespread attention. Most efforts focus on designing different types of network architectures…

Recently, neural network for scene flow estimation show impressive results on automotive data such as the KITTI benchmark. However, despite of using sophisticated rigidity assumptions and parametrizations, such networks are typically…

In this paper, we focus on designing effective method for fast and accurate scene parsing. A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation. Two strategies are widely…

We study the problem of self-supervised 3D scene flow estimation from real large-scale raw point cloud sequences, which is crucial to various tasks like trajectory prediction or instance segmentation. In the absence of ground truth scene…

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for…

We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video. We model the object motion as a 6 degree-of-freedom rigid-body transformation. The instance segmentation mask is…

Accurate estimation of large displacement optical flow remains a critical challenge. Existing methods typically rely on iterative local search or/and domain-specific fine-tuning, which severely limits their performance in large displacement…

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…

Learning accurate scene reconstruction without pose priors in neural radiance fields is challenging due to inherent geometric ambiguity. Recent development either relies on correspondence priors for regularization or uses off-the-shelf flow…

Self-supervised monocular depth estimation has gathered notable interest since it can liberate training from dependency on depth annotations. In monocular video training case, recent methods only conduct view synthesis between existing…

Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams. Based on multi-layers…

Unsupervised localization and segmentation are long-standing robot vision challenges that describe the critical ability for an autonomous robot to learn to decompose images into individual objects without labeled data. These tasks are…