Related papers: Fast Neural Scene Flow

Dynamic scene understanding is one of the most conspicuous field of interest among computer vision community. In order to enhance dynamic scene understanding, pixel-wise segmentation with neural networks is widely accepted. The latest…

Optical flow provides information on relative motion that is an important component in many computer vision pipelines. Neural networks provide high accuracy optical flow, yet their complexity is often prohibitive for application at the edge…

3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors. Unlike optical flow, the data is usually sparse and in most cases partially occluded in between two temporal samplings. Here we propose a…

Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks. In such framework, besides the regular ConvNets responsible for RGB frame inputs, a…

Scene flow estimation has been receiving increasing attention for 3D environment perception. Monocular scene flow estimation -- obtaining 3D structure and 3D motion from two temporally consecutive images -- is a highly ill-posed problem,…

Scene flow is the dense 3D reconstruction of motion and geometry of a scene. Most state-of-the-art methods use a pair of stereo images as input for full scene reconstruction. These methods depend a lot on the quality of the RGB images and…

State-of-the-art neural implicit surface representations have achieved impressive results in indoor scene reconstruction by incorporating monocular geometric priors as additional supervision. However, we have observed that multi-view…

Motion detection is a fundamental but challenging task for autonomous driving. In particular scenes like highway, remote objects have to be paid extra attention for better controlling decision. Aiming at distant vehicles, we train a neural…

We reframe scene flow as the task of estimating a continuous space-time ODE that describes motion for an entire observation sequence, represented with a neural prior. Our method, EulerFlow, optimizes this neural prior estimate against…

Neural Ordinary Differential Equations (NODEs) often struggle to adapt to new dynamic behaviors caused by parameter changes in the underlying physical system, even when these dynamics are similar to previously observed behaviors. This…

In recent years, deep neural networks showed their exceeding capabilities in addressing many computer vision tasks including scene flow prediction. However, most of the advances are dependent on the availability of a vast amount of dense…

Anticipating the future in a dynamic scene is critical for many fields such as autonomous driving and robotics. In this paper we propose a class of novel neural network architectures to predict future LiDAR frames given previous ones. Since…

Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take…

In the last decades, scene text recognition has gained worldwide attention from both the academic community and actual users due to its importance in a wide range of applications. Despite achievements in optical character recognition, scene…

We propose an application of online hard sample mining for efficient training of Neural Radiance Fields (NeRF). NeRF models produce state-of-the-art quality for many 3D reconstruction and rendering tasks but require substantial…

Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or…

Neural 3D implicit representations learn priors that are useful for diverse applications, such as single- or multiple-view 3D reconstruction. A major downside of existing approaches while rendering an image is that they require evaluating…

State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we push the limits of scene flow estimation.…

The Forward-Forward (FF) algorithm was recently proposed as a local learning method to address the limitations of backpropagation (BP), offering biological plausibility along with memory-efficient and highly parallelized computational…

Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes. It takes long per-scene training time and per-image testing time. In this paper, we present EfficientNeRF as an…