18 accepted papers
Text-to-video (T2V) generation aims to synthesize videos with high visual quality and temporal consistency that are semantically aligned with input text. Reward-based post-training has emerged as a promising direction to improve the quality and semantic alignment of generated videos. However, recent…
Recent advances in 3D vision-language models (VLMs) highlight a strong potential for 3D scene understanding and reasoning.However, effectively tokenizing 3D scenes into holistic scene tokens, and leveraging these tokens across diverse 3D understanding tasks, remain highly challenging. We present NDT
Generating dynamic 4D objects from sparse inputs is difficult because it demands joint preservation of appearance and motion coherence across views and time while suppressing artifacts and temporal drift. We hypothesize that the view discrepancy arises from supervision limited to pixel- or latent-sp
Long Video Temporal Grounding (LVTG) aims at identifying specific moments within lengthy videos based on user-provided text queries for effective content retrieval. The approach taken by existing methods of dividing video into clips and processing each clip via a full-scale expert encoder is challen…
The difficulty in identifying lymph node malignancies, including lymphoma and metastatic tumors, pose a diagnostic challenge at their primary sites. Given the heterogeneity of lymph node structures across different regions and the difficulty in distinguishing them from surrounding tissues, accurate…
Most existing Dynamic Gaussian Splatting methods for complex dynamic urban scenarios rely on accurate object-level supervision from expensive manual labeling, limiting their scalability in real-world applications. In this paper, we introduce SplatFlow, a Self-Supervised Dynamic Gaussian Splatting wi…
In this paper we present a novel indoor 3D reconstruction method with occluded surface completion given a sequence of depth readings. Prior state-of-the-art (SOTA) methods only focus on the reconstruction of the visible areas in a scene neglecting the invisible areas due to the occlusions e.g. the c…
"Monocular 3D reconstruction for categorical objects heavily relies on accurately perceiving each object’s pose. While gradient-based optimization in a NeRF framework updates the initial pose, this paper highlights that scale-depth ambiguity in monocular object reconstruction causes failures when th…
A major challenge in monocular 3D object detection is the limited diversity and quantity of objects in real datasets. While augmenting real scenes with virtual objects holds promise to improve both the diversity and quantity of the objects, it remains elusive due to the lack of an effective 3D objec…
In this paper, we tackle the control and trajectory planning problems for the cooperative transportation system of cable-suspended payload with multi Unmanned Aerial Vehicles (UAVs). Firstly, a payload controller is presented considering the dynamic coupling between the UAV and the payload to accomp…
This paper proposes a novel monocular teach-and-repeat navigation system with the capability of scale awareness, i.e. the absolute distance between observation and goal images. It decomposes the navigation task into a sequence of visual servoing sub-tasks to approach consecutive goal/node images in…
3D point cloud-based place recognition is highly demanded by autonomous driving in GPS-challenged environments and serves as an essential component (i.e. loop-closure detection) in lidar-based SLAM systems. This paper proposes a novel approach, named NDT-Transformer, for real-time and large-scale pl…
This paper presents a robust monocular visual teach-and-repeat (VT&R) navigation system for long-term operation in outdoor environments. The approach leverages deep-learned descriptors to deal with the high illumination variance of the real world. In particular, a tailored self-supervised descriptor…
Robot-assisted endobronchial intervention requires accurate localization based on both intra- and pre-operative data. Most existing methods achieve this by registering 2D videos with 3D CT models according to a defined similarity metric with local features. Instead, we formulate the bronchoscopic lo
In order to integrate uncertainty estimates into deep time-series modelling, Kalman Filters (KFs) (Kalman et al., 1960) have been integrated with deep learning models, however, such approaches typically rely on approximate inference tech- niques such as variational inference which makes learning mor…
This paper introduces a fully deep learning approach to monocular SLAM, which can perform simultaneous localization using a neural network for learning visual odometry (L-VO) and dense 3D mapping. Dense 2D flow and a depth image are generated from monocular images by sub-networks, which are then use…
This letter presents a novel semantic mapping approach, Recurrent-OctoMap, learned from long-term three-dimensional (3-D) Lidar data. Most existing semantic mapping approaches focus on improving semantic understanding of single frames, rather than 3-D refinement of semantic maps (i.e. fusing semanti
Dual-band and multi-band power amplifiers (PAs) becomes popular as they can effectively reduce the equipment cost and operation cost. On the other hand, the nonlinear interference among signals in different bands needs special attention. Previous modeling results [1] suffer performance degradation w…