Related papers: SimLOD: Simultaneous LOD Generation and Rendering

Real-time video analytics on the edge is challenging as the computationally constrained resources typically cannot analyse video streams at full fidelity and frame rate, which results in loss of accuracy. This paper proposes a Transprecise…

In video generation models, particularly world models, training large-scale video diffusion Transformers (such as DiT and MMDiT) poses significant computational challenges due to the extreme variance in sequence lengths within mixed-mode…

Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision. The progress of deep learning (DL) has impressively improved the…

Low-latency instance segmentation of LiDAR point clouds is crucial in real-world applications because it serves as an initial and frequently-used building block in a robot's perception pipeline, where every task adds further delay.…

Embodied vision-based real-world systems, such as mobile robots, require a careful balance between energy consumption, compute latency, and safety constraints to optimize operation across dynamic tasks and contexts. As local computation…

Point cloud scene flow estimation is fundamental to long-term and fine-grained 3D motion analysis. However, existing methods are typically limited to pairwise settings and struggle to maintain temporal consistency over long sequences as…

Real-time streaming of point cloud video, characterized by massive data volumes and high sensitivity to packet loss, remains a key challenge for immersive applications under dynamic network conditions. While connection-oriented protocols…

We address the challenges associated with deploying neural networks on CPUs, with a particular focus on minimizing inference time while maintaining accuracy. Our novel approach is to use the dataflow (i.e., computation order) of a neural…

Multi-task learning (MTL) aims at solving multiple related tasks simultaneously and has experienced rapid growth in recent years. However, MTL models often suffer from performance degeneration with negative transfer due to learning several…

Continual Learning (CL) aims to learn new data while remembering previously acquired knowledge. In contrast to CL for image classification, CL for Object Detection faces additional challenges such as the missing annotations problem. In this…

Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…

Implicit neural networks have been successfully used for surface reconstruction from point clouds. However, many of them face scalability issues as they encode the isosurface function of a whole object or scene into a single latent vector.…

In distributed multimedia applications, content is often delivered to users in a degraded form due to network-induced lossy compression. Real-time and interactive use cases like cloud gaming, which render content on the fly, require low…

On-device continual learning (CL) is critical for edge AI systems operating on non-stationary data streams, but most existing methods rely on backpropagation or exemplar-heavy classifiers, incurring substantial compute, memory, and latency…

Research in manipulation of deformable objects is typically conducted on a limited range of scenarios, because handling each scenario on hardware takes significant effort. Realistic simulators with support for various types of deformations…

Region proposal is critical for object detection while it usually poses a bottleneck in improving the computation efficiency on traditional control-flow architectures. We have observed region proposal tasks are potentially suitable for…

Scene flow represents the motion information of each point in the 3D point clouds. It is a vital downstream method applied to many tasks, such as motion segmentation and object tracking. However, there are always occlusion points between…

Diffusion models have exhibited remarkable prowess in visual generalization. Building on this success, we introduce an instruction-based object addition pipeline, named Add-SD, which automatically inserts objects into realistic scenes with…

Our project page: https://scutyklin.github.io/SceneLCM/. Automated generation of complex, interactive indoor scenes tailored to user prompt remains a formidable challenge. While existing methods achieve indoor scene synthesis, they struggle…

Room layout estimation is a long-existing robotic vision task that benefits both environment sensing and motion planning. However, layout estimation using point clouds (PCs) still suffers from data scarcity due to annotation difficulty. As…